Chapter 2

Literature Review
Yang Li, Biaoan Shan et al. [1] In this paper, the author presented a comprehensive review on the
application of ML and BL techniques in the healthcare sector. ML is the leading technology for
performing complex analysis, intelligent judgment, and creative problem solving in healthcare.
Smart healthcare has the characteristics of preventability, immediacy, and interconnection of
information. Through wireless network, using portable mobile devices, medical staff can
constantly perceive, process, and analyze major medical events (preventability). Doctors can
grasp the case information of each patient at any time and quickly develop a diagnosis and
treatment plan (immediacy). Medical personnel can log in the medical system anywhere to
inquire about medical images and medical advice and patient’s referral information can be
accessed at any hospital through the medical network (interconnection of information). These
functions are supported by new digital technologies. BC follows absolute privacy rules to
identify users related to transactions. It is mainly used for the management of information
systems to help achieve secure storage, transactions, process automation, and other applications.
Our research will provide healthcare practitioners with an insight to keep ML and BC
technologies fully utilized.

Taher M., Kamrul Hasan et al. [2] This paper aims to provide a baseline study toward IoT,
smart healthcare, smart cities, machine learning and their co-relation. . In a broader perspective
we can refer to blockchain technology in the IoT as a “secure by design” system that can be used
to address security concerns in IoT applications, considering the impressive features of
blockchain technology such as immutability, transparency, auditability, data encryption and
operational resilience, as explained. Networked smart home applications will also be helpful in
this context. The patient, who gets up in the morning and stands in front of a mirror equipped
with cameras, will be able to establish a connection with the attending physician if he has
symptoms. Based on the patient data, he then decides in real time which steps are sensible.
However, the whole thing goes even further: in the worst case, fall sensors installed in the carpet
and in the house or suitable healthcare wearable’s could detect when a patient falls and is lying
on the floor or when help is required for other reasons. Automated in the context of a smart city,
the corresponding control center could be informed and an ambulance sent, with the appropriate
hospital with the appropriate capacity being selected based on the diagnosis. In combination with
smart diagnostics and wearable’s, such smart infrastructures could help older patients in
particular to live independently longer than before in their own homes and still not have to do
without reliable mechanisms for care. The acquisition of patient data takes up a (too) large part
of the limited time of nursing staff, especially in the hospital environment. Here, intelligent
devices can be used to collect the important patient data via voice command, for example, and
assign it correctly and evaluate it with the help of artificial intelligence and big data. This cannot
all be recorded using wearables but is often also obtained from the impression and assessment of
the patient by the nursing staff. The nursing staff would then have more time for the actual care
and would not have to record all the data or even later transfer it to the electronic patient file via
a PC.

Habibzadeh, Soyata et al. [3] This paper, the author studied emerging trends in smart
healthcare applications and key technological developments that have a direct impact in these
transitions. The authors also reviewed different security considerations in smart healthcare
systems and their consequences and counter measures. He analyzed security and privacy issues
in the IoT’s application in smart cities and identified their proposed solutions. Authors tend to
use graph theory for rectification of highlighted issues since the conventional approaches do not
provide optimal results for security and safety critical systems. The authors consider smart city
systems as a whole and discuss how a smart healthcare system interacts and collaborates with
smart city infrastructure and how it works for the healthcare field. Several case studies are also
reviewed by the authors and they suggest how a more powerful, integrated and effective system
can be built out of smart healthcare systems. A comprehensive survey study was performed
describing IoT technologies for smart cities and the main components and features of a smart
city. He also explained practical experiences and challenges faced by implementers around the
world. A comprehensive survey of potential techniques and applications of collaborative drones
with the IoT which have been recently used to enhance the smartness of smart cities based on
data collection, privacy, security, public safety, disaster management, energy consumption and
quality of life in smart cities. The applications of machine learning techniques for big data
analysis in smart healthcare systems. The authors also highlighted several strengths and
weaknesses for existing approaches with a special focus on research challenges in this aspect. He
proposed a model for a smart health monitoring system based on fog computing. The proposed
architecture claims to acknowledge the underlying problems of a clinic-centric healthcare system
and change it to a smart patient-centric healthcare system.
Ullah, Al-Turjman et al. [4] In this paper, the author performed a review to evaluate the roles of
artificial intelligence, machine learning and deep reinforcement learning in the evolution of
smart cities to develop an effective system for possible monitoring of losses, traffic management,
smart city innovations, digitalized and integrated systems and software. He introduced an ML-
based, distributed big data analysis framework for next gen web for the IoT and demonstrated
that the suggested distributed framework is more efficient than the conventional frameworks
Deep Block Scheme, which is a deep learning-based blockchain scheme for secure smart cities.
The authors presented a case study of car manufacturing for the proposed scheme and compared
it with existing research with parameters such as security and privacy. Energy efficiency in the
IoT is also one of the key areas of research. A systematically analyzed IoT architecture and the
power distribution within. A comprehensive summary of the energy consumption model in the
IoT and pros and cons of improving energy efficiency were presented an OTS (one-time
signature) scheme-based secure architecture for an energy-efficient IoT in edge infrastructure.
The authors used a blockchain-based, distributed network at the fog layer to improve the security
and privacy of the architecture. A lot of research has been carried out over the course of the past
few years for the IoT, smart cities, smart healthcare, blockchain and AI in the IoT. Use of WSN
in smart cities and in particular healthcare has opened up several new research avenues and
challenges for smart cities which are addressed by employing AI and blockchain technologies.

