International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 12 | Nov 2025
p-ISSN: 2395-0072
www.irjet.net
Heart Disease Identification Method Using Machine Learning Classification in E-Healthcare Prof. Savita S G1, Shweta2 1
Professor, Master of Computer Application, VTU, Kalaburagi, Karnataka, India
2Student, Master of Computer Application, VTU, Kalaburagi, Karnataka, India
--------------------------------------------------------------------***----------------------------------------------------------------------------pipelines. It is ideal for testing feature-selection methods, ABSTRACT- Heart disease remains one of the leading baseline classifiers (logistic regression, tree ensembles), and evaluation workflows, but its limited size and demographic skew require cautious claims about generalizability. Treat it as a reproducible baseline: run experiments here first, then validate on larger, more diverse clinical cohorts. [2]
causes of mortality worldwide, demanding early detection and timely intervention to improve patient outcomes. With the rapid growth of electronic healthcare (E-Healthcare) systems, Machine Learning (ML) techniques provide powerful tools to analyze clinical data and identify hidden patterns associated with heart disease. In this work, a classification-based approach is proposed for heart disease prediction using patient health attributes such as age, blood pressure, cholesterol level, resting ECG, and exerciseinduced factors. The methodology integrates preprocessing, feature selection, and supervised ML algorithms like Logistic Regression, Random Forest, and Gradient Boosting to predict disease presence with improved accuracy. The system further incorporates model evaluation metrics such as ROCAUC, sensitivity, specificity, and F1-score to ensure reliability in a clinical setting. Designed for E-Healthcare applications, the framework supports automated risk assessment, aiding physicians in decision-making and enhancing preventive care strategies. This study highlights how ML-based classification can improve the efficiency of healthcare systems while ensuring accessibility, scalability, and realtime support for patients at risk of heart disease.
This comprehensive review of deep-learning methods for cardiac diagnosis summarizes CNN/RNN/transformer approaches applied to ECG, imaging, and multimodal EHR data. It documents preprocessing best practices (demolishing, segmentation), architecture choices, and where deep mode ls outperform classical methods— especially on large waveform or imaging datasets. The paper also emphasizes interpretability and deployment considerations relevant for clinical adoption. Use its recommendations when designing deep-model experiments. [3] This recent survey focuses on ML trends in cardiovascular care and e-Health, noting the shift from tabular models to multimodal, attention-based architectures and transformer models for long sequences. It outlines regulatory, datagovernance, and clinician-trust challenges, and recommends reporting calibration, decision thresholds, and prospective validation. For Healthcare projects, the survey provides contemporary guidance on deployment readiness and realworld evaluation. [4]
Keyword: In this work, a classification-based approach is proposed for heart disease prediction using patient health attributes such as age, blood pressure, cholesterol level, resting ECG, and exercise-induced factors.
These established clinical risk calculators (e.g., pooledcohort/Framingham style scores) remain the practical baseline for cardiovascular risk assessment and are widely used in clinical workflows. They combine demographic, clinical, and lab variables into an interpretable risk estimate and thus serve as useful comparator features or benchmarks for ML models. Any ML system should be evaluated against such clinical scores and, ideally, demonstrate added predictive value and proper calibration before clinical use. [5]
1. INTRODUCTION This review synthesizes machine-learning approaches applied to heart-disease diagnosis across many studies, comparing model families (tree ensembles, SVMs, CNNs for ECG, RNNs/transformers for time series). It highlights common pitfalls—small datasets, label noise, class imbalance—and stresses rigorous validation (temporal/patient splits) and clinically relevant metrics. The review is a practical roadmap for selecting algorithms, preprocessing steps, and evaluation protocols for eHealthcare pipelines. Use it to shape method choices and validation strategies before prototyping. [1]
2. PROBLEM STATEMENT Heart disease is one of the leading causes of death worldwide, and its timely detection is critical for reducing mortality rates. Traditional diagnostic methods often require specialized medical expertise, advanced equipment, and time-consuming tests, which may not always be accessible to
This widely used clinical benchmark provides a compact tabular dataset of patient attributes and diagnostic labels for heart disease, commonly used for prototyping classification
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 159