Journal of African Development

Machine learning (ML) has emerged as a transformative component of modern healthcare, enabling healthcare organizations to move from reactive treatment toward predictive, preventive, and personalized care. The rapid growth of electronic health records (EHRs), medical imaging, genomic information, wearable devices, mobile health applications, and other digital health technologies has created large and complex datasets that can be analyzed using ML algorithms. These technologies can support disease prediction, early diagnosis, risk stratification, clinical decision-making, treatment selection, patient monitoring, drug discovery, and healthcare resource optimization. In personalized medicine, ML facilitates the integration of clinical, genetic, behavioral, environmental, and lifestyle information to identify patient-specific disease risks and treatment responses. From a patient-centric healthcare perspective, predictive analytics can also improve communication, engagement, service delivery, adherence, and the overall patient experience. However, challenges related to data quality, privacy, algorithmic bias, explainability, interoperability, cybersecurity, clinical validation, and regulatory oversight continue to limit widespread adoption. This review discusses the principles, applications, opportunities, and challenges of ML in predictive healthcare and personalized medicine, with particular attention to patient-centered value creation. The review argues that successful implementation requires a human-centered approach in which ML augments rather than replaces healthcare professionals and is supported by robust governance, transparent algorithms, high-quality data, and continuous real-world validation.....