Asif Ahmed, Sazid Alam et al. [5] In this paper, Critical Patient Caring or monitoring System
is a process where a doctor can continuously monitor more than one patient, for more than one
parameter at a time in a remote place and also can have control over medicine dosage. Devices
such as vital sign monitors, mechanical ventilators and dialysis machines, and some others more
are used to support critical patients whose bodies need time to recover and repair. Most of the
machines are managed manually by supervising the patient's condition and test reports. So, we
thought to automate the process and decision-making ability with the help of modern technology,
especially the auto deployable machine learning models and cloud computing. Machine learning
models can predict the near future condition of the patients, whether their condition will increase
or decrease, whether they need any immediate support or not. To generalize our models and data,
they have selected IBM Cloud as a PaaS which altogether spans public, private and hybrid
environments. The ml models run within the cloud service and also trains with the auto-deployed
data, the CPMS also can access the Cloud services through Bluemix. The most significant of this
paper carries the auto deployable machine learning model within the cloud storage with
noteworthy accuracy.

Nejkar, Nimbhorkar et al. [6] There is been significant progress in patient monitoring systems
using different embedded and a real-time operating system (RTOS). He discussed, monitoring
patient's body temperature, respiration rate, heartbeat, and body movement using a Raspberry Pi
board. They provided an IoT based patient monitoring system. This prototype can also serve
critical patients. In the case of machine learning, there are many novel works describing
mortality prediction of the patients using Cardiac-intensive-care Warning Index (C-WIN)
system, Predicting in-hospital mortality of patients with acute kidney injury in the ICU using
random forest model and also different models validate the models that are being used to predict
the mortality. Studying different novel works and approaches, they came to a conclusion to
bridge the gap between the automated patient caring system with machine learning and real-time
feedback facility. Also, we had to consider the state of the art that can be done in all the
requirements and effective costing.

Naveenkumar, Kirubhakaran et al. [7] This paper aims the user/patient may make an
informed decision to see a doctor about their particular symptoms, resulting in improved patient
health services. The Naïve Bayes Classifier technique is used to analyses a large amount of data
obtained. For each sub-field of Disease Predictions, we also demonstrated how symptom data
storage combined with data classification can assist the administrative, clinical, academic and
educational aspects of Disease Prediction from Symptoms. There are a host of data collection
issues that can be discussed in terms of health prediction. It's an AI branch that promotes the idea
that machines can learn from data, recognize patterns, and make decisions with minimal human
intervention. Machine learning is a programming algorithm that uses sample data or previously
collected data to optimize results with high accuracy. There are two stages of the machine
learning algorithm: preparation and research. The signs and symptom logs of the user/patient are
used to predict the illness. Machine Learning technology offers a strong application forum in the
medical sector to address health disease prediction concerns based on the user/patient
experience.
Shabaz Ali, G. Divya, et al. [8] In this paper the data mining is a process of knowledge
discovery from unknown or useless datasets. There are various techniques of data mining that are
used to process the data and convert them as useful information. It can be used in the various
fields such as business analysis, healthcare, stock management etc. Medical field has wide
amount of data that can be processed by the help of data mining techniques. It might have
happened before that yourself or someone near you want immediate help of doctor but could not
find anyone. By creating a model that can predict the diseases based on user symptoms is quite
helpful in getting fast and appropriate medical facilities for patients. The timely analysis of data
and gaining accurate prediction of diseases from symptoms can save many lives. Early detection
of diseases helps doctor to give accurate medication. In the field of medicine different algorithms
of machine learning are used for predicting different diseases and helps the physicians to
diagnose fast. Based on the input of data the accuracy of results may vary.

G.Pooja reddy et al. [9] In this paper “Smart E-Health Prediction System Using Data Mining”
most of the topics covered are on the system architecture. In this paper the design aspects of the
system are primarily focused. In this paper the author has given a detailed framework to beat the
downside of existing system. The smart health framework is used to implement the design
aspects of the project. This framework asks for uses input and gather the symptoms to predict the
disease based on data mining techniques. There are various modules such as login- used for
authentication of patient and doctor, Diseases prediction, Doctor Searching, Feedback and
Chatting with doctor for clearing patient doubts. There are some advantages such as finding the
nearest doctor option to find doctor near to our location. These features can be used for better
implementation of the system to help patients. This paper is used for analyzing the various data
mining techniques that can be used for healthcare services. The author has discussed about the
different types of datasets that can be used in various fields of medical and healthcare services.
The methodologies for preprocessing of data and probabilities used in the algorithm are
explained clearly. The parameters of heart disease are specified and visualization of datasets are
shown.

