Sustainability 15 13484 v2

sustainability
Article
The Application of AutoML Techniques in Diabetes Diagnosis:
Current Approaches, Performance, and Future Directions
Lily Popova Zhuhadar 1 and Miltiadis D. Lytras 2, *
1 Center for Applied Data Analytics, Western Kentucky University, Bowling Green, KY 42101, USA;
lily.popova.zhuhadar@wku.edu
2 Effat College of Engineering, Effat University, Jeddah P.O. Box 34689, Saudi Arabia
* Correspondence: mlytras@effatuniversity.edu.sa
Abstract: Artificial Intelligence (AI) has experienced rapid advancements in recent years, facilitating
the creation of innovative, sustainable tools and technologies across various sectors. Among these
applications, the use of AI in healthcare, particularly in the diagnosis and management of chronic
diseases like diabetes, has shown significant promise. Automated Machine Learning (AutoML),
with its minimally invasive and resource-efficient approach, promotes sustainability in healthcare
by streamlining the process of predictive model creation. This research paper delves into advance-
ments in AutoML for predictive modeling in diabetes diagnosis. It illuminates their effectiveness in
identifying risk factors, optimizing treatment strategies, and ultimately improving patient outcomes
while reducing environmental footprint and conserving resources. The primary objective of this
scholarly inquiry is to meticulously identify the multitude of factors contributing to the development
of diabetes and refine the prediction model to incorporate these insights. This process fosters a
comprehensive understanding of the disease in a manner that supports the principles of sustainable
healthcare. By analyzing the provided dataset, AutoML was able to select the most fitting model, em-
phasizing the paramount importance of variables such as Glucose, BMI, DiabetesPedigreeFunction,
and BloodPressure in determining an individual’s diabetic status. The sustainability of this process
lies in its potential to expedite treatment, reduce unnecessary testing and procedures, and ultimately
foster healthier lives. Recognizing the importance of accuracy in this critical domain, we propose that
supplementary factors and data be rigorously evaluated and incorporated into the assessment. This
Citation: Zhuhadar, L.P.; Lytras, M.D.
approach aims to devise a model with enhanced accuracy, further contributing to the efficiency and
The Application of AutoML
sustainability of healthcare practices.
Techniques in Diabetes Diagnosis:
Current Approaches, Performance,
Keywords: AutoML; artificial intelligence; predictive modeling; deep learning; diabetes diagnosis
and Future Directions. Sustainability
2023, 15, 13484. https://doi.org/
10.3390/su151813484
Academic Editor: Petra Poulová 1. Introduction

Received: 19 May 2023 1.1. Research Objectives
Revised: 28 August 2023 Diabetes mellitus is a chronic metabolic disorder affecting millions of people world-
Accepted: 4 September 2023 wide, posing significant challenges for healthcare systems [1]. Diabetes, a relentless chronic
Published: 8 September 2023 ailment, surfaces either when the pancreas fails to generate adequate insulin or when the
body is inefficient in capitalizing on the insulin produced. Regrettably, no cure has been
discovered for this disease yet. Diabetes is generally conceived as an outcome of a com-
plex interplay between genetic predispositions and environmental triggers [2]. Numerous
Copyright: © 2023 by the authors.
risk factors associated with diabetes span across ethnicity, family history, advancing age,
Licensee MDPI, Basel, Switzerland.
excessive weight, poor dietary choices, lack of physical activity, and smoking habits [3].
This article is an open access article
Significantly, the lack of early detection of diabetes not only worsens the disease prognosis
distributed under the terms and
conditions of the Creative Commons
but also sets the stage for the development of further chronic conditions such as kidney
Attribution (CC BY) license (https://
disease [4]. Patients suffering from pre-existing non-communicable diseases occupy an
creativecommons.org/licenses/by/ exceptionally vulnerable position. Their susceptibility to infectious diseases, including
4.0/).
Sustainability 2023, 15, 13484. https://doi.org/10.3390/su151813484 https://www.mdpi.com/journal/sustainability

Sustainability 2023, 15, 13484 2 of 24
but not limited to the formidable COVID-19, is significantly heightened [5]. Therefore, ap-
praising the risk factors and potential susceptibility to chronic conditions, such as diabetes,
becomes an area of critical importance within the healthcare domain. An early diagnosis of
these chronic ailments offers twofold benefits: it aids in mitigating future medical costs, and
concurrently decreases the likelihood of exacerbating health complications, thus ensuring
the maintenance of a patient’s quality of life. These insights equip healthcare professionals
with valuable data, enabling them to make more informed, strategic decisions about patient
treatment. This is crucial in high-risk scenarios, where the right decisions can make a
significant difference in patient outcomes.
Recent advancements in AI and machine learning algorithms have paved the way
for more accurate and efficient predictive models in the diagnosis and management of
diabetes [6]. While machine learning offers innovative solutions across various sectors, a
significant level of distrust persists among certain groups. This skepticism primarily arises
from the ‘black-box’ nature of these models, characterized by their opaqueness in revealing
internal decision-making processes. Such a lack of explainability can lead to apprehension
among potential users, particularly in the healthcare sector [7]. This sector’s slow adoption
of machine learning solutions is reflective of consumers’ wariness of technologies they
perceive as enigmatic and potentially fallible [8]. The need for transparency in machine
learning cannot be overstated, especially in a field as critical as healthcare. Here, errors
can have dire, often irreversible consequences. As such, the ability to elucidate the logic
and processes behind a machine learning prediction becomes vital. Providing insight
into the reasoning that drives these predictions is instrumental in fostering trust among
end-users. By achieving this, we can catalyze the broader acceptance and application of
machine learning solutions in healthcare, thereby maximizing their potential in advancing
patient care.
This research explores the development of an open-source, cloud-based platform for
creating highly accurate predictive classification models. This tool is geared towards assist-
ing healthcare professionals in early diabetes detection based on various risk indicators.
By providing a preliminary diagnosis, it enables medical practitioners to advise patients
on proactive measures, such as diet modification, exercise, and blood glucose monitoring.
The effectiveness of these classification models was assessed through multiple evaluative
measures, including accuracy, precision, recall, F-measure, confusion matrices, and the area
under the receiver operating characteristic (ROC) curve. This multifaceted evaluation was
essential for identifying the highest-performing classifier [9].
Insightful features instrumental in predicting diabetes severity were gleaned from
the most effective classification models. As a result, the platform is envisioned as an
invaluable resource for clinicians, empowering them with data-driven insights to provide
informed counsel and initiate effective treatment protocols for patients at a heightened risk
of diabetes or those requiring urgent intervention. Ultimately, this study strives to identify
the contributing factors to diabetes onset, thereby enhancing the accuracy of predictive
models and facilitating earlier, more effective intervention.
This study utilizes the Pima Indian Diabetes dataset, a notable benchmark in diabetes
research. The Pima Indians, an Indigenous group residing in Arizona, USA and Mexico,
have been found to exhibit an unusually high incidence rate of diabetes mellitus [10]. As
such, studies focusing on this group hold substantial relevance and potential for advancing
global health knowledge [11,12]. In particular, the dataset encompasses Pima Indian females
aged 21 and above. Not only does this dataset offer valuable insights into diabetes, but it
also serves as a crucial resource for understanding health patterns among underrepresented
minority or Indigenous communities.
The National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK [13]) is
diligently endeavoring to augment the precision of diabetes diagnosis by harnessing the
power of a meticulously curated dataset, replete with pertinent diagnostic measurements
that hold the key to unlocking a more refined understanding of the disease and its intricate
mechanisms. The ramifications of these findings possess the potential to transcend the
immediate interests of the NIDDK, extending to the broader medical community and, most
critically, to the patients whose lives could be significantly improved through enhanced
diagnostic precision.
As the investigation advances and a more expansive array of variables is scrutinized,
the prediction model is anticipated to undergo a continuous metamorphosis, thereby em-
powering medical professionals to manage diabetes risk more adeptly on an individual
level. This heightened diagnostic accuracy is poised to yield more tailored advice and
treatment modalities, ultimately ameliorating the lives of those afflicted by diabetes. While
novel factors will invariably emerge, the primary aspiration remains the unyielding refine-
ment and improvement of the model, ensuring its enduring applicability within the realms
of medical research and practice. The sustained investment in diabetes prediction modeling
is indisputably essential, given the profound implications for patients and the medical
community at large. By leveraging machine learning algorithms for predictive modeling in
diabetes diagnosis, healthcare professionals can harness the power of advanced analytics
to identify early warning signs and risk factors, ultimately enabling more accurate and
timely intervention strategies. In summation, this ambitious research venture harbors
immense potential for revolutionizing the future of diabetes diagnosis and management,
and the findings are poised to leave an indelible impact on the fields of medical research
and practice.
1.2. Scientific Context of the Study

