TITLE:
Heart Disease Prediction: A Logistic Regression Approach
AUTHORS:
Awele Okolie, Callistus Obunadike, Stanley Chinedu Okoro, Itunu Blessing Olufemi, PearlRose Nwoke, Prince Michael Akwabeng
KEYWORDS:
Heart Disease Prediction, Logistic Regression, Machine Learning, Predictive Modeling, Healthcare Analytics, Clinical Data, Early Diagnosis
JOURNAL NAME:
Open Journal of Applied Sciences,
Vol.15 No.11,
November
17,
2025
ABSTRACT: Heart disease remains one of the leading causes of mortality worldwide, accounting for millions of deaths annually. Early detection of individuals at risk is essential for reducing complications and improving patient outcomes. This study applies logistic regression, a supervised machine learning algorithm, to predict the likelihood of heart disease based on clinical and demographic features such as age, sex, chest pain type, resting blood pressure, cholesterol level, fasting blood sugar, and maximum heart rate achieved. The dataset obtained from Kaggle’s Heart Disease Dataset, comprises 1025 patient records with 14 attributes. Following data preprocessing including handling missing values, feature scaling using StandardScaler, and categorical encoding, the data were divided into training (80%) and testing (20%) subsets. A logistic regression model with the liblinear solver and L2 regularization was trained and evaluated using multiple performance metrics. The model achieved 85.24% accuracy on the training set and 80.49% accuracy on the test set, with a ROC-AUC score of 0.86 and consistent results from 5-fold cross-validation. These findings demonstrate that logistic regression provides a robust, interpretable, and computationally efficient approach for binary classification in healthcare. The model’s high recall indicates its reliability in identifying patients at risk of heart disease, supporting its potential application in clinical decision-support systems for early diagnosis and intervention.