Volume 20 No 22 (2022)
 Download PDF
A Machine Learning Approach for Predicting Onset and Progression-Towards Early Detection of Chronic Diseases
Vaibhav Kumar , Bhagwinder Singh , Shilpi Sharma , Dolly Sharma
The paper suggests utilizing data mining and machine learning approaches to diagnose chronic diseases due to their cost-effectiveness and ability to analyse large amounts of patient data to identify patterns that may not be detectable by human experts. This enables early detection of diseases, which can improve patient outcomes. Using machine learning techniques can facilitate delivery for customized medical care to individual patients. This approach allows healthcare providers to develop treatment plans that are tailored to the specific needs and circumstances of each patient, resulting in improved outcomes.In modern times, people are exposed to environmental conditions and adopt lifestyles that make them susceptible to various chronic illnesses. Early detection of illness is crucial, but accurate prediction based solely on symptoms is challenging for doctors. Data mining can aid in disease prediction by finding hidden patterns in the vast amount of medical data generated each year. With the increasing amount of medical data available, accurate analysis can greatly benefit patient care. We propose a healthcare model that uses mining algorithms such as K nearest neighbours, Decision Trees and Logistic Regression, along with a dataset of disease symptoms. Each model also takes into account a person's lifestyle habits and medical check-up information for accurate disease prediction. Logistic Regression has a prediction accuracy of 95.6% for Heart disease, which is higher than the accuracy of Naive Bayes algorithm. On the other hand, the Decision Tree algorithm has an accuracy of 99% for predicting patients with thyroid disease. It is noteworthy that among patients who do not have any thyroid problems, Logistic Regression has an accuracy of 81.16% in predicting those with hyperthyroidism or hypothyroidism.
Chronic Disease, Machine Learning, Logistic Regression, Decision Tree
Copyright © Neuroquantology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.