See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/379872405

APPLICATION OF DATA MINING IN HEALTH CARE

Article in International Research Journal of Modernization in Engineering Technology and Science · April 2024

CITATIONS READS

0 438

1 author:

Yabin Paul Thomas

Saintgits College of Engineering
1 PUBLICATION 0 CITATIONS

SEE PROFILE

All content following this page was uploaded by Yabin Paul Thomas on 17 April 2024.

The user has requested enhancement of the downloaded file.

 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868 www.irjmets.com

APPLICATION OF DATA MINING IN HEALTH CARE

Yabin Paul Thomas*1, Sobin Thomas Sony*2, Alan Sabu*3, Abhijith G Nair*4
*1,2,3,4Third Year BCA Student, PG Department Of Computer Applications And Artificial Intelligence,
Saintgits College Of Applied Sciences Kottayam, Kerala, India.
ABSTRACT
In In today's rapidly evolving technological landscape, organizations across various fields are increasingly
relying on data mining technology. Notably, the healthcare sector, vital for everyone's well-being, has witnessed
significant advancements. Technologies for examining physical conditions and detecting diseases have become
instrumental in preventive healthcare. Awareness about symptoms empowers individuals to take proactive
measures, preventing the onset of certain diseases. Given the vast amount of medical data available, efficient
methods for data collection from diverse databases are essential. Modern data mining technologies play a
pivotal role in this context. This study explores the specific applications of data mining in the medical field,
emphasizing its relevance and success in healthcare due to its high accuracy in prediction and results.
Keywords: Data Mining Technology, Healthcare Sector, Examining Physical Conditions, Detecting Diseases,
Preventive Healthcare, Symptoms Awareness, Proactive Measures, Medical Data, Modern Data Mining
Technologies, Applications.
I. INTRODUCTION
Data mining, a process of uncovering hidden data, relationships, and patterns from extensive datasets, stands as
a transformative method compared to traditional approaches. Organizations harness data mining technology,
extracting valuable insights from their data warehouses. In the medical industry, diverse data mining tools help
identify contemporary patterns, making it a quantitative and user friendly approach. Readability and error-
correction capabilities enhance its utility. Data Mining techniques are used for various industrial purposes like
automation, accident detection especially in cloud environment, health care and business sector. The healthcare
sector in India, comprising public and private organizations, faces the challenge of managing substantial data
related to patients, medicines, and diseases. With a focus on low-cost medical treatment for the economically
disadvantaged, public sector healthcare organizations play a crucial role. Given the enormity of healthcare data,
the demand for new technologies and techniques for efficient data management is evident. This paper explores
the applications of data mining in healthcare, emphasizing its indispensability in addressing contemporary
challenges and enhancing healthcare practices.
II. LITERATURE SURVEY
1. Data Mining Techniques in Healthcare: A Review (2005) - Han, J., & Kamber, M.
 This foundational work provides an overview of various data mining techniques and their applications in
healthcare.
 Discusses the challenges and opportunities of applying data mining in healthcare, emphasizing the potential
for improved decision-making and patient care.
2. Applications of Data Mining Techniques in Healthcare and Prediction of Heart Attacks (2012) - Rana,
S., & Sharma, A.
 Focuses on the application of data mining in predicting heart attacks, showcasing how predictive modeling
can assist in identifying high-risk patients.
 Discusses the use of decision trees, neural networks, and other techniques for predicting cardiovascular
events.
3. A Survey of Data Mining Techniques in the Field of Healthcare (2014) - Bellazzi, R., & Zupan, B.
 Provides a comprehensive survey of data mining techniques used in healthcare, covering areas such as
disease prediction, diagnosis, and treatment planning.
 Highlights the challenges and future directions in the integration of data mining in healthcare systems.