In this segment of the paper, we plunge into the complex world of machine learn-
ing, considering it as a crucial facet within the realm of artificial intelligence (AI). Our
exploration commences with an overview of the current state of AI, clarifying its contempo-
rary advancements and direction. We then navigate the discourse towards a comparative
analysis of AI, machine learning, deep learning, and generative AI [14]. Through this
comparative lens, we illuminate their distinct features as well as their overlapping facets.
This comparison shines a light on their unique characteristics and shared elements, en-
abling us to appreciate the interconnectedness and individuality of these concepts. This
understanding is crucial in realizing the full potential of AI and its multifaceted aspects in
current and future applications.
As our discourse unfolds, we underscore the concept of AutoML, an innovative
tool that has become central to numerous sectors, including healthcare. By highlighting
specific instances, we illustrate the profound transformative influence AutoML has on these
industries, enabling efficiency and precision. As we approach the end of this section, we
turn our attention to the pressing issue of health inequity. We propose potential pathways
through which AutoML, when thoughtfully applied, could serve as a powerful tool in
mitigating this pervasive challenge. The overarching objective of this discourse is to inspire
a profound comprehension of the complex intersections among AI, AutoML, and health
equity, thus deepening our understanding of how these components can synergistically
work towards a more equitable future.
1.2.1. Comparative Analysis of AI, Machine Learning, Deep Learning, and Generative AI
In recent years, the disciplines of artificial intelligence (AI), machine learning (ML),
and deep learning (DL) have garnered substantial attention, establishing themselves as
focal points in the technology sector. These techniques, subsets of AI, are employed to
automate processes, predict outcomes, and derive insights from extensive datasets. The
preceding six months have witnessed a phenomenal surge in generative AI, most notably
marked by OpenAI’s “ChatGPT” [15]. Despite some shared characteristics, these areas
Sustainability 2023, 15, x FOR PEER REVIEW 4 of 24
exhibit profound differences. This section will elucidate the principal distinctions among
AI, ML, DL, and generative AI.
Artificial intelligence(AI),
Artificialintelligence (AI),a akey pillar
key pillarof computer
of computer science, represents
science, a complex
represents and
a complex
dynamic field that engages a wide array of techniques to empower machines
and dynamic field that engages a wide array of techniques to empower machines to ex- to exhibit
capabilities analogous
hibit capabilities to human
analogous cognition
to human (refer to(refer
cognition Figure
to 1). It incorporates
Figure methodsmeth-
1). It incorporates that
facilitate computational systems to replicate human-like behavior, ranging
ods that facilitate computational systems to replicate human-like behavior, ranging fromfrom basic task
execution
basic taskto advanced
execution toproblem
advanced solving
problemandsolving
decision making.
and decision making.
Figure1.1.AAcomparative
Figure comparativeview
view
of of
AI,AI, machine
machine learning,
learning, deepdeep learning,
learning, and generative
and generative AI (source
AI (source [16]).
[16]).
This field aims at creating systems that can intelligently analyze the environment,
learn This
fromfield aims at draw
experiences, creating systems understand
inferences, that can intelligently analyze the
complex concepts, andenvironment,
even exhibit
learn fromall
creativity, experiences,
of which were drawtraditionally
inferences, understand
considered complex
unique toconcepts, and even exhibit
human intelligence; it is
creativity, all
commonly of which
defined as a were traditionally
field that encompasses considered unique tothat
any technology human intelligence;
imparts human-like it is
cognitive
commonly abilities
defined to as
computers
a field that [17].
encompasses any technology that imparts human-like
The notion
cognitive oftoAI
abilities achieving[17].
computers human-level cognitive abilities has been popularized
throughThevarious
notion methodologies,
of AI achievingone of the mostcognitive
human-level notable ones being
abilities thebeen
has seminal—albeit
popularized
somewhat antiquated—Turing Test. This test, proposed by the
through various methodologies, one of the most notable ones being the seminal—albeitBritish mathematician Alan
Turing, gauges a machine’s ability to exhibit intelligent behavior
somewhat antiquated—Turing Test. This test, proposed by the British mathematician Alan that is indistinguishable
from thatgauges
Turing, of a human. Modern
a machine’s manifestations
ability of AI, such
to exhibit intelligent as Apple’s
behavior that Siri, exemplify this
is indistinguishable
notion quite
from that ofvividly.
a human. When we interact
Modern with Siri and
manifestations receive
of AI, such aascoherent
Apple’s response, it mirrors
Siri, exemplify this
anotion
human-like conversational
quite vividly. When weability,interactindicating
with Siri and how far AI
receive has evolved
a coherent in mimicking
response, it mirrors
human interaction.
a human-like conversational ability, indicating how far AI has evolved in mimicking hu-
Machine
man interaction. learning (ML), a significant subset of AI (refer to Figure 1), is primarily
concerned with deciphering
Machine learning (ML),patterns
a significantembedded
subset of within
AI (referdatasets.
to FigureThis
1),intricate process
is primarily con-
not only empowers machines to derive rules for optimal behavior
cerned with deciphering patterns embedded within datasets. This intricate process not but also equips them to
adapt to evolvingmachines
only empowers circumstancesto derivein the world.
rules The algorithms
for optimal behavior involved
but alsoinequips
this endeavor,
them to
while not novel in their inception, have been known and explored
adapt to evolving circumstances in the world. The algorithms involved in this endeavor,for decades and, in some
cases, centuries. However, it is the recent breakthroughs in the domain
while not novel in their inception, have been known and explored for decades and, in of computer science
and
some parallel
cases, computing that have imbued
centuries. However, these algorithms
it is the recent breakthroughs with in
thethe
capability
domainto ofoperate
computer at
an unprecedented scale. Now they can handle and analyze voluminous
science and parallel computing that have imbued these algorithms with the capability to datasets, a feat that
was previously
operate unattainable. This
at an unprecedented transformative
scale. Now they can advancement
handle and hasanalyze
significantly broadened
voluminous da-
the application and impact of ML, heralding a new era in the field
tasets, a feat that was previously unattainable. This transformative advancement has sig-of AI [18].
Deep learning (DL), a subset of ML (refer to Figure 1), operates through the utilization
nificantly broadened the application and impact of ML, heralding a new era in the field of
of intricate neural networks. In essence, it represents a set of interrelated techniques akin to
AI [18].
Deep learning (DL), a subset of ML (refer to Figure 1), operates through the utiliza-
tion of intricate neural networks. In essence, it represents a set of interrelated techniques
other methodological groups such as ‘Decision Trees’ or ‘Support Vector Machines’. The
recent surge in its popularity can be largely attributed to the significant strides made in
parallel computing. This has enabled DL techniques to handle larger datasets and perform
more complex computations, thereby resulting in heightened interest and widespread
application in the field. Nevertheless, there exists a significant differentiation between ML
and DL in terms of the learning methods they employ. ML algorithms typically utilize
either supervised or unsupervised learning approaches. In supervised learning, algorithms
are trained on labeled datasets, where each input data point is associated with a specific
output [19]. For example, an algorithm can be trained using a collection of labeled images of
cats and dogs, enabling it to predict whether a new image contains a cat or a dog. However,
unsupervised learning algorithms are employed when input data lack designated outputs,
and their purpose is to identify patterns within the data [19].
In the realm of DL, algorithms primarily leverage a form of supervised learning
known as deep neural networks. These networks are composed of multiple layers of
interconnected nodes designed to hierarchically process data. Each layer in the network
extracts features from the input data, which are then used by subsequent layers to further
refine the output. DL algorithms have the capacity to learn from unstructured data,
including images, audio, and text, making them versatile across various applications such
as image recognition, speech recognition, and natural language processing [20]. However,
a limitation of DL algorithms, as observed in studies, is their lack of interpretability [21].
Due to their autonomous learning nature, deciphering the decision-making process of deep
neural networks can be challenging, posing a significant obstacle in scenarios where end-
users or stakeholders require explanations for an algorithm’s decisions. Conversely, ML
algorithms often provide superior interpretability, as they are designed to make decisions
based on specific rules or criteria. For instance, the logic behind a Decision Tree algorithm,
which relies on a series of if–then statements, can be easily articulated and understood [22].
Moreover, DL algorithms have gained recognition for their remarkable accuracy and
performance in tasks involving image recognition and natural language processing. Their
ability to discern complex patterns and relationships within data contributes to this superior
performance, which may prove challenging for other types of algorithms [23].
However, it is essential to acknowledge that DL algorithms can be computationally
demanding and may require specialized hardware to achieve optimal accuracy and per-
formance [24]. In contrast, ML algorithms, while potentially lacking the same level of
accuracy or performance, generally exhibit higher speed and require fewer computational
resources. Despite these differences, ML algorithms remain effective in tasks such as
predictive modeling and anomaly detection.
Generative AI represents a subset of sophisticated DL models designed to produce
text, images, or code based on textual or visual inputs. Two leading frameworks in the
realm of generative AI currently dominate the field: generative adversarial networks
(GANs) and generative pre-trained transformers (GPTs) [25].
The concept of GANs, devised by Ian Goodfellow [26] in 2014, operates on the premise
of competition between two neural network sub-models. A generator model is tasked
with creating new content, while a discriminator model is charged with classifying this
content as real or counterfeit. These models engage in a perpetual learning cycle, consis-
tently enhancing their capabilities until the discriminator is unable to distinguish between
the output of the generator and authentic input examples. On the other hand, the GPT
framework is employed primarily for generative language modeling.
Generative AI’s main objective is to emulate human interaction. It operates using a
synergistic blend of supervised learning (predicting the subsequent word in a sentence
based on the preceding words) and unsupervised learning (discerning the structure of
language without explicit guidance or labels). Its capabilities are vast, ranging from
generating text and code, providing translations across various languages, creating a
diverse range of creative content, and engaging in conversational dialogue.
1.2.2. Why Is Generative AI Crucial in Today’s Technological Landscape?

The origin of generative AI can be traced back to the 1950s, when pioneers in computer
science began to experiment with Markov Chains algorithms [27] to generate novel data.
Despite its longstanding history, it is only in recent years that we have seen transformative
strides in generative AI’s performance and capabilities. This leap in progress has witnessed
its application in diverse fields, whether it be generating engaging narratives in text
generation [28], synthesizing melodious compositions in music generation [29], or crafting
visually engaging content in image generation [30,31]. However, the recent advancements
in AI technology now demand a reassessment of how we interact with our environment.
AI has bolstered computing capabilities, enhancing both speed and scalability [32–35]. In
bioinformatics, it has ushered in a revolution, allowing for rapid, accurate, and cost-effective
human genome sequencing [36–39].
By taking on routine tasks, AI has propelled workplace efficiency and productivity to
unprecedented levels [40,41], While these AI tools might not surpass human ingenuity yet,
they serve as vital enablers for innovation, design, and engineering, thereby considerably
amplifying human creativity and efficiency.
Cutting-edge generative AI technologies, such as GPT-4 and DALL-E 2, are designed
around machine learning algorithms that can autonomously produce novel content. GPT-4,
OpenAI’s most sophisticated large language model yet, excels in understanding and7using
Sustainability 2023, 15, x FOR PEER REVIEW of 24
context-appropriate words, thereby creating meaningful language that mirrors human
communication with striking accuracy. The vast potential of AI cannot be overstated.
Its applications span from driving breakthroughs in disease management to boosting
the k-nearest neighbors algorithm (KNN)) and b. optimization methods (these include
workplace performance. The promise that AI holds is profound and its implications far-
hyperparameter optimization and architecture optimization); for more details, refer to
reaching. While generative AI has yet to fully capture the nuances of human creativity, it
[47]. (4) Model evaluation: this consists of low-fidelity (Davis, 2019), early stopping (Nel-
has nonetheless emerged as a potent catalyst for innovation in various domains, including
son and Thompson, 2020), surrogate model (Martinez, 2021), and weight-sharing (Rivera
design and engineering. This thereby amplifies human inventiveness and productivity
and
(referSantos, 2022);
to Figure 2). for more details, refer to [48].
Figure 2. AutoML
AutoML workflow
workflow (source:
(source: [49]).
[42]).
1.2.3. AutoML
1.2.4. What Is Automated
and Its RoleMachine Learning?
in Healthcare
In the landscape
AutoML aims toof computational
automate intelligence,
the process the relevance
of selecting the bestand applicability
machine learningof algo-
deep
learning models have surged across diverse sectors, successfully addressing
rithms, optimizing hyperparameters, and managing data pre-processing. This automation complex AI
tasks. However, the creation of these intricate models often involves a labor-intensive,
reduces the time and expertise needed to develop effective models, making it an attractive trial-
and-error in
approach process conducted
healthcare, wheremanually
rapid and byaccurate
domaindecision
experts, making
a methodology
is crucialthat mandates
[20].
substantial resource allocation and an extensive time commitment. To circumnavigate
AutoML has become an essential tool in the medical field for identifying risk factors,
these challenges,
predicting diseasethe paradigm of
progression, AutoML
and guidinghas risen to prominence
treatment as a solution
strategies [50,51]. aiming of
In the context to
streamline and optimize the machine learning pipeline, refer to Figure 2 for an example of
diabetes diagnosis, AI-powered predictive models have been instrumental in detecting
machine learning pipeline [42]. The concept of AutoML, however, is interpreted differently
early signs of the disease and assisting clinicians in making data-driven decisions [52].
by different sectors of the scientific community. For example, Ref. [43] theorizes that
These models leverage vast amounts of data from various sources, such as electronic
AutoML is primarily designed to mitigate the demand for data scientists, thereby equipping
health records, genomics, and wearable devices, to provide accurate predictions of diabe-
domain experts with the capacity to construct machine learning applications without a
tes risk and onset [53].
deep reservoir of ML knowledge.
1.2.5. AutoML in Diabetes Diagnosis
Several studies have explored the application of AutoML for diabetes diagnosis. One
such study by [54] used AutoML to predict diabetes onset by analyzing electronic health
records, demonstrating improved predictive performance compared to traditional ma-
In contrast, Ref. [44] perceives AutoML as a harmonious blend of automation and

