Medical Risk Classifier : Heart Disease Risk Prediction Using Regularized Logistic Regression

Heart disease is one of the major health problems affecting people across the world. Identifying the possibility of heart disease at an early stage can help in taking timely medical advice and reducing potential risks. However, analysing different health-related factors manually can sometimes be difficult and may lead to errors. To address this problem, this project introduces a Medical Risk Classifier, a machine learning-based system designed to predict the risk of heart disease using basic clinical information. The system uses the UCI Heart Disease (Cleveland) dataset, which contains patient details such as age, blood pressure, cholesterol level, chest pain type, maximum heart rate and other medical attributes. The collected data is cleaned and prepared before applying a regularized Logistic Regression algorithm to classify the possibility of heart disease. L2 regularization is used to reduce overfitting and improve the stability of the model. The system is evaluated using stratified 5-fold cross-validation, along with performance measures such as precision, recall, F1-score, ROC-AUC and confusion matrix. A key focus of this project is to improve the model's ability to identify patients who may have heart disease rather than depending only on overall accuracy. For this reason, the decision threshold is adjusted to give greater importance to recall and reduce the chances of missing positive cases. The project also examines the contribution of different clinical features to the model's predictions. Overall, the Medical Risk Classifier demonstrates how machine learning can be used to analyse medical data and support preliminary heart disease risk assessment through a simple and interpretable approach. It is developed for academic and experimental purposes and is not intended to replace professional medical diagnosis.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-19
DOI
https://doi.org/10.5281/zenodo.24370376
Primary Topic
Artificial Intelligence in Healthcare
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Medical Risk Classifier : Heart Disease Risk Prediction Using Regularized Logistic Regression

Prajwal Rai, Anupama Surya, Nilesh Kumar Rajbhar, Nitin Kumar et al.
Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence in Healthcare
article

Medical Risk Classifier : Heart Disease Risk Prediction Using Regularized Logistic Regression

Prajwal Rai, Anupama Surya, Nilesh Kumar Rajbhar, Nitin Kumar, Nishika, Prashant Awasthi
article en

Abstract

Heart disease is one of the major health problems affecting people across the world. Identifying the possibility of heart disease at an early stage can help in taking timely medical advice and reducing potential risks. However, analysing different health-related factors manually can sometimes be difficult and may lead to errors. To address this problem, this project introduces a Medical Risk Classifier, a machine learning-based system designed to predict the risk of heart disease using basic clinical information. The system uses the UCI Heart Disease (Cleveland) dataset, which contains patient details such as age, blood pressure, cholesterol level, chest pain type, maximum heart rate and other medical attributes. The collected data is cleaned and prepared before applying a regularized Logistic Regression algorithm to classify the possibility of heart disease. L2 regularization is used to reduce overfitting and improve the stability of the model. The system is evaluated using stratified 5-fold cross-validation, along with performance measures such as precision, recall, F1-score, ROC-AUC and confusion matrix. A key focus of this project is to improve the model's ability to identify patients who may have heart disease rather than depending only on overall accuracy. For this reason, the decision threshold is adjusted to give greater importance to recall and reduce the chances of missing positive cases. The project also examines the contribution of different clinical features to the model's predictions. Overall, the Medical Risk Classifier demonstrates how machine learning can be used to analyse medical data and support preliminary heart disease risk assessment through a simple and interpretable approach. It is developed for academic and experimental purposes and is not intended to replace professional medical diagnosis.

Zenodo (CERN European Organization for Nuclear Research)
Greater Noida Institute of Technology (MBA Institute) (IN)
Artificial Intelligence in Healthcare
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon