Biomarkers are the molecular signatures that drive and reflect disease states and are indispensable for disease diagnosis, therapeutic target identification, and drug development. The landscape of biomarker discovery has undergone a transformative shift with the emergence of AI-powered predictive pipelines that can integrate complex, high-dimensional datasets. However, the field still lacks a comprehensive, cross-disciplinary foundation that unites AI pipelines with disease-specific biological insights. Together, a combined scattered knowledge of 15 review articles fails to provide a unified framework encompassing data availability, methodological trends, and disease-specific biomarker discoveries across therapeutic areas. Most prior efforts have concentrated on narrow aspects, i.e., either focusing on disease-specific AI models or individual stages of the biomarker discovery pipelines, leaving a substantial gap in translational utility. This study addresses this gap by systematically consolidating and analyzing findings from 236 AI-driven biomarker discovery studies. We systematically map the trends of datasets, data modalities, preprocessing strategies, feature engineering methods, AI models, and explainability methods across 147 diseases, which we further organize into 19 therapeutic areas. By doing so, we aim to provide a comprehensive resource that not only highlights current trends and gaps but also lays the groundwork for future advancements, including the design of multi-task learning models and multimodal AI frameworks tailored to complex biomedical data.
Abbasi et al. (Tue,) studied this question.