machine learning. This definition emphasizes the automated assemblage of an ML pipeline,
constrained by a limited computational budget. In a world experiencing an exponential
growth in computing power, AutoML has emerged as a focal point for both industrial and
academic research. A comprehensive AutoML system exhibits the dynamic amalgamation
of a multitude of techniques, resulting in an intuitive, end-to-end ML pipeline system.
Several AI-centric companies, including Google, Microsoft Azure, Amazon, H2O.ai, and
RapidMiner, have developed and publicly shared systems like Cloud AutoML. Figure 2
illustrates the structure of an AutoML pipeline, comprising several key processes: (1)
Data preparation: this consists of data collection, data cleaning, and data augmentation;
for more details, refer to [45]. (2) Model or feature engineering: this consists of feature
selection (Chen and Li, 2022), feature extraction, and feature selection; for more details,
refer to [46]. (3) Model generation: this consists of two parts: a. search space (this includes
traditional models such as Support Vector Machine (SVM) (Garcia and Moreno, 2017) and
the k-nearest neighbors algorithm (KNN)) and b. optimization methods (these include
hyperparameter optimization and architecture optimization); for more details, refer to [47].
(4) Model evaluation: this consists of low-fidelity (Davis, 2019), early stopping (Nelson
and Thompson, 2020), surrogate model (Martinez, 2021), and weight-sharing (Rivera and
Santos, 2022); for more details, refer to [48].
1.2.4. AutoML and Its Role in Healthcare

AutoML aims to automate the process of selecting the best machine learning algo-
rithms, optimizing hyperparameters, and managing data pre-processing. This automation
reduces the time and expertise needed to develop effective models, making it an attractive
approach in healthcare, where rapid and accurate decision making is crucial [19].
AutoML has become an essential tool in the medical field for identifying risk factors,
predicting disease progression, and guiding treatment strategies [49,50]. In the context of
diabetes diagnosis, AI-powered predictive models have been instrumental in detecting
early signs of the disease and assisting clinicians in making data-driven decisions [51].
These models leverage vast amounts of data from various sources, such as electronic health
records, genomics, and wearable devices, to provide accurate predictions of diabetes risk
and onset [52].
1.2.5. AutoML in Diabetes Diagnosis

Several studies have explored the application of AutoML for diabetes diagnosis.
One such study by [53] used AutoML to predict diabetes onset by analyzing electronic
health records, demonstrating improved predictive performance compared to traditional
machine learning models. Deep learning, a subfield of AI, has demonstrated remarkable
success in various medical applications, including diabetes diagnosis [54]. Convolutional
neural networks (CNNs) and recurrent neural networks (RNNs) are two prominent deep
learning architectures that have been employed in the analysis of complex data for diabetes
prediction and diagnosis [55,56]. These models can process high-dimensional data, such as
medical images, and identify intricate patterns that traditional machine learning techniques
may not capture [6].
2. Materials and Methods

This study adheres to an established research structure, which mirrors the AutoML
workflow (as illustrated in Figure 2). This structure will be further expanded upon in the
following sections, where we will delineate the step-by-step progression of this research.
Initially, we begin by comprehending the intrinsic nature of the problem and the attributes
harbored by the data. This comprehension phase leads directly into the data preparation
phase, forming the cornerstone of our research foundation. Subsequently, we embark on
the feature engineering stage. The entire process culminates with the generation of the
model, which is subsequently subjected to a rigorous evaluation process. This process of

evaluation is crucial to validate the effectiveness of the model.
2.1. Problem Understanding and Determining the Purpose of the Analysis

The purpose of this analysis is to guide the selection of appropriate modeling methods,
evaluate model performance, and choose relevant metrics based on the research question
at hand. For instance, one may seek to investigate the relationship between diabetes
occurrence in patients within the NIDDK dataset and other distinct attributes, such as
Glucose, BloodPressure, Insulin, BMI, and Age. Alternatively, the focus might be on
predicting the likelihood of a new patient developing diabetes in the near future. When
addressing the former question, the analysis centers on the coefficients’ significance and the
goodness of fit through descriptive or explanatory analysis. Descriptive modeling involves
fitting a regression model to identify relationships between independent variables and
the dependent variable. On the other hand, explanatory modeling aims to draw causal
inferences based on theory-driven hypotheses. However, the present study focuses its
efforts on addressing the latter inquiry, specifically centered on predicting the development
of diabetes in a newly encountered patient. The primary objective is to rigorously evaluate
the predictive performance of the model in this context.
To achieve this aim, advanced analytics modeling, prominently featuring machine
learning algorithms, is commonly practiced within the domain. While our focus is not
centered on descriptive or explanatory analysis, variability within disease data can affect
the accuracy and reliability of our predictions. To address this, we have partitioned the data
into training and testing sets at the beginning of the process, which allows us to monitor
and account for any fluctuations or inconsistencies. Various performance metrics have been
used alongside validation techniques to assess the model’s robustness against the variability
inherent in the disease data. In assessing the quality of predictive models, especially for
classification problems with categorical outcomes (e.g., diabetes or no diabetes), certain
methods are frequently employed.
The process typically begins by partitioning the existing data into training and testing
sets. This is followed by the application of various performance metrics in tandem with
validation techniques. Principal tools for evaluating the efficacy of a classification model
include confusion matrices (or truth tables), lift charts, receiver operator characteristic
(ROC) curves, and area under the curve (AUC). The following sections will elaborate on
the construction and usage of these tools, as well as detailing how to carry out effective
performance evaluations.
2.2. Data Exploration and Pre-Processing

This study primarily centers around the application of sophisticated machine learning
techniques to the Pima Indian Diabetes Dataset. The dataset is sourced from Kaggle (https:
//www.kaggle.com/uciml/pima-indians-diabetes-database, accessed on 10 January 2023).
To ensure ethical standards, it has been meticulously anonymized, so it is completely
void of any identifiable patient characteristics. While larger and more complex diabetes
datasets now exist, the Pima Indian Diabetes dataset continues to serve as a benchmark
in diabetes classification research. Its binary outcome variable naturally suits supervised
learning methodologies. Despite this, the dataset’s flexibility extends beyond just one
model type, with numerous machine learning algorithms having been leveraged to produce
diverse classification models. It is composed of 768 entries, each representing an individual
subject (500 non-diabetics and 268 diabetics). Every individual is profiled through nine
distinct attributes, as detailed in Table 1.
Table 1. Data dictionary.
Attribute Description Data Type Range

Number of times the individual has been
Pregnancies integer (0, 17)
pregnant. Range (0,17).
Plasma glucose concentration (mg/dL) after
Glucose integer (0, 199)
2 h in an oral glucose tolerance test.
BloodPressure Diastolic blood pressure (mm Hg). integer (0, 122)
Triceps skinfold thickness (mm)—a measure
SkinThickness integer (0, 99)
of body fat.
Insulin 2 h serum insulin level (mu U/mL). integer (0, 846)
BMI Body mass index. real (0, 67.1)
A function that scores the likelihood of
DiabetesPedigreeFunction diabetes based on family history. Higher real (0.078, 2.42)
values indicate a higher risk.
Age Age of the individual in years. integer (21, 8)
Diagnosis of diabetes. Encoded as ‘1’ for
Outcome ‘diagnosed with diabetes’ and ‘0’ for ‘not Categorical (binary) (0, 1)
diagnosed with diabetes’.
The attribute ‘Pregnancies’ quantifies the total number of pregnancies an individual

