Journal of Artificial Intelligence and Robotics

ABSTRACT

Cardiovascular diseases (CVDs), particularly atherosclerotic cardiovascular disease (ASCVD), are the leading causes of mortality worldwide, with sub-Saharan Africa facing significant challenges in their early detection and management. Traditional risk assessment tools, such as the Framingham score and ASCVD Estimator Plus, are poorly suited to the unique genetic, environmental, and lifestyle factors present in the region's populations. These tools often fail to provide accurate risk predictions, underscoring the urgent need for more advanced and adaptable solutions. This article explores the transformative potential of AI, specifically machine learning (ML) and deep learning (DL), in improving ASCVD risk prediction and early detection in sub-Saharan Africa. AI models, such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, can process vast amounts of data, including medical imaging, genetic profiles, and lifestyle inputs, offering more precise and personalized risk assessments. A key innovation discussed in this paper is the Jos CVD Risk App, developed specifically for use in sub-Saharan Africa. This AI-driven tool leverages non-invasive anthropometric measurements to assess ASCVD risk, offering a more accessible and affordable alternative to traditional methods. By addressing the limitations of conventional tools, this app provides scalable, accurate, and cost-effective solutions for CVD risk assessment in underserved regions. The article highlights the need for continued innovation, data collection, and refinement of AI models to enhance their predictive accuracy and contribute to better cardiovascular outcomes in sub-Saharan Africa, ultimately improving public health across the region.

KEYWORDS

1. Atherosclerotic cardiovascular disease
2. Artificial intelligence
3. Machine learning
4. Deep learning