From stethoscopes to supercomputers: The AI revolution in medicine: A review

Deckker, Dinesh and Sumanasekara, Subhashini (2025) From stethoscopes to supercomputers: The AI revolution in medicine: A review. World Journal of Advanced Research and Reviews, 26 (1). pp. 1114-1131. ISSN 2581-9615

[thumbnail of WJARR-2025-1138.pdf] Article PDF
WJARR-2025-1138.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download ( 577kB)

Abstract

Artificial Intelligence (AI) has rapidly emerged as a transformative force in modern medicine, revolutionising diagnostics, treatment personalisation, and clinical decision-making. This review synthesises current literature on AI's evolution, applications, challenges, and future directions in healthcare. From early rule-based systems to advanced deep learning algorithms, AI has consistently demonstrated capabilities that rival and enhance human expertise—particularly in imaging, predictive analytics, and drug discovery. The role of AI in global health is also expanding, offering scalable solutions to reduce disparities in low-resource settings. However, the integration of AI raises ethical and legal concerns, including data privacy, algorithmic bias, and unclear accountability frameworks. Drawing on the Technology Acceptance Model (TAM), Diffusion of Innovations Theory, and Principlism, this review highlights theoretical perspectives essential to understanding AI adoption and governance. The paper concludes with a call for longitudinal studies, ethical frameworks, and policy innovations to support AI's responsible and equitable deployment in the medical field.

Item Type: Article
Official URL: https://doi.org/10.30574/wjarr.2025.26.1.1138
Uncontrolled Keywords: Artificial Intelligence; Medical Diagnostics; Personalized Medicine; Clinical Decision Support; Medical Imaging; Predictive Analytics; Healthcare Ethics; Algorithmic Bias; Global Health; Explainable AI
Depositing User: Editor WJARR
Date Deposited: 22 Jul 2025 23:50
Related URLs:
URI: https://eprint.scholarsrepository.com/id/eprint/1755