has experienced. The attribute ‘Glucose’ represents the blood glucose concentration, provid-
ing insight into the individual’s glycemic status. ‘BloodPressure’, ‘SkinThickness’, ‘Insulin’,
and ‘BMI’ respectively correspond to measurements of blood pressure, skin fold thickness,
serum insulin levels, and body mass index, each of which delivers crucial insights into the
health status of the participant. Further, the attribute ‘DiabetesPedigreeFunction’ signifies
the likelihood of diabetes predicated on the individual’s familial history, encapsulating
genetic influence in the propensity towards diabetes. The attribute termed ‘Outcome’
serves as a categorical binary response variable in our study. It represents the presence or
absence of diabetes in an individual.
The predictors (independent variables) used in this research include ‘Pregnancies’,
‘Glucose’, ‘BloodPressure’, ‘SkinThickness’, ‘Insulin’, ‘BMI’, ‘DiabetesPedigreeFunction’,
and ‘Age’. The target variable (dependent outcome variable) is ‘Outcome’. The dataset
under analysis is complete, devoid of any null or missing values, which ensures a compre-
hensive assessment of the data points. However, drawing upon domain-specific knowl-
edge [57], inconsistencies were noted in several critical attributes, namely: glucose concen-
tration, blood pressure, skin thickness, insulin levels, and BMI. These inconsistencies are
presented as zero values, which do not fall within the established normal ranges, hence
rendering them inaccurate (Table 2). To rectify this, we implemented a data imputation
technique, specifically opting to replace these zero values with the corresponding attribute’s
median value. This strategy was chosen because the median, unlike the mean, is robust to
outliers and can provide a more accurate representation of the central tendency for each
attribute. Figure 3 serves as a comprehensive scatterplot matrix, employed as a primary
exploratory instrument to discern potential pairwise associations among the study vari-
ables. The distribution of data points within this matrix offers substantial insights into the
nature of these relationships. For instance, a scattered, diffused distribution indicates the
absence of an identifiable correlation, while a more streamlined, linearly arranged set of
points hints at a linear interdependency among the attributes.
Table 2. Statistical summary.
Attribute
Table 2. Statistical Min.
summary. 1st qu. Median Mean 3rd qu. Max
Pregnancies 0 1 3 3.845 6 17
Attribute Min. 1st qu. Median Mean 3rd qu. Max
Glucose
Pregnancies 0 0 99 1 117 3 120.93.845 140.2
6 199
17
BloodPressure
Glucose 0 0 62 99 72 117 69.11120.9 80
140.2 122
199
BloodPressure0
SkinThickness 0 0 62 23 72 20.5469.11 3280 122
99
SkinThickness 0
Insulin 0 0 0 30.5 23 79.820.54 32
127.2 99
846
BMIInsulin 0 0 27.3 0 32 30.5 31.9979.8 127.2
36.6 846
67.1
BMI
DiabetesPedigree
0 27.3 32 31.99 36.6 67.1
DiabetesPedigree0.078 0.2437 0.3725 0.4719 0.6262 2.42
Function
0.078 0.2437 0.3725 0.4719 0.6262 2.42
Function 21
Age 24 29 33.24 41 81
Age 21 24 29 33.24 41 81
Figure 3.
Figure 3. Scatterplot
Scatterplot of
of attributes.
attributes.
In
In aa critical
critical analysis
analysis ofof the
the scatterplot
scatterplot matrix
matrix depicted
depicted inin Figure
Figure 3, 3, aa strong
strong positive
positive
correlation
correlationemerges
emergesamongamongspecific
specificvariable
variablepairs
pairsthat
thatdemonstrate
demonstratenotable
notable proportionality.
proportional-
This correlation
ity. This is most
correlation is conspicuous between
most conspicuous Pregnancies
between and Age,and
Pregnancies SkinThickness and BMI,
Age, SkinThickness
and
and Glucose
BMI, and and Insulinand
Glucose levels. Nonetheless,
Insulin in an examination
levels. Nonetheless, of the actualofcorrelation
in an examination the actual
values, outlined
correlation values,in outlined
Table 3, Age and 3,
in Table Pregnancies exhibited the
Age and Pregnancies strongest
exhibited the correlation, but
strongest corre-
since
lation,the
butcorrelation coefficient coefficient
since the correlation was belowwas 0.550, it was
below deemed
0.550, it wasinsufficient to warrant
deemed insufficient to
the removal
warrant of either of
the removal attribute. This observation
either attribute. underpins
This observation the relative
underpins lack of lack
the relative robust
of
associations amongstamongst
robust associations the study variables.
the A detailed
study variables. scrutiny of
A detailed the results
scrutiny of the further confirms
results further
the absence of multicollinearity, ensuring the accuracy and reliability
confirms the absence of multicollinearity, ensuring the accuracy and reliability of the of the observed corre-
ob-
lations. Additionally, an examination of Figure 3 unveils the existence of
served correlations. Additionally, an examination of Figure 3 unveils the existence of out- outliers in specific
attributes (Age, Insulin,
liers in specific Glucose,
attributes (Age, BMI, DiabetesPedigreeFunction,
Insulin, and BloodPressure).and
Glucose, BMI, DiabetesPedigreeFunction,
BloodPressure).
Table 3. Correlation matrix.
Attributes Age BloodPressure BMI DiabetesPedigreeFunction Glucose Insulin Outcome = False Pregnancies SkinThickness
Age 1 0.240 0.036 0.034 0.264 −0.042 −0.238 0.544 −0.114
BloodPressure 0.240 1 0.282 0.041 0.153 0.089 −0.065 0.141 0.207
BMI 0.036 0.282 1 0.141 0.221 0.198 −0.293 0.018 0.393
DiabetesPedigree-
0.034 0.041 0.141 1 0.137 0.185 −0.174 −0.034 0.184
Function
Glucose 0.264 0.153 0.221 0.137 1 0.331 −0.467 0.129 0.057
Insulin −0.042 0.089 0.198 0.185 0.331 1 −0.131 −0.074 0.437
Outcome = false −0.238 −0.065 −0.293 −0.174 −0.467 −0.131 1 −0.222 −0.075
Pregnancies 0.544 0.141 0.018 −0.034 0.129 −0.074 −0.222 1 −0.082
SkinThickness −0.114 0.207 0.393 0.184 0.057 0.437 −0.075 −0.082 1
These outliers might be the result of various underlying factors. Considering the
limited size of the dataset, eliminating these outliers could potentially result in the loss of
valuable information. To circumvent this risk, a decision was made to standardize the data,
which would help to alleviate the potential negative impact of these outliers.
2.3. Feature Selection

Feature selection, the process of discerning and selecting the most significant variables
essential for accurate model prediction, continues to be a subject of discussion within
the research community. Critics assert the redundancy of model fitting, contending that
a faster, brute-force approach to data analysis can more efficiently identify meaningful
correlations for decision making [58]. However, the practical relevance of models remains
indisputable. Beyond aiding decision making, models serve as conduits for advancing
knowledge in various fields of study. Given the critical role of models, the process of
feature selection becomes equally crucial. It offers two key advantages: first, it optimizes
the performance of the algorithm by minimizing potential noise from extraneous variables;
second, it facilitates a more streamlined interpretation of the model’s output by reducing
the complexity associated with numerous attributes or features.
The research undertaken employs principal component analysis (PCA) as a funda-
mental analytical instrument. This sophisticated statistical method principally aids in
discerning variables that display maximum variability within a given dataset. The method-
ology accomplishes this by astutely transforming the original variables into a new collection
of constructs, denoted as ‘principal components’. Each principal component carries its
distinct set of attributes. PCA’s value extends beyond mere dimensionality reduction, as it
unearths underlying patterns in data.
It accomplishes this by assigning a rank to these components, contingent upon the frac-
tion of the total variance they account for. This procedure enables a deeper interpretation
of multifaceted datasets, facilitating a more detailed comprehension of the interrelations
and structures embedded within the data.
2.4. Model Generation and Results

In the pursuit of creating an optimized model for forecasting diabetes diagnoses, the
study utilized AutoML to analyze the Pima Indian Diabetes dataset. For the purpose
of maintaining a controlled environment, each model was subject to the same training
and testing datasets. In Figure 4, AutoML has identified the top nine models best suited
for the dataset: Naïve Bayes, Logistic Regression, Decision Tree, Gradient Boosted Trees,
Generalized Linear Model, Support Vector Machine, Fast Large Margin, Deep Learning,
and Random Forest.
Sustainability 2023,15,
Sustainability2023, 15,13484
x FOR PEER REVIEW 12 of 24
12 24
Figure 4.
Figure 4. Model
Model generation.
generation.
It crucialtotohighlight
It is crucial highlightthatthat these
these models
models underwent
underwent recalibration
recalibration withwith diverse
diverse com-
combinations
binations of feature of feature sets. comprehensive
sets. This This comprehensive approach approach
resulted resulted
in 40,423indistinct
40,423 distinct
models,
models,
derived derived
from anfrom an expansive
expansive 5262 unique
5262 unique featurefeature set combinations.
set combinations. The coreThe core
aim aim of
of this
this
studystudy
is toisdetermine
to determinethe the
most most effective
effective model
model basedbased on performance
on performance metrics
metrics suchsuch as
as ac-
accuracy, recall,precision,
curacy, recall, precision,and andAUC,
AUC,totoname
nameaafew.few. ItIt should be noted that that RapidMiner
RapidMiner
offers
offers additional
additional metrics
metrics that
that might become critical during the model’s deployment stage.
These metrics can encompass
These metrics can encompass variations
variations experienced
experienced by abymodel
a modelwhen trained
when with with
trained different
dif-
feature set combinations, the training duration, the scoring time, and
ferent feature set combinations, the training duration, the scoring time, and the conse- the consequent gains.
For
quentinstance,
gains. ourFor analysis
instance,could explore the
our analysis holistic
could exploreperformance
the holisticofperformance
each model underof each a
multitude of feature variations, drawing comparisons between
model under a multitude of feature variations, drawing comparisons between model dif-model differences and the
associated
ferences and training durations.
the associated As shown
training in Figure
durations. As4,shown
standard deviation
in Figure bars are deviation
4, standard included
to depict the variability or spread of the data. These bars provide
bars are included to depict the variability or spread of the data. These bars provide insights into the stability
in-
and
sights into the stability and consistency of the model’s performance across differentsets.
consistency of the model’s performance across different iterations and training A
itera-
model with smaller standard deviation bars suggests consistent results,
tions and training sets. A model with smaller standard deviation bars suggests consistent while larger bars
indicate variability.
results, while largerFrom the widevariability.
bars indicate pool of 40,423
From models
the wide evaluated, our AutoML
pool of 40,423 modelssystem
evalu-
has strategically narrowed down to nine machine learning models
ated, our AutoML system has strategically narrowed down to nine machine learning deemed most promising,
mod-
including the following:
els deemed most promising, including the following:
1.
1. Bayes: aa simple
Naïve Bayes:
Naïve simple yet
yet effective
effective probabilistic
probabilistic classifier
classifier based
based on
on Bayes’
Bayes’ Theorem
Theorem
with strong independence assumptions between features. Given a class variable Y
with strong independence assumptions between features. Given a class variable Y
and dependent feature vectors X1 through Xn, Naïve Bayes assumes that each feature
is independent. The formula is typically given as: P(Y | X1, ..., Xn) ∝ P(Y )ΠP( Xi |Y ).
2. Logistic Regression: a powerful statistical model used for predicting the probability of
a binary outcome. Logistic Regression models the probability that Y belongs to a partic-
ular class. The Logistic Regression is given as: p( X ) = eˆ(b0 + b1X )/(1 + eˆ(b0 + b1X )).
3. Decision Tree: an intuitive model that predicts outcomes by splitting the dataset into
subsets based on feature values, akin to a tree structure. Decision Trees do not have
a general equation, as they work by partitioning the feature space into regions and
assigning a class value to each region. The partitioning process is based on specific
criteria, such as Gini impurity or information gain.
4. Gradient Boosted Trees: an ensemble learning method that constructs a robust model
by optimizing a set of weak learners in a stage-wise fashion, using the gradient descent
algorithm. Gradient Boosted Trees do not have a single formula as such. The method
builds an ensemble of shallow and weak successive trees with each tree learning and
improving on the previous one.
5. Generalized Linear Model (GLM): a flexible generalization of ordinary linear regres-
sion that allows for response variables that have error distribution models other than
a normal distribution. A GLM generalizes linear regression by allowing the linear
model to be related to the response variable via a link function: g( E(Y )) = η = Xβ,
where E(Y ) is the expected value of the response variable, η is the linear predictor,
and Xβ is the matrix product of the observed values and their coefficients.
6. Support Vector Machine (SVM): a boundary-based model which finds the optimal
hyperplane that distinctly classifies the data points in high-dimensional space. SVMs
find the hyperplane that results in the largest margin between classes. For linearly
separable classes, this can be represented as: Y ( X ) = WˆTϕ( X ) + b, where W is the
normal to the hyperplane, ϕ( X ) is the transformed input, and b is the bias.
7. Fast Large Margin: a model that aims to ensure a large margin between decision
boundary and data points, enhancing the robustness and generalization of the model.
This method is commonly used in SVM. It aims to maximize the margin, which is
represented in the SVM formula above.
8. Deep Learning: a neural network model inspired by the human brain, which excels at
capturing intricate patterns in large datasets. Deep Learning models involve a series
of linear and non-linear transformations, where each layer of hidden units is usually
computed as f (WX + b), where f is an activation function like ReLU or sigmoid, W is
the weight matrix, X is the input, and b is the bias.
9. Random Forest: an ensemble learning method that fits a number of Decision Tree
classifiers on various sub-samples of the dataset and uses averaging to improve the
predictive accuracy and control over-fitting. Like the Decision Tree (DT), a random
forest does not have a specific formula. It creates a collection of decision trees from a
randomly selected subset of the training set and aggregates the votes from different
DTs to decide the final class of the test object.
2.5. Model Evaluation

