A Narrative Review of Artificial Intelligence for Drug Repurposing: Lessons From COVID-19 and Oncology (2020-2025)

Clinical Snapshot

Key Findings

• P Value: Not reported at the review level

• Effect Size: Not applicable — no pooled effect size reported; individual study metrics referenced descriptively without standardised extraction

• Primary Outcome: Narrative synthesis of AI methodologies (ML, DL, knowledge graphs, NLP) applied to drug repurposing in COVID-19 and oncology contexts; no primary quantitative outcome is defined or reported

• Nnt Or Sensitivity: Not applicable — no NNT, sensitivity/specificity, or hazard ratio data synthesised; individual AI model performance metrics (e.g., AUC values from cited studies) are referenced narratively but not pooled or critically compared

• Confidence Interval: Not reported — no meta-analytic synthesis performed

Clinical Application

The AI methodologies described (ML, DL, KGs, NLP) require substantial computational infrastructure, curated biomedical databases, and interdisciplinary expertise. Implementation in clinical or pharmaceutical settings is feasible at institutional level but not at the point of care. Regulatory validation pathways for AI-identified repurposed candidates remain underdeveloped globally In the Australian context, AI-driven drug repurposing intersects with TGA regulatory frameworks for new indications of registered medicines, PBS listing processes for repurposed agents, and NHMRC-funded translational research priorities. The MRFF (Medical Research Future Fund) has funded AI-in-health initiatives relevant to this space. For oncology specifically, the Therapeutic Goods Administration's provisional approval pathway and the PBS's managed entry schemes could theoretically accommodate AI-identified repurposed oncology agents, but no Australian-specific data or regulatory guidance is discussed in this review. RACGP guidelines do not currently address AI-assisted prescribing of repurposed medicines. The review's findings are relevant to Australian pharmaceutical researchers but offer no direct guidance for Australian prescribers or PBS formulary decisions. Broadly applicable as a conceptual overview for researchers and clinicians interested in computational drug repurposing methodology; not directly applicable to individual patient management decisions. Most relevant to pharmaceutical scientists, clinical trialists, and health technology assessment bodies evaluating AI-assisted drug development pipelines

Abstract

Drug repurposing presents a cost-effective and time-efficient strategy to identify new therapeutic applications for existing drugs. Recent advances in artificial intelligence, including machine learning, deep learning, knowledge graphs, and natural language processing, have revolutionized this field by enabling automated discovery of drug-disease associations. This review examines the role of artificial intelligence in drug repurposing, drawing insights from two critical case areas: Coronavirus disease 2019 and oncology. We explore current trends, methodological frameworks, and technological innovations in artificial intelligence-driven drug repurposing, as well as challenges and emerging future directions. The findings of this paper underscore the transformative potential of artificial intelligence in biomedical research and justify its continued integration in pharmaceutical pipelines.

References

1. 1.Ogungbite, A. B., & Sibiya, M. (2025). A narrative review of artificial intelligence for drug repurposing: Lessons from COVID-19 and oncology (2020–2025). CPT: Pharmacometrics & Systems Pharmacology. https://doi.org/10.26434/chemrxiv-2025-f1hgn