The Relevance of Machine Learning for Early Detection of Heart Disease: Development of a Digital Risk Prediction Tool
1
Public Health Department, Ahmadu Bello University, Zaria, Nigeria
2
Bacteriology Department, Nigeria Center for Disease Control, Abuja, Nigeria
3
Mega PCR Laboratory, APIN Public Health Initiatives, Abuja, Nigeria
Popul. Med. 2026;8(Supplement Supplement 1):
ABSTRACT
INTRODUCTION:
Machine learning (ML) is increasingly being recognized as a transformative force in healthcare, offering new opportunities for disease prevention, diagnosis, and health system efficiency 1. In Africa, where cardiovascular diseases continue to rise due to socioeconomic disparities, limited access to diagnostic infrastructure, and unfavorable social determinants of health 2,3 ML-driven tools hold promise for bridging gaps in early detection and clinical decision support. Machine learning, a subset of AI, enables the use of large datasets to identify patterns, stratify risk, and generate actionable insights for both clinicians and policymakers.
METHODS:
This study demonstrates the detection of heart diseases through the development of a machine learning-based application using routine demographic and clinical indicators. Implemented in 2025 as part of an academic initiative in Abuja, Nigeria, the project employed a publicly available heart disease dataset of over 4000 participants to train a logistic regression model, achieving an R² score of 0.85 indicating high predictive capacity. The model was deployed through a web interface and designed for integration into a mobile application platform to enhance accessibility.
RESULTS:
The experience revealed the opportunities and challenges of ML integration in healthcare. Opportunities include the potential for low-cost, user-friendly tools that can support early screening, empower health workers, and enhance community-level disease surveillance. Challenges, however, persist, particularly in relation to limited local datasets, dependency management during cloud deployment, and the infrastructural constraints of digital health systems in Sub-Saharan Africa.
CONCLUSIONS:
This project illustrates how ML can be contextualized to strengthen early detection in healthcare delivery. While not a replacement for diagnostic expertise, the heart disease risk predictor exemplifies how ML-powered tools can complement public health initiatives, foster early detection, and inform policy on the integration of digital health technologies in Africa’s primary healthcare systems.
Machine learning (ML) is increasingly being recognized as a transformative force in healthcare, offering new opportunities for disease prevention, diagnosis, and health system efficiency 1. In Africa, where cardiovascular diseases continue to rise due to socioeconomic disparities, limited access to diagnostic infrastructure, and unfavorable social determinants of health 2,3 ML-driven tools hold promise for bridging gaps in early detection and clinical decision support. Machine learning, a subset of AI, enables the use of large datasets to identify patterns, stratify risk, and generate actionable insights for both clinicians and policymakers.
METHODS:
This study demonstrates the detection of heart diseases through the development of a machine learning-based application using routine demographic and clinical indicators. Implemented in 2025 as part of an academic initiative in Abuja, Nigeria, the project employed a publicly available heart disease dataset of over 4000 participants to train a logistic regression model, achieving an R² score of 0.85 indicating high predictive capacity. The model was deployed through a web interface and designed for integration into a mobile application platform to enhance accessibility.
RESULTS:
The experience revealed the opportunities and challenges of ML integration in healthcare. Opportunities include the potential for low-cost, user-friendly tools that can support early screening, empower health workers, and enhance community-level disease surveillance. Challenges, however, persist, particularly in relation to limited local datasets, dependency management during cloud deployment, and the infrastructural constraints of digital health systems in Sub-Saharan Africa.
CONCLUSIONS:
This project illustrates how ML can be contextualized to strengthen early detection in healthcare delivery. While not a replacement for diagnostic expertise, the heart disease risk predictor exemplifies how ML-powered tools can complement public health initiatives, foster early detection, and inform policy on the integration of digital health technologies in Africa’s primary healthcare systems.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