To ascertain the most effective algorithms for this specific dataset and to impartially
assess the performance of each model, we implemented an extensive model evaluation
process. This assessment utilized a comprehensive set of metrics that provide a multidi-
mensional perspective on each model’s efficacy. The selected metrics included: precision,
recall, accuracy, confusion matrices, receiver operator characteristic (ROC) curves, and area
under the curve (AUC). These metrics were utilized to evaluate the performance of each
model rigorously and holistically, thereby ensuring that the optimal algorithm was selected
for our specific data context.
1. Precision: the ‘precision’ represents the proportion of correctly predicted true samples
out of all predictions labelled as true, regardless of their actual truthfulness, as shown
below,
TP
Precision =
(TP/(TP + FP)
where TP is true positive; FP is false positive; FN is false negative; and TN is true negative.
In the examination of the precision results illustrated in the Table 4, it becomes evident
that the Logistic Regression model takes the lead in terms of performance, demonstrating
a notable precision rate of 73.1%. It conspicuously surpasses the other models in the
comparison. Trailing it is the Generalized Linear Model, registering a commendable
precision rate of 66.5%. Following closely, the Decision Tree makes a decent showing with
a precision rate of 66.0%.
Table 4. Precision results.
Model Precision Standard Deviation Gains Total Time

Naive Bayes 56.5% ±20.9% 20 6 min 49 s
Generalized Linear Model 66.5% ±10.8% 36 7 min 4 s
Logistic Regression 73.1% ±20.5% 36 7 min 6 s
Fast Large Margin 66.0% ±14.1% 34 7 min 0 s
Deep Learning 58.3% ±28.1% 18 8 min 20 s
Decision Tree 66.0% ±17.6% 26 6 min 57 s
Random Forest 54.9% ±24.6% 18 7 min 58 s
Gradient Boosted Trees 53.0% ±26.5% 12 8 min 0 s
Support Vector Machine 55.8% ±21.5% 22 7 min 15 s
2. Recall: this metric provides the proportion of actual positive cases that were correctly
classified, as shown in the formula below,
TP
Recall =
( TP + FN )
A careful examination of Table 5 reveals a discernible performance superiority dis-
played by the Generalized Linear Model, boasting an impressive recall rate of 61.8%. This
model demonstrates significant outperformance when compared to its counterparts. Trail-
ing behind it is the Fast Large Margin, which manages to yield a satisfactory recall rate
of 60.8%. Following that, the Naïve Bayes model makes a decent showing with a recall
rate of 55.2%.
Table 5. Recall results.
Model Recall Standard Deviation Gains Total Time

Naive Bayes 55.2% ±17.3% 20 6 min 49 s
3. Accuracy: this broad metric provides a ratio of correctly predicted instances to the
total instances in the dataset, as shown in the formula below,
( TP + TN )
Accuracy =
( TP + TN + FP + FN )
The data delineated in Table 6 afford a compelling comparative analysis of the effec-
tiveness of various predictive models. An examination of the figures reveals that both
the Generalized Linear Model and Logistic Regression take precedence, achieving an
exceptional accuracy rate of 79.2%. This performance significantly exceeds that of the
other models under scrutiny. A comprehensive exploration of the accuracy results can be
visualized through the use of a confusion matrix. This matrix, a powerful tool for accu-
racy assessment, offers a clear and concise snapshot of the performance of our predictive
model, effectively illuminating the interplay between true and false, and positive and
negative predictions.
Table 6. Accuracy results.
Model Accuracy Standard Deviation Gains Total Time

Naive Bayes 77.6% ±5.1% 20 6 min 49 s
4. Confusion matrix for accuracy: the confusion matrix, an exemplary analytical instru-
ment, portrays the intersection of actual and forecasted outcome classes derived from
the testing set. The predicted class outcomes are typically displayed in a horizon-
tal fashion across rows, while the actual class outcomes are organized vertically in
columns [59]. This matrix, also referred to as a truth table, can be efficiently scruti-
nized by focusing on the diagonal line running from the top left to the bottom right.
Ideal classification performance is indicated by entries exclusively populating this
main diagonal, with the anticipation that all off-diagonal components would hold
zero values.
Table 7 illustrates the confusion matrix for the accuracy of each of these nine models.
The confusion matrix encapsulates the comprehensive performance of a predictive model.
It acts as a quantifier of the fraction of instances that have been accurately forecasted. The
construction of this matrix involves a calculation derived from the summation of true
positive and true negative predictions.
Table 7. Confusion matrix for accuracy.
true false true true class precision

pred.false 113 22 83.70%
Naïve Bayes
pred.true 19 29 60.42%
class recall 85.61% 56.86%
pred.false 115 26 81.56%
LogisticRegression
pred.true 12 30 71.43%
pred.false 115 31 78.77%
Decision Tree
pred.true 12 25 67.57%
Gradient pred.false 111 24 82.22%
Boosted Trees pred.true 21 27 56.25%
Generalized pred.false 110 21 83.97%
Linear Model pred.true 17 35 67.31%
Support Vector pred.false 112 27 80.58%
Machine pred.true 17 28 62.22%
Fast Large pred.false 110 22 83.33%
Margin pred.true 17 34 66.67%
pred.false 116 26 81.69%
Deep Learning
pred.true 16 25 60.98%
pred.false 110 27 80.29%
Random Forest
pred.true 19 28 59.57%
Evaluation metrics like precision, recall, and accuracy provide an aggregate view,
serving to illustrate an averaged representation of the classifier’s performance across
the entire dataset. This characteristic, however, can sometimes veil disparities in model
performance. For instance, it is plausible for a classifier to showcase high accuracy over
the entire dataset but concurrently underperform in terms of class-specific recall and
precision. To select the most effective model, we extended our evaluation to additional
metrics. This decision was driven by the need to unmask potential trade-offs and provide a
more nuanced, comparative analysis of model performance, such as the receiver operator
characteristic (ROC) curve along with the resultant area under the curve (AUC).
5. The receiver operating characteristics (ROC) curve, and the area under the curve
(AUC): these two metrics serve as critical performance indicators for classification
models, effectively encapsulating the degree to which classes can be separated. ROC
curves, which originated in the field of signal detection, plot the true positive rate
(sensitivity) against the false positive rate (1—specificity) at varying threshold settings.
The area under the ROC curve (AUC-ROC) serves as a robust indicator of model
performance, allowing us to compare different models and identify the one that offers
the best balance between sensitivity and specificity. By broadening our examination to
include such comprehensive metrics, we are better positioned to identify the optimal
model—one that not only excels in general performance, but also demonstrates
proficiency in handling the diverse challenges posed by our data [60]. In the context
of AUC, it could be interpreted as the probability that a model will rank a randomly
selected positive instance above a randomly chosen negative one. The AUC measures
the full two-dimensional area beneath the entire ROC curve, spanning from (0.0) to
(1.1), with the maximum attainable value being 1. An ROC curve is plotted by 17
Sustainability 2023, 15, x FOR PEER REVIEW setting
of 24
the fraction of TPs (TP rate) against the fraction of FPs (FP rate), as shown in Figure 5.
Figure 5.
Figure 5. ROC
ROC comparison.
comparison.
While
Whileaapreliminary
preliminaryoverview
overview of of
Figure
Figure5 might suggest
5 might a marginal
suggest a marginaldifference between
difference be-
the Generalized Linear Model (GLM) and the Logistic Regression
tween the Generalized Linear Model (GLM) and the Logistic Regression model, given model, given their area
under curve
their area (AUC)
under curvevalues
(AUC) of 82.4%
values and 84.1%,
of 82.4% respectively,
and a more granular
84.1%, respectively, analysis
a more granular
uncovers a noteworthy
analysis uncovers superiority
a noteworthy of the GLM.
superiority At first
of the GLM. glance,
At firsttheglance,
close AUC values
the close AUC of
the twoof
values models
the two may appear
models mayto appear
offer similar performance
to offer metrics. However,
similar performance it is crucialitto
metrics. However, is
remember
crucial to that AUC primarily
remember that AUC provides
primarilyan overall
provides measure of performance
an overall measure ofacross varying
performance
threshold levels.threshold
across varying The true levels.
differentiation
The truesurfaces when we
differentiation delve when
surfaces deeperwe into individual
delve deeper
metric
into individual metric assessments—an approach of paramount importance where
assessments—an approach of paramount importance in our domain in our the
do-
high
maincost
whereassociated
the high with false negatives
cost associated necessitates
with false negativesa focus on recall
necessitates as a on
a focus significant
recall as
performance metric.
a significant performance metric.
Table
Table 88 provides
provides an an in-depth,
in-depth, comparative
comparative view view of
of both
both models’
models’ performance
performance across
across
all pertinent metrics. Notably, it reveals that the GLM outshines the
all pertinent metrics. Notably, it reveals that the GLM outshines the Logistic RegressionLogistic Regression
model
model inin terms
terms ofof recall,
recall, registering
registering an an impressive
impressive rate
rate of
of 61.8%
61.8% compared
compared to tothe
thelatter’s
latter’s
52.5%.
52.5%. In our specific context, where a premium is placed on minimizing false negatives,
In our specific context, where a premium is placed on minimizing false negatives,
the recall metric assumes a heightened significance. Consequently, our decision to favor
the Generalized Linear Model as the optimal choice for our project is influenced not
merely by its marginally higher AUC, but more critically by its considerably superior re-
call rate. By delivering a robust performance on this vital metric, the GLM is far better
the recall metric assumes a heightened significance. Consequently, our decision to favor
the Generalized Linear Model as the optimal choice for our project is influenced not merely
by its marginally higher AUC, but more critically by its considerably superior recall rate.
By delivering a robust performance on this vital metric, the GLM is far better equipped to
align with, and effectively meet, our project’s core objectives.
Table 8. Overall performance.
Generalized Linear Model Logistic Regression Model

Standard Standard
Criterion Value Criterion Value
Deviation Deviation
Accuracy 79.2% ±3.7% Accuracy 79.2% ±6.3%
Sustainability 2023, 15, x FOR PEER REVIEW 18
Classification Error 20.8% ±3.7% Classification Error 20.8% ±6.3%
AUC 82.4% ±5.0% AUC 84.1% ±7.2%
Precision 66.5% ±10.8% Precision 73.1% ±20.5%
Recall 61.8% ±13.2% Recall 52.5% ±14.0%
Recall 61.8% ±13.2% Recall 52.5% ±14.0%
F Measure 63.5% ±9.7% F Measure 60.0% ±13.0%
F Measure 63.5% ±9.7% F Measure 60.0% ±13.0%
Sensitivity 61.8% ±13.2% Sensitivity 52.5% ±14.0%
Specificity 86.5% Sensitivity
±4.1% 61.8%
Specificity ±13.2% 90.3% Sensitivity ±52.5%
6.1% ±14.0%
Specificity 86.5% ±4.1% Specificity 90.3% ±6.1%
2.6. Model Optimization—Prescriptive Analytics