4. Data Mining in Healthcare - A Review (2015) - Kumar, P., & Deep, A.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[2452]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868 www.irjmets.com
 Discusses the role of data mining in healthcare management, patient care, and disease prediction.
 Emphasizes the importance of efficient data preprocessing and feature selection in improving the accuracy
of predictive models.
5. Big Data Analytics in Healthcare: Promise and Potential (2016) - Dumbill, E.
 Explores the impact of big data analytics, including data mining, in healthcare, emphasizing the potential for
personalized medicine and improved patient outcomes.
 Discusses challenges related to data privacy, security, and interoperability.
III. METHODOLOGY
Method and analysis which is performed in your research work should be written in this section. A simple
strategy to follow is to use keywords from your title in first few sentences.
Data Mining
Data mining is a dynamic process that involves the extraction and sorting of valuable information from
extensive datasets. Essentially, data mining tools serve as predictive instruments, utilizing existing data or
conducting analyses to foresee future trends. Within the realm of data mining, various parameters play crucial
roles, each serving distinct purposes. Path analysis involves uncovering patterns within interconnected data
points, revealing relationships that exist among them.
Data Mining Application Areas
Nowadays data mining is broadly used in many fields. Data mining is used to automate the predication from the
large data. Some of the data mining applications in various fields are;
• Business
• Healthcare
• Telecommunication
• Marketing and Sales
• Road Safety
• Education
Data Mining Application of HealthCare
Data mining has been used intensively and widely by numerous industries. In healthcare, data mining is
becoming more popular nowadays. Data mining applications can incredibly benefit all parties involved in the
healthcare industry. For example, data mining can help the healthcare industry in fraud detection and abuse,
customer relationship management, effective patient care, and best practices for affordable healthcare services.
The large amounts of data generated by healthcare transactions are too complex and huge to be processed and
analysed by conventional method.
Treatment Effectiveness: Data mining facilitates the identification of specific patient characteristics or
demographic factors that may influence the success of certain treatments. By analysing large datasets,
healthcare professionals can gain insights into the nuances of treatment responses among diverse patient
populations. This knowledge can inform personalized and more effective treatment plans, ultimately improving
overall healthcare outcomes.
Healthcare Management: Data mining involves using advanced analytical techniques to extract valuable
insights from medical data. It aids in patient management, disease prediction, resource allocation, fraud
detection, decision support, quality improvement, personalized medicine, and epidemiological studies. This
leads to better decision-making, improved resource utilization, and enhanced patient care.
Customer Relationship Management: Data mining involves using analytical techniques to understand and
improve interactions with customers. It includes segmentation for targeted strategies, predictive analytics for
future behaviour, churn prediction, personalized marketing, and analysis of customer satisfaction. Additionally,
data mining helps in detecting fraud, predicting customer lifetime value, and leveraging social media data for
better insights. Overall, CRM in data mining enhances customer engagement and supports informed decision-
making for businesses.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[2453]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868 www.irjmets.com
Fraud and Abuse: In data mining, fraud and abuse detection are critical applications. By analysing patterns
and anomalies within large datasets in cloud [5], data mining helps identify irregularities or fraudulent
activities. It plays a key role in safeguarding systems, preventing financial losses, and ensuring the integrity of
data. The technology enables early detection of suspicious behaviour, making it an indispensable tool for
maintaining security and trust in various domains, including finance, healthcare, and online platforms. This
paper explores the synergy between data mining and healthcare by highlighting how data mining techniques
contribute to the analysis, storage, and processing of substantial healthcare datasets. The integration of data
mining and healthcare forms a cohesive model within the realm of distributed network technology. In this
context, the cloud plays a pivotal role, providing support for big data in terms of data security, encryption,
integrity, transformation, heterogeneity, and quality.
Despite encountering challenges such as scalability, availability, and bandwidth limitations for data transfer in
the integration of data mining with cloud technology, ongoing efforts by cloud providers aim to address these
issues. Solutions are being continuously developed to enhance the efficiency of utilizing data mining in
healthcare on the cloud platform. The integration and application of data mining in healthcare are anticipated
to have a profound and expanding impact in the years to come.
IV. RESULTS
Table 1. Results of comparative analysis of various disease in Healthcare:
Accuracy
Types of Data Mining Traditional Level for
S. No Technique Algorithm
Disease Tool Method DM
Applications
Naïve Bayes Probability
1 Tuberculosis WEKA KNN 78 Percent
classifier statistics
2 Heart Disease ODND,NCC2 Classification Naive Probability 60 Percent
Decision
3 Kidney RST Classification Statistics 76 Percent
making
Diabetes C4.5 Neural
4 ANN Classification 82 Percent
Mellitus Algorithm Network
Blood bank
5 WEKA Classification J48 90 Percent
Sector
SPSS
6 Dengue C5.0 Statistics 80 Percent
Modeler
7 Hepatitis C SNP INFORMATION Gain Decision rule 74 Percent
Neural 84.9
8 Heart disease Python Classification MLP
Network Percent
Machine 79.8
9 Diabetes WEKA Classification SMO
learning Percent
Neural 95.025
10 Heart Disease Python Classification ANN
Network Percent