Krishan Kumar, Aejaz Hassan et al. [10] This paper serves many applications and techniques
of machine learning in healthcare system. The healthcare sector is being transformed by the
ability to record massive amounts of information about individual patients, the enormous volume
of data being collected is impossible for human beings to analyze. Machine learning is one of the
emerging approaches in the health sector. The system may also use for making decision
regarding whether patient require more clinical care (therefore improving patient safety). The
data used in this study were related to general surgery patients from a single medical institution.
Proceeding with the evaluations of clinical cases from other hospitals is critical for confirming
the validity of the model. The data collected from the clinical pathway and supervised learning
techniques, can be considered for use in the model. As increasing population of patients the
machine learning will allow health care systems to make care more efficiently and appropriately.
With the help of machine learning methods/approaches we identify the patients and provide
proper care management. Patients can be identified (e.g. on the basis of patient’s characteristics,
risks, beliefs and genetic profile). The changing of healthcare by using predictive analytics for
proper treatment and decision without any risk factor. Machine learning have been recently
covers all the fields of healthcare services even though computers will completely replace
doctors, nurses and modern technology.

Zeina Rayan, Marco Alfonse et al. [11] In this paper, the author is concerned with designing
and developing algorithms that enable the computers to evolve their behaviors according to
empirical data. The ML approach is evolving rapidly as a result of the improvement of the ML
algorithms, enhanced methods of capturing data, improved computer networks, new sensors/IO
units, and the interest in self-customization to users’ behavior. ML plays an important role in s-
Health, it can improve the quality of healthcare services by providing accurate medical
diagnosis, predicting diseases in early stages and disease analyses. The e-Health can be defined
as “an emerging field in the intersection of medical informatics, public health and business,
referring to health services and information delivered or enhanced through the Internet and
related technologies. In a broader sense, the term characterizes not only a technical development,
but also a state-of-mind, a way of thinking, an attitude, and a commitment for networked, global
thinking, to improve health care locally, regionally, and worldwide by using information and
communication technology.” There is an intersection between s-Health and Mobile Health (m-
Health); m-Health can be defined as “emerging mobile communications and network
technologies for healthcare systems”. The idea of a smart health system is that it uses all data
coming from sensors on the patient body, smart homes, smart city infrastructure, and robots to
help make better decisions and improve healthcare by providing emergency response and paging
doctors, nurses, and technicians. The data security and privacy plays a big role in both s-Health
and smart cities where gathering so many information about citizens could possibly violate the
citizen privacy.

References:

[1]. Yang Li, Biaoan Shan, Beiwei Li, Xiaoju Liu, Yi Pu, “Literature Review on the Applications of
Machine Learning and Block chain Technology in Smart Healthcare Industry: ABibliometric Analysis”,
Journal of Healthcare Engineering Volume 2021, Article ID 9739219, 11 pages
https://doi.org/10.1155/2021/9739219

[2]. Taher M. Ghazal, Mohammad Kamrul Hasan, Muhammad Turki Alshurideh, Haitham M. Alzoubi,”
IoT for Smart Cities: Machine Learning Approaches in Smart Healthcare—A Review”, Future Internet
2021, 13, 218.

[3].Habibzadeh, H.; Soyata, T. Toward uniform smart healthcare ecosystems: A survey on prospects,
security, and privacy considerations. In Connected Health in Smart Cities; Springer: Cham, Switzerland,
2019; ISBN 9783030278441.

[4].Ullah, Z.; Al-Turjman, F.; Mostarda, L.; Gagliardi, R. Applications of artificial intelligence and
machine learning in smart cities. Computer Community 2020, 154, 313–323.

[5]. Asif Ahmed Neloy, Sazid Alam, Rafia Alif Bind, Nusrat Jahan Moni, “ Machine Learning based
Health Prediction System using IBM Cloud as PaaS”, Proceedings of the Third International Conference
on Trends in Electronics and Informatics (ICOEI 2019) IEEE Xplore Part Number: CFP19J32-ART;
ISBN: 978-1-5386-9439-8.

[6]. Nejkar, V. A., Nimbhorkar, S. R., Paliwal, J. K., & Shrivastav, A. A. (2018). Smart Nanny an IoT
Based Baby Monitoring System. i-Manager's Journal on Computer Science.

[7]. Naveenkumar S , Kirubhakaran R , Jeeva G , Shobana M, Sangeetha K, “Smart Health Prediction

[9] G.Pooja reddy, “Smart E-Health Prediction System Using Data Mining”, International Journal of
Innovative Technology and Exploring Engineering (IJITEE), Vol-8 Issue-6, April 2019.

[10] Krishan Kumar, Aejaz Hassan Paray, “A Survey of Different Approaches of Machine Learning in
Healthcare Management System”, Int. J. Advanced Networking and Applications Volume: 11 Issue: 03
Pages: 4270-4276 (2019) ISSN: 0975-0290

[11]. Zeina Rayan, Marco Alfonse, Abdel-Badeeh M.Salem, “Machine Learning Approaches in Smart
Health”, 8th Congress of Information and Communication Technology, ICICT 2019.