2.6. Model Optimization—Prescriptive Analytics
In the realm of In
predictive
the realm modeling, the norm
of predictive is to utilize
modeling, the normalgorithms with
is to utilize the aim of
algorithms with the a
forecasting a specific outcome based on given inputs. Yet, a more intriguing and
forecasting a specific outcome based on given inputs. Yet, a more intriguing and p potentially
sophisticated technique reimaginestechnique
tially sophisticated this traditional approach.
reimagines Instead of starting
this traditional approach. with the of sta
Instead
input to predictwith
an output,
the inputthis innovative
to predict methodology
an output, embarks
this innovative from a model
methodology and afrom a m
embarks
desired outcome, andwith the goal
a desired to determine
outcome, with thean goal
optimized input that
to determine an fulfills the input
optimized desired that fulfill
target. This novel strategy is commonly recognized as prescriptive analytics.
desired target. This novel strategy is commonly recognized as prescriptive Unlike itsanalytics
traditional predictive counterparts,
like its traditional AutoML
predictive opens the door
counterparts, AutoMLto prescriptive
opens the dooranalytics. It
to prescriptive an
goes beyond predicting outcomes. These sophisticated systems analyze an array
ics. It goes beyond predicting outcomes. These sophisticated systems analyze an arrof possible
actions, pinpointing the optimal
possible actions, course to pursue,
pinpointing therebycourse
the optimal delivering a bespoke
to pursue, action
thereby plan
delivering a bes
for a given situation. The overarching aim is to tailor the approach to meet a predetermined
action plan for a given situation. The overarching aim is to tailor the approach to m
outcome, whichpredetermined
often entails adjusting
outcome,the confidence
which level for
often entails the preferred
adjusting class to drive
the confidence level for the
the desired result.
ferred class to drive the desired result.
Delving into this case study,
Delving we case
into this leveraged
study,thewe simulation
leveraged the tool (depictedtool
simulation in Figure
(depicted6) in Figu
to bifurcate thetooutcome into two distinct categories. “True” denoted the presence
bifurcate the outcome into two distinct categories. “True” denoted the presence o of
diabetes, whereas “false”
betes, signified
whereas its absence.
“false” signifiedBy itsusing prescriptive
absence. By usinganalytics, we analytics,
prescriptive can more we can
effectively strategize and prescribe actions to reach the desired outcome.
effectively strategize and prescribe actions to reach the desired outcome.
Figure
Figure 6. Generalized 6. Generalized
Linear Linear Model—simulator.
Model—simulator.
After
After running the running the(Figures
optimization optimization
7 and(Figures 7 and
8), for this 8),study
case for this
wecase studya we reach
reached
model with 97%model
accuracy
withon theaccuracy
97% ‘diabetes’
onclass.
the ‘diabetes’ class.
Sustainability 2023,15,
Sustainability2023, 15,13484
x FOR PEER REVIEW 19 of 24
19 24
Figure 7.
7. Optimization framework.
framework.
Figure 7. Optimization
Figure Optimization framework.
Figure 8. Generalized Linear Model after optimization.

Figure 8.
Figure 8. Generalized
Generalized Linear
Linear Model
Model after
after optimization.
optimization.
3. Discussion
3. Discussion
3. Discussion
Diabetesmellitus,
Diabetes mellitus, a pervasivechronic chronic metabolic disorder, affects countless individ-
Diabetes mellitus,aapervasive
pervasive chronic metabolic
metabolic disorder,
disorder,affects countless
affects countlessindividuals
individ-
uals
on on a
a global global scale,
scale, scale, posing
posingposing
serious,serious, persistent
persistent challenges
challenges to
to healthcarehealthcare systems
systemssystems
worldwide world-
[1].
uals on a global serious, persistent challenges to healthcare world-
wide
This [1]. This
relentless relentless
chronic chronic
affliction affliction
manifests manifests
either when either
the when
pancreas theispancreas
incapable is incapable
of produc-
wide [1]. This relentless chronic affliction manifests either when the pancreas is incapable
of producing
ing sufficient
sufficient insulin, orinsulin,
when the or body’s
when the body’s
ability ability to utilize
to efficiently efficiently
the utilize
insulinthe insulin
produced
of producing sufficient insulin, or when the body’s ability to efficiently utilize the insulin
produced
is is compromised.
compromised. Despiteresearch
Despite extensive extensive andresearch
continuousand continuous medicala advances,
medical advances, definitive
produced is compromised. Despite extensive research and continuous medical advances,
a definitive
cure for this cure
diseasefor remains
this disease remains elusive.
elusive.
a definitive cure for this disease remains elusive.
The onset
The onset of
of diabetes
diabetes isis widely
widely recognized
recognized as aa result
result of an intricate
intricate interplay between
between
The onset of diabetes is widely recognized as as a result of of an intricate interplay
interplay between
genetic predispositions
genetic predispositions and and environmental
environmental triggers [2]. Importantly,
Importantly, the the absence
absence of of early
genetic predispositions and environmental triggers [2]. Importantly, the absence of early early
detection
detection methods for diabetes not only exacerbates the disease prognosis but also paves
detection methods
methods for for diabetes
diabetes notnot only
only exacerbates
exacerbates the the disease
disease prognosis
prognosis but but also
also paves
paves
the way for the
the the onset
onsetof ofadditional
additionalchronic
chronicailments
ailments such
suchas as
kidney
kidney disease [4].[4].
disease Hence, the
Hence,
the way for the onset of additional chronic ailments such as kidney disease [4]. Hence, the
necessity
the for for
necessity improved
improved early detection
early detectionmeasures
measuresis highlighted,
is highlighted, underscoring
underscoring the the
im-
necessity for improved early detection measures is highlighted, underscoring the im-
portance of of
importance ongoing
ongoing research
research in in
this area.
this area.
portance of ongoing research in this area.
The principal
The principalaimaimofofthis
thisresearch
research is is
toto forecast
forecast thethe likelihood
likelihood of diabetes
of diabetes in individ-
in individuals,
The principal aim of this research is to forecast the likelihood of diabetes in individ-
uals, utilizing
utilizing key attributes
key attributes such assuchage,asglucose
age, glucose levels,
levels, BMI, BMI, and other
and other pertinent
pertinent factors.
factors. The
uals, utilizing key attributes such as age, glucose levels, BMI, and other pertinent factors.
study discerned that the Generalized Linear Model exhibited exceptional
The study discerned that the Generalized Linear Model exhibited exceptional efficacy in efficacy in prog-
The study discerned that the Generalized Linear Model exhibited exceptional efficacy in
nosticating diabetes
prognosticating diagnoses.
diabetes The exploration
diagnoses. The explorationof advances in AutoML
of advances in AutoMLfor predictive and
for predictive
prognosticating diabetes diagnoses. The exploration of advances in AutoML for predictive
prescriptive modeling in diabetes diagnosis underscored their efficiency in discerning risk

factors, optimizing treatment strategies, and ultimately enhancing patient health outcomes.
For entities like the National Institute of Diabetes and Digestive and Kidney Dis-
eases [13] and other potential users, the AutoML model generated from this study could
be considered a robust foundational tool. It is recommended that medical professionals
and institutions scrutinize the attributes employed in this dataset when predicting diabetes
occurrence in individuals. Furthermore, the identification and analysis of similar attributes
could substantially aid in refining the model and bolstering its diagnostic capabilities.
While the findings are indeed promising, it is crucial to bear in mind that this scenario
is associated with the critical realm of human health. Accurate predictions can facilitate
timely treatment and mitigate health complications, thereby fostering healthier lives.
Although no model is flawless, the current model provides valuable insights for
stakeholders involved in predicting, treating, and managing patients at risk of diabetes.
The model could be further improved through contributions from the National Institute
of Diabetes and Digestive and Kidney Diseases and healthcare professionals who have a
profound comprehension of the variables linked to diabetes and their impacts on diagnosis.
This would enable the model’s more reliable utilization in informed decision making
concerning patient health.
The strategy for disseminating the model to the general public holds immense potential
to raise awareness about the myriad factors associated with an increased risk of diabetes.
By doing so, individuals can make well-informed health-related decisions and engage in
preventative measures as necessary.
4. Final Reflections
4.1. Health Inequity and the Role of AI
Despite the promising advancements in AI and deep learning for predictive modeling
in diabetes diagnosis, several challenges remain. Issues such as data privacy, algorithmic
bias, and the interpretability of AI models need to be addressed to ensure the ethical and
effective deployment of these technologies in clinical settings [61]. Moreover, fostering col-
laboration between AI researchers, clinicians, and patients is essential for the development
of robust, patient-centered AI solutions for diabetes diagnosis and management [62].
The COVID-19 pandemic profoundly underscored the interwoven relationship be-
tween inequity and health, revealing a stark disparity in disease burden among individuals
from ethnically diverse backgrounds. This disproportionate impact was manifested through
elevated mortality rates, an increased incidence of Intensive Care Unit (ICU) admissions,
and heightened hospitalization figures, a phenomenon investigated by Bambra, et al.,
2020 [63].
Inequity, however, is far from a novel occurrence within global society. It represents
an entrenched, multifaceted issue pervading across international lines, a ubiquitous phe-
nomenon that fundamentally undermines human rights and hampers overall societal
progress. A plethora of interconnected factors actively contribute to the perpetuation of
these inequities, thereby entrenching the health disparities observed. Foremost among
these factors is poverty, a prevailing societal issue that is inextricably linked to detrimental
health outcomes. It propagates a cycle of deprivation where those living in economically
disadvantaged conditions are predisposed to poor health and limited access to quality
healthcare services. Environmental and climatic factors further exacerbate this issue, with
changes in the climate disproportionately affecting communities that lack the resources to
adapt effectively.
The ramifications are widespread, with alterations in disease patterns and heightened
risks of natural disasters, among other issues. Furthermore, an individual’s vulnerability
to trauma—be it psychological, physical, or societal—is also a significant determinant of
health outcomes.
Traumatic events, especially those recurring or persistent, can lead to long-lasting
physical and mental health problems, further exacerbating disparities. Gender and racial
imbalances serve as another pivot in the inequity equation. These deep-seated biases and
discriminations, both systemic and institutional, have tangible impacts on health. They
affect everything from access to healthcare services to disease outcomes and life expectancy.
Societal norms, which define and dictate acceptable behaviors and attitudes within a
community, also play a significant role. Norms that propagate discrimination, suppress
individual freedoms, or limit opportunities based on race, gender, class, or other factors
contribute to the creation and continuation of health inequities.
In summary, the intersectionality of these numerous, complex factors produces a
formidable challenge to health equity worldwide. The onus is on all stakeholders to address
these issues proactively and holistically, in an effort to alleviate the health disparities
entrenched within our societies.
4.2. AutoML and Sustainability