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[2454]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868 www.irjmets.com
90 95.025
80 84.9
82 80 79.8
70 78 76 74
60
60
50
40

30
20
10
0
Tuberculosis Heart Kidney Diabetes Dengue Hepatitis C Heart Diabetes Heart
Disease Mellitus disease disease
Figure 2: Accuracy Level Chart
V. CONCLUSION
This paper explores the synergy between data mining and healthcare by highlighting how data mining
techniques contribute to the analysis, storage, and processing of substantial healthcare datasets. The
integration of data mining and healthcare forms a cohesive model within the realm of distributed network
technology. In this context, the cloud plays a pivotal role, providing support for big data in terms of data
security, encryption, integrity, transformation, heterogeneity, and quality.
Despite encountering challenges such as scalability, availability, and bandwidth limitations for data transfer in
the integration of data mining with cloud technology, ongoing efforts by cloud providers aim to address these
issues. Solutions are being continuously developed to enhance the efficiency of utilizing data mining in
healthcare on the cloud platform. The integration and application of data mining in healthcare are anticipated
to have a profound and expanding impact in the years to come.
VI. REFERENCES
[1] NV Balaji, 2021, Heart disease prediction system using Correlation Based Feature Selection with
Multilayer Perceptron approach, IOP conference series: materials science and engineering
[2] Ambily Merlin Kuruvilla, 2019, Predicting Diabetes Mellitus Using Feature Selection And Classification
Techniques In Machine Learning Algorithms, Karpagam JCS
[3] Ambily Merlin Kuruvilla, 2021, Improved Artificial Neural Network Through Metaheuristic Methods
And Rough Set Theory For Modern Medical Diagnosis, Indian Journal of Computer Science and
Engineering.
[4] PC Sherimon, 2023, Customized Hybrid Deep Learning Model for Road Accident Detection Based on
CCTV Images, 2023 IEEE International Performance, Computing, and Communications Conference
(IPCCC).
[5] RB Ansaba, 2022, Big Data in Cloud Computing Environment, International Journal Of Recent Trends In
Multidisciplinary Research.
[6] Dr. John T Abraham, 2018 Volume 3, Issue 11, Application of artificial intelligence in educational
scenario: computer assisted instructions (CAI) - a tool for improving teaching learning process ,
International Journal of Scientific Development and Research (IJSDR)
[7] V.V. Ramalingam, 2018,” Prediction of Heart Diseases Using Machine Learning”, International Journal of
Engineering and Technology.
[8] Amin Ul Haq 2019 A Hybrid Intelligence System Frame Work for Prediction of Heart Disease Using ML,
Mobile Information Systems.
[9] Shadman Nashif Heart Disease Detection by Using Machine Learning Algorithm and a Real time
Cardiovascular Health Monitoring System World journal of Engineering and Technology,vol.06
no.04,2018,article id 88650.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[2455]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868 www.irjmets.com
[10] Poornima Singh 2018 Effective heart disease prediction system using data mining techniques
International journal of Nano medicine.
[11] M. Gunay and T. Ensarı 2019 Predictive churn analysis with machine learning methods IEEE 26th
Signal Processing and Communications Applications Conference (SIU), Izmir, 2018, pp. 1- 4.
[12] R. Suguna, M. Shyamala Devi and Rincy Merlin Mathew 2019 Customer Churn Predictive Analysis by
Component Minimization using Machine Learning International Journal of Innovative Technology and
Exploring Engineering.
[13] Devansh Shah, Samir Patel and Santosh Kumar Bharti, 2020, Heart Disease Prediction using Machine
Learning Techniques, Springer.
[14] Hamidreza and Ashrafi Esfahani, 2017, Cardiovascular disease detection using a new ensemble
classifier, IEEE International Conference on Knowledge-Based Engineering and Innovation (KBEI).

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[2456]
View publication stats