Enhancing Healthcare in Africa: A Brief Review of Lung Cancer Prediction and Detection

Abstract

Lung cancer is a leading cause of cancer-related mortality worldwide and imposes a significant burden on low-resource regions, such as Africa. Early detection combined with an accurate diagnosis can significantly improve patient outcomes. Recent advances in artificial intelligence (AI) have shown substantial promise when integrated into lung cancer screening, diagnosis, and risk prediction. This review examines the current state of AI applications in lung cancer detection, with a focus on deep learning models, radiomics, and multimodal AI approaches. Recent studies have analyzed model architectures, performance evaluation metrics, and barriers to clinical adoption. Machine learning systems have demonstrated high accuracy in lung nodule classification and risk prediction. However, issues such as dataset bias, limited generalizability, and challenges in clinical integration remain critical, especially in African contexts. This study underscores the urgent need for AI models trained in diverse populations to ensure diagnostic reliability in underrepresented regions. Furthermore, the continued development of explainable AI (XAI) techniques is essential to foster trust and transparency among clinicians. Future research should prioritize the creation of region-specific and cost-effective AI tools and the establishment of standardized validation protocols tailored to real-world African healthcare settings.