Our findings surrounding the application of AutoML techniques in diabetes diagnosis
have crucial implications, not only for healthcare outcomes but also for sustainability in the
healthcare sector.
To begin with, environmental sustainability can be impacted indirectly through the
more efficient utilization of resources. For instance, AutoML techniques can rapidly parse
through and analyze large volumes of patient data, making the diagnosis process more
efficient. This efficiency could translate into a reduction in the use of physical resources in
healthcare settings, including less need for physical storage as data can be more effectively
managed and utilized. Additionally, quicker and more accurate diagnoses could potentially
reduce the need for excessive testing, thereby reducing waste.
Economic sustainability is also a vital consideration. The application of AutoML
techniques in healthcare, especially in the diagnosis of diseases like diabetes, can lead to
cost savings for both healthcare providers and patients. By leveraging machine learning
algorithms for diagnosis, it could streamline the process, reduce manual labor, and con-
sequently decrease healthcare delivery costs. These savings could be redirected towards
other critical areas within healthcare, supporting more sustainable economic growth within
the sector.
Finally, in terms of social sustainability, the implications are profound. Improved diag-
nostic accuracy and speed through AutoML can enhance patient outcomes and experiences,
potentially reducing the societal burden of diseases like diabetes. More accurate and earlier
diagnoses could lead to more effective treatment plans, reducing complications, morbidity,
and mortality associated with the disease. The reduced healthcare burden can result in a
better quality of life, echoing the principles of social sustainability.
Lytras et al. [64] emphasized the revolutionary influence of Big Data and Data Ana-
lytics on contemporary business strategies. As various sectors assimilate these profound
insights, the evolution of AutoML and generative AI is set to usher in transformative
shifts in the near future. It’s clear that ‘Artificial Intelligence and Big Data Analytics for
Smart Healthcare’ stands as a pivotal reference for healthcare practitioners, highlighting
the transformative capabilities of emergent technologies such as AI, machine learning, and
data science [65,66]. Pioneering tools like AutoML, which optimize machine learning pro-
cesses, alongside generative AI with its ability to create new data instances, offer immense
potential to elevate healthcare efficiency and resilience.
In conclusion, while our research presents promising insights into the potential of
AutoML in diabetes diagnosis, we recommend further studies to understand and optimize
these techniques for greater sustainability benefits. Future research could focus on quantify-
ing the potential savings and benefits across the environmental, economic, and social dimen-
sions to provide a comprehensive view of the role of AutoML in sustainable healthcare.
Author Contributions: Conceptualization, L.P.Z. and M.D.L.; methodology, L.P.Z. and M.D.L.;
software, L.P.Z. and M.D.L.; validation, L.P.Z. and M.D.L.; formal analysis, L.P.Z. and M.D.L.;
investigation, L.P.Z. and M.D.L.; resources, L.P.Z. and M.D.L.; data curation, L.P.Z. and M.D.L.;
writing—original draft preparation, L.P.Z. and M.D.L.; writing—review and editing, L.P.Z. and
M.D.L.; visualization, L.P.Z. and M.D.L.; supervision, L.P.Z. and M.D.L.; project administration, L.P.Z.
All authors have read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: This study uses the Pima Indian Diabetes Dataset. The dataset, sourced
from Kaggle (https://www.kaggle.com/uciml/pima-indians-diabetes-database), is openly accessible
under a Public Domain License (accessed on 10 January 2023).
Conflicts of Interest: The authors declare no conflict of interest. The sponsors had no role in the
design, execution, interpretation, or writing of the study.
References
1. Saeedi, P.; Petersohn, I.; Salpea, P.; Malanda, B.; Karuranga, S.; Unwin, N.; Colagiuri, S.; Guariguata, L.; Motala, A.A.; Ogurtsova,
K. Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: Results from the International
Diabetes Federation Diabetes Atlas. Diabetes Res. Clin. Pract. 2019, 157, 107843. [CrossRef] [PubMed]
2. Bonnefond, A.; Unnikrishnan, R.; Doria, A.; Vaxillaire, M.; Kulkarni, R.N.; Mohan, V.; Trischitta, V.; Froguel, P. Monogenic
diabetes. Nat. Rev. Dis. Primers 2023, 9, 12. [CrossRef]
3. Tsao, C.W.; Aday, A.W.; Almarzooq, Z.I.; Alonso, A.; Beaton, A.Z.; Bittencourt, M.S.; Boehme, A.K.; Buxton, A.E.; Carson,
A.P.; Commodore-Mensah, Y. Heart disease and stroke statistics—2022 update: A report from the American Heart Association.
Circulation 2022, 145, e153–e639. [CrossRef] [PubMed]
4. Pareek, N.K.; Soni, D.; Degadwala, S. Early Stage Chronic Kidney Disease Prediction using Convolution Neural Network. In
Proceedings of the 2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), Salem, India,
4–6 May 2023; IEEE: Piscataway, NJ, USA, 2023; pp. 16–20.
5. Khunti, K.; Valabhji, J.; Misra, S. Diabetes and the COVID-19 pandemic. Diabetologia 2023, 66, 255–266. [CrossRef]
6. Esteva, A.; Robicquet, A.; Ramsundar, B.; Kuleshov, V.; DePristo, M.; Chou, K.; Cui, C.; Corrado, G.; Thrun, S.; Dean, J. A guide to
deep learning in healthcare. Nat. Med. 2019, 25, 24–29. [CrossRef] [PubMed]
7. Nazir, S.; Dickson, D.M.; Akram, M.U. Survey of explainable artificial intelligence techniques for biomedical imaging with deep
neural networks. Comput. Biol. Med. 2023, 156, 106668. [CrossRef]
8. Saranya, A.; Subhashini, R. A systematic review of Explainable Artificial Intelligence models and applications: Recent develop-
ments and future trends. Decis. Anal. J. 2023, 7, 100230.
9. Tschandl, P.; Codella, N.; Akay, B.N.; Argenziano, G.; Braun, R.P.; Cabo, H.; Gutman, D.; Halpern, A.; Helba, B.; Hofmann-
Wellenhof, R. Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion
classification: An open, web-based, international, diagnostic study. Lancet Oncol. 2019, 20, 938–947. [CrossRef]
10. Leslie, D.; Mazumder, A.; Peppin, A.; Wolters, M.K.; Hagerty, A. Does “AI” stand for augmenting inequality in the era of covid-19
healthcare? BMJ 2021, 372, n304. [CrossRef]
11. Smith, J.W.; Everhart, J.E.; Dickson, W.; Knowler, W.C.; Johannes, R.S. Using the ADAP learning algorithm to forecast the onset of
diabetes mellitus. In Proceedings of the Annual Symposium on Computer Application in Medical Care, Washington, DC, USA,
6–9 November 1988; American Medical Informatics Association: Bethesda, MD, USA, 1988; p. 261.
12. Larabi-Marie-Sainte, S.; Aburahmah, L.; Almohaini, R.; Saba, T. Current techniques for diabetes prediction: Review and case
study. Appl. Sci. 2019, 9, 4604. [CrossRef]
13. The National Institute of Diabetes and Digestive and Kidney Diseases. Available online: https://www.niddk.nih.gov/ (accessed
on 4 April 2023).
14. Dwivedi, Y.K.; Kshetri, N.; Hughes, L.; Slade, E.L.; Jeyaraj, A.; Kar, A.K.; Baabdullah, A.M.; Koohang, A.; Raghavan, V.; Ahuja,
M. “So what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative
conversational AI for research, practice and policy. Int. J. Inf. Manag. 2023, 71, 102642. [CrossRef]
15. American Artificial Intelligence Research Laboratory. Available online: https://openai.com/ (accessed on 1 August 2023).
16. Popova Zhuhadar, L. A Comparative View of AI, Machine Learning, Deep Learning, and Generative AI. Available online:
https://commons.wikimedia.org/wiki/File:Unraveling_AI_Complexity_-_A_Comparative_View_of_AI,_Machine_Learning,
_Deep_Learning,_and_Generative_AI.jpg (accessed on 30 March 2023).
17. Zhang, C.; Lu, Y. Study on artificial intelligence: The state of the art and future prospects. J. Ind. Inf. Integr. 2021, 23, 100224.
[CrossRef]
18. Mosavi, A.; Salimi, M.; Faizollahzadeh Ardabili, S.; Rabczuk, T.; Shamshirband, S.; Varkonyi-Koczy, A.R. State of the art of
machine learning models in energy systems, a systematic review. Energies 2019, 12, 1301. [CrossRef]
19. Fregoso-Aparicio, L.; Noguez, J.; Montesinos, L.; García-García, J.A. Machine learning and deep learning predictive models for
type 2 diabetes: A systematic review. Diabetol. Metab. Syndr. 2021, 13, 148. [CrossRef] [PubMed]
20. Chen, H.; Wang, Y.; Guo, T.; Xu, C.; Deng, Y.; Liu, Z.; Ma, S.; Xu, C.; Xu, C.; Gao, W. Pre-trained image processing transformer. In
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20–25 June 2021; pp.
12299–12310.
21. Monga, V.; Li, Y.; Eldar, Y.C. Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing. IEEE
Signal Process. Mag. 2021, 38, 18–44. [CrossRef]
22. Wang, Y.; Wang, D.; Geng, N.; Wang, Y.; Yin, Y.; Jin, Y. Stacking-based ensemble learning of decision trees for interpretable
prostate cancer detection. Appl. Soft Comput. 2019, 77, 188–204. [CrossRef]
23. Monshi, M.M.A.; Poon, J.; Chung, V. Deep learning in generating radiology reports: A survey. Artif. Intell. Med. 2020, 106, 101878.
[CrossRef] [PubMed]
24. Chen, C.; Zhang, P.; Zhang, H.; Dai, J.; Yi, Y.; Zhang, H.; Zhang, Y. Deep learning on computational-resource-limited platforms: A
survey. Mob. Inf. Syst. 2020, 2020, 8454327. [CrossRef]
25. Goodfellow, I. Nips 2016 tutorial: Generative adversarial networks. arXiv 2016, arXiv:1701.00160.
26. Goodfellow, I.J. On distinguishability criteria for estimating generative models. arXiv 2014, arXiv:1412.6515.
27. Shannon, C.E. A mathematical theory of communication. Bell Syst. Tech. J. 1948, 27, 379–423. [CrossRef]
28. Yang, Z.; Jin, S.; Huang, Y.; Zhang, Y.; Li, H. Automatically generate steganographic text based on markov model and huffman
coding. arXiv 2018, arXiv:1811.04720.
29. Van Der Merwe, A.; Schulze, W. Music generation with markov models. IEEE MultiMedia 2010, 18, 78–85. [CrossRef]
30. Yokoyama, R.; Haralick, R.M. Texture pattern image generation by regular Markov chain. Pattern Recognit. 1979, 11, 225–233.
[CrossRef]
31. Berger, M.A. Images generated by orbits of 2-D Markov chains. Chance 1989, 2, 18–28. [CrossRef]
32. Giret, A.; Julian, V.; Carrascosa, C. AI-supported Digital Twins in applications related to sustainable development goals. In
Proceedings of the International FLAIRS Conference Proceedings, Clearwater Beach, FL, USA, 14–17 May 2023; p. 36.
33. Abou-Foul, M.; Ruiz-Alba, J.L.; López-Tenorio, P.J. The impact of artificial intelligence capabilities on servitization: The moderating
role of absorptive capacity-A dynamic capabilities perspective. J. Bus. Res. 2023, 157, 113609. [CrossRef]
34. Batista, E.; Lopez-Aguilar, P.; Solanas, A. Smart Health in the 6G Era: Bringing Security to Future Smart Health Services. IEEE
Commun. Mag. 2023; early access.
35. Barrett, J.S.; Goyal, R.K.; Gobburu, J.; Baran, S.; Varshney, J. An AI Approach to Generating MIDD Assets Across the Drug
Development Continuum. AAPS J. 2023, 25, 70. [CrossRef] [PubMed]
36. Rezaei, M.; Rahmani, E.; Khouzani, S.J.; Rahmannia, M.; Ghadirzadeh, E.; Bashghareh, P.; Chichagi, F.; Fard, S.S.; Esmaeili, S.;
Tavakoli, R. Role of Artificial Intelligence in the Diagnosis and Treatment of Diseases. Kindle 2023, 3, 1–160.
37. Lin, J.; Ngiam, K.Y. How data science and AI-based technologies impact genomics. Singap. Med. J. 2023, 64, 59.
38. Flower, F.L.L. AI and Bioinformatics for Biology; Bharathiar University: Coimbatore, India, 2023.
39. Xie, J.; Luo, X.; Deng, X.; Tang, Y.; Tian, W.; Cheng, H.; Zhang, J.; Zou, Y.; Guo, Z.; Xie, X. Advances in artificial intelligence to
predict cancer immunotherapy efficacy. Front. Immunol. 2023, 13, 1076883. [CrossRef] [PubMed]
40. Fischer, L.H.; Wunderlich, N.; Baskerville, R. Artificial intelligence and digital work. In Proceedings of the Hawaii International
Conference on System Science, Maui, HI, USA, 3–6 January 2023.
41. Korke, P.; Gobinath, R.; Shewale, M.; Khartode, B. Role of Artificial Intelligence in Construction Project Management. In
Proceedings of the E3S Web of Conferences, Yogyakarta, Indonesia, 9–10 August 2023; EDP Sciences: Les Ulis, France, 2023;
Volume 405, p. 04012.
42. Popova Zhuhadar, L. AutoML Workflow. Available online: https://commons.wikimedia.org/wiki/File:AutoML_diagram.png
(accessed on 30 March 2023).
43. Zöller, M.-A.; Huber, M.F. Benchmark and survey of automated machine learning frameworks. J. Artif. Intell. Res. 2021, 70,
409–472. [CrossRef]
44. Yao, Q.; Wang, M.; Chen, Y.; Dai, W.; Li, Y.-F.; Tu, W.-W.; Yang, Q.; Yu, Y. Taking human out of learning applications: A survey on
automated machine learning. arXiv 2018, arXiv:1810.13306.
45. Shorten, C.; Khoshgoftaar, T.M.; Furht, B. Text data augmentation for deep learning. J. Big Data 2021, 8, 101. [CrossRef] [PubMed]
46. Zhou, J.; Zheng, L.; Wang, Y.; Wang, C.; Gao, R.X. Automated model generation for machinery fault diagnosis based on
reinforcement learning and neural architecture search. IEEE Trans. Instrum. Meas. 2022, 71, 3501512. [CrossRef]
47. Tamez-Pena, J.G.; Martinez-Torteya, A.; Alanis, I.; Tamez-Pena, M.J.G.; Rcpp, D.; Rcpp, L. Package ‘fresa. cad’. 2023. Available
online: https://vps.fmvz.usp.br/CRAN/web/packages/FRESA.CAD/FRESA.CAD.pdf. (accessed on 30 March 2023).
48. Reichenberger, S.; Sur, R.; Sittig, S.; Multsch, S.; Carmona-Cabrero, Á.; López, J.J.; Muñoz-Carpena, R. Dynamic prediction of
effective runoff sediment particle size for improved assessment of erosion mitigation efficiency with vegetative filter strips. Sci.
Total Environ. 2023, 857, 159572. [CrossRef] [PubMed]
49. Obermeyer, Z.; Powers, B.; Vogeli, C.; Mullainathan, S. Dissecting racial bias in an algorithm used to manage the health of
populations. Science 2019, 366, 447–453. [CrossRef] [PubMed]
50. Obermeyer, Z.; Emanuel, E.J. Predicting the future—Big data, machine learning, and clinical medicine. N. Engl. J. Med. 2016, 375,
1216. [CrossRef]
51. Ravì, D.; Wong, C.; Deligianni, F.; Berthelot, M.; Andreu-Perez, J.; Lo, B.; Yang, G.-Z. Deep learning for health informatics. IEEE J.
Biomed. Health Inform. 2016, 21, 4–21. [CrossRef] [PubMed]
52. Kavakiotis, I.; Tsave, O.; Salifoglou, A.; Maglaveras, N.; Vlahavas, I.; Chouvarda, I. Machine learning and data mining methods in
diabetes research. Comput. Struct. Biotechnol. J. 2017, 15, 104–116. [CrossRef]
53. Udler, M.S.; McCarthy, M.I.; Florez, J.C.; Mahajan, A. Genetic Risk Scores for Diabetes Diagnosis and Precision Medicine. Endocr.
Rev. 2019, 40, 1500–1520. [CrossRef] [PubMed]
54. Miotto, R.; Wang, F.; Wang, S.; Jiang, X.; Dudley, J.T. Deep learning for healthcare: Review, opportunities and challenges. Brief.
Bioinform. 2018, 19, 1236–1246. [CrossRef]
55. Goyal, P.; Choi, J.J.; Pinheiro, L.C.; Schenck, E.J.; Chen, R.; Jabri, A.; Satlin, M.J.; Campion, T.R., Jr.; Nahid, M.; Ringel, J.B. Clinical
characteristics of COVID-19 in New York city. N. Engl. J. Med. 2020, 382, 2372–2374. [CrossRef]
56. Chavez, S.; Long, B.; Koyfman, A.; Liang, S.Y. Coronavirus Disease (COVID-19): A primer for emergency physicians. Am. J.
Emerg. Med. 2021, 44, 220–229. [CrossRef]
57. Zia, U.A.; Khan, N. An Analysis of Big Data Approaches in Healthcare Sector. Int. J. Tech. Res. Sci. 2017, 2, 254–264.
58. Bollier, D.; Firestone, C.M. The Promise and Peril of Big Data; Aspen Institute, Communications and Society Program: Washington,
DC, USA, 2010.
59. Provost, F.J.; Fawcett, T.; Kohavi, R. The case against accuracy estimation for comparing induction algorithms. In Proceedings of
the ICML, Madison, WI, USA, 24–27 July 1998; pp. 445–453.
60. Green, D.M.; Swets, J.A. Signal Detection Theory and Psychophysics; Wiley: New York, NY, USA, 1966; Volume 1.
61. Vayena, E.; Blasimme, A.; Cohen, I.G. Machine learning in medicine: Addressing ethical challenges. PLoS Med. 2018, 15, e1002689.
[CrossRef] [PubMed]
62. Chen, J.H.; Asch, S.M. Machine learning and prediction in medicine—Beyond the peak of inflated expectations. N. Engl. J. Med.
2017, 376, 2507. [CrossRef] [PubMed]
63. Bambra, C.; Riordan, R.; Ford, J.; Matthews, F. The COVID-19 pandemic and health inequalities. J. Epidemiol. Community Health
2020, 74, 964–968. [CrossRef] [PubMed]
64. Lytras, M.D.; Raghavan, V.; Damiani, E. Big data and data analytics research: From metaphors to value space for collective
wisdom in human decision making and smart machines. Int. J. Semant. Web Inf. Syst. IJSWIS 2017, 13, 1–10. [CrossRef]
65. Lytras, M.D.; Visvizi, A. Artificial intelligence and cognitive computing: Methods, technologies, systems, applications and policy
making. Sustainability 2021, 13, 3598. [CrossRef]
66. Lytras, M.D.; Visvizi, A.; Sarirete, A.; Chui, K.T. Preface: Artificial intelligence and big data analytics for smart healthcare: A
digital transformation of healthcare Primer. Artif. Intell. Big Data Anal. Smart Healthc. 2021, xvii–xxvii.
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.

