1 Lakeshore Cancer Center, Lagos Nigeria.
2 Internal Medicine (Consulting group), Obafemi Awolowo University Health Center, Ile-Ife, Nigeria.
3 Tennessee Technological University, Cookeville, USA.
4 Department of Physics, University of Ibadan, Ibadan, Nigeria.
5 Babcock University, Ilishan-Remo, Nigeria.
6 Bingham University Teaching Hospital, Plateau, Nigeria.
7 London Northwest University Healthcare NHS Trust, Northwick Park Hospital, Harrow, UK.
8 Evercare Hospital, Lagos Nigeria.
9 Edo Specialist Hospital, Benin, Nigeria.
World Journal of Advanced Research and Reviews, 2025, 28(01), 449-468
Article DOI: 10.30574/wjarr.2025.28.1.3444
Received on 30 August 2025; revised on 03 October 2025; accepted on 06 October 2025
Background. Artificial intelligence (AI) has emerged as a transformative tool for cancer diagnosis, with applications ranging from radiology and histopathology to genomics and clinical decision support. Yet the evidence base remains fragmented, and the translation of AI innovations into clinical workflows, particularly in Africa, lags behind technical progress.
Objective. This review aimed to map the global evidence on AI for cancer diagnosis, assess methodological maturity using the Technology Readiness Level (TRL) framework, and explore deployment challenges and opportunities with an equity lens, focusing on Africa as a potential innovation testbed.
Methods. A scoping review was conducted in accordance with the PRISMA-ScR framework. PubMed, Scopus, IEEE Xplore, and Web of Science were searched for studies published between 2015 and 2025. Eligible studies included peer-reviewed research, pilot deployments, and reviews explicitly applying AI to cancer diagnosis. Data were charted for cancer type, AI technique, evaluation method, TRL, and deployment context, and synthesized narratively.
Results. Twenty studies met the inclusion criteria. CNNs dominated imaging and pathology applications, while transformers and federated learning emerged as promising innovations. Data-efficient learning, Bayesian inference, and reinforcement learning remain largely experimental (TRL 2–4). Most studies relied on retrospective validation; only two reported prospective trials. African contributions were limited to three single-center pilots, none advancing beyond TRL 3.
Conclusions. AI for cancer diagnosis is at a crossroads: techniques are maturing technically but remain under-validated clinically. Deployment challenges, trust, workflow fit, and governance, are global, though amplified in Africa. Leveraging Africa as a living laboratory for frugal, equitable innovation could accelerate global progress. Developers, policymakers, and African consortia must collaborate to ensure AI advances both rigorously and inclusively.
Artificial Intelligence; Cancer Diagnosis; Machine Learning; Deep Learning; Technology Readiness Levels (TRLs); Federated Learning; Global Health Equity
Preview Article PDF
Joy Aifuobhokhan, Tobiloba Philip Olatokun, Chijioke Cyriacus Ekechi, Jumoke Oladeji, Olajiire Onikoyi Olajide, Ayodeji Ogunjinmi, Adebusola. Popoola, Oreoluwa D. Fuwape and Obotha-Adigo Okeoghene Genevieve. Artificial Intelligence in Cancer Diagnosis: A Scoping Review of Global Innovation and African Implementation. World Journal of Advanced Research and Reviews, 2025, 28(01), 449-468. Article DOI: https://doi.org/10.30574/wjarr.2025.28.1.3444.
Copyright © 2025 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0