Sustainability 15 13484 v2

Uploaded by

Copyright:

Available Formats

Sustainability 15 13484 v2

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Sustainability 15 13484 v2

Uploaded by

Copyright:

Available Formats

sustainability

Academic Editor: Petra Poulová 1. Introduction

Sustainability 2023, 15, 13484. https://doi.org/10.3390/su151813484 https://www.mdpi.com/journal/sustainability

1.2. Scientific Context of the Study

Sustainability 2023, 15, x FOR PEER REVIEW 4 of 24

1.2.2. Why Is Generative AI Crucial in Today’s Technological Landscape?

In contrast, Ref. [44] perceives AutoML as a harmonious blend of automation and

1.2.4. AutoML and Its Role in Healthcare

1.2.5. AutoML in Diabetes Diagnosis

2. Materials and Methods

model, which is subsequently subjected to a rigorous evaluation process. This process of

2.1. Problem Understanding and Determining the Purpose of the Analysis

2.2. Data Exploration and Pre-Processing

Table 1. Data dictionary.

Attribute Description Data Type Range

The attribute ‘Pregnancies’ quantifies the total number of pregnancies an individual

Sustainability 2023, 15, x FOR PEER REVIEW 10 of 24

Table 2. Statistical summary.

Table 3. Correlation matrix.

2.3. Feature Selection

2.4. Model Generation and Results

2.5. Model Evaluation

Table 4. Precision results.

Model Precision Standard Deviation Gains Total Time

Table 5. Recall results.

Model Recall Standard Deviation Gains Total Time

Table 6. Accuracy results.

Model Accuracy Standard Deviation Gains Total Time

Table 7. Confusion matrix for accuracy.

true false true true class precision

Table 8. Overall performance.

Generalized Linear Model Logistic Regression Model

2.6. Model Optimization—Prescriptive Analytics

Figure 8. Generalized Linear Model after optimization.

prescriptive modeling in diabetes diagnosis underscored their efficiency in discerning risk

4.2. AutoML and Sustainability

You might also like