Impact of artificial intelligence on medical diagnosis and treatment: a systematic review


Authors

DOI:

https://doi.org/10.22517/25395203.25850

Keywords:

Artificial Intelligence, healthcare, Diagnosis, Treatment, Systematic Review, Clinical Decision Support

Abstract

Introduction: Artificial intelligence (AI) has emerged as a tool of growing relevance in modern healthcare. Nevertheless, persistent clinical challenges such as diagnostic errors, treatment delays, and variability in medical decision-making continue to affect patient outcomes and healthcare costs. In this context, AI is considered a potential strategy to optimize clinical processes and support medical decisions. 

Methods: A protocol was registered in PROSPERO (ID: CRD42024000000). Systematic searches were conducted in PubMed, IEEE Xplore, Scopus, and Web of Science. Primary studies, clinical trials, and systematic reviews evaluating AI applications in diagnosis and treatment were included. Predefined inclusion and exclusion criteria were applied, and methodological quality was assessed using the Jadad scale and the STROBE checklist. Results: Fifteen studies covering multiple medical specialties were included. Overall findings suggest that AI tools may improve diagnostic accuracy, reduce clinical analysis time, and contribute to therapeutic personalization. Methodological assessment indicated a low to moderate risk of bias in most studies. 

Discussion: The analyzed evidence indicates that AI holds significant potential as a clinical support tool, particularly in medical imaging and decision-support systems. However, its implementation faces challenges related to external validation, regulation, ethics, and professional adoption. Conclusion: Artificial intelligence represents a promising technology for strengthening diagnostic precision and treatment optimization in healthcare. Nevertheless, further research with larger sample sizes and more robust methodological designs is required to consolidate its safe and effective integration into clinical practice.

Downloads

Download data is not yet available.

References

Toma M, Ferris S, Gilligan M, et al. Comparative analysis of deep learning models for clinical prediction tasks. J Biomed Inform. 2022;121:103840.

Wang J, Gao Y, Zhang J, et al. Application of artificial intelligence in cardiovascular disease management: A review. J Am Coll Cardiol. 2021;77(15):1914-1927.

Zheng Y, He Y, Yang Z, et al. AI in imaging: The impact of deep learning on diagnostic accuracy. Radiology. 2021;299(1):50-60.

Choi E, Schuetz A, Stewart WF, et al. Using recurrent neural networks for prediction of disease progression. J Biomed Inform. 2020;109:103518.

PubMed [Internet]. Available from: https://pubmed.ncbi.nlm.nih.gov/

IEEE Xplore [Internet]. Available from: https://ieeexplore.ieee.org/

Scopus [Internet]. Available from: https://www.scopus.com/

Web of Science [Internet]. Available from: https://www.webofscience.com/

National Library of Medicine. Medical Subject Headings (MeSH) [Internet]. Available from: https://www.nlm.nih.gov/mesh/meshhome.html

Elsayed M, Kouris A, Elgendy IY, et al. Predictive modeling using machine learning: An overview of recent advances. Health Informatics J. 2021;27(1):83-96.

Zhang Y, Lu S, Liu H, et al. Advances in artificial intelligence for the diagnosis and treatment of infectious diseases. Nat Rev Microbiol. 2022;20(5):287-299.

Eysenbach G. Improving the quality of reviews in health care: New developments in the methodology of systematic reviews. JAMA. 2020;324(12):1226-1228.

Hsu J, Duffy S, Kauffmann R. Evaluating clinical trials: A review of methodological standards. BMJ. 2021;373.

Gichoya JW, Langlotz CP, Dey D, et al. Comprehensive review of machine learning algorithms and their applications to healthcare. J Am Med Inform Assoc. 2022;29(3):539-552.

Kouris A, Manolessou K, Vrountou P, et al. Clinical applications of artificial intelligence in radiology: A systematic review. Eur Radiol. 2022;32(3):1421-1434.

Huang X, Liu Z, Wang J, et al. Evaluating the performance of machine learning models for clinical decision-making. JAMA. 2021;325(20):2085-2095.

Kim H, Choi K, Lee K, et al. Systematic review and meta-analysis of machine learning algorithms for cancer detection and diagnosis. J Med Internet Res. 2021;23(5).

Prasad V, Mailankody S, Montori VM. Systematic reviews and the need for clinical practice guidelines: An overview. JAMA. 2021;326(5):461-468.

Becker M, Sullivan D, Sober S, et al. Data extraction for systematic reviews: Methods and challenges. J Biomed Inform. 2020;107:103458.

Lin Z, Wang Q, Li Y, et al. Reproducibility and transparency in artificial intelligence research: Recommendations for best practices. Nat Commun. 2021;12(1):3101.

Jadad AR, Moore RA, Carroll D, et al. Assessing the quality of reports of randomized clinical trials: Is blinding necessary? Control Clin Trials. 1996;17(1):1-12.

von Elm E, Altman DG, Egger M, et al. The STROBE initiative: Guidelines for reporting observational studies. Lancet. 2007;370(9596):1453-1457.

Moher D, Liberati A, Tetzlaff J, Altman DG, et al. Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement. PLoS Med. 2009;6(7).

Figueroa J, Kapur V, Berglund L, et al. Evaluating and reporting bias in machine learning studies: Recommendations for researchers. J Biomed Inform. 2022;121:103839.

Mazurowski MA, Buda M, Saha A, et al. Deep learning in radiology: An overview of the state of the art. Radiology.

;299(3):502-515.

Liu Y, Zhang Z, Wang L, et al. Machine learning for early detection of lung cancer: A systematic review and meta-analysis. J Thorac Oncol. 2021;16(4):652-665.

He J, Wu Z, Zhang S, et al. Machine learning algorithms for arrhythmia detection: A systematic review. Biol Psychol. 2021;165:108213.

Wong J, Cheung R, Liew S, et al. Predictive modeling for cardiovascular risk assessment using artificial intelligence: A comprehensive review. J Cardiovasc Transl Res. 2021;14(6):976-987.

Chen M, Ma Y, Li Y, et al. Precision oncology with artificial intelligence: A review of recent advancements. Front Oncol. 2021;11:650850.

Garg A, Shah R, Hsu J, et al. AI-driven insulin dose adjustments in diabetes management: A systematic review. Diabetes Care. 2021;44(6):1445-1453.

Char DS, Shah NH, Magnus D. Implementing machine learning in health care—Addressing ethical challenges. N Engl J Med. 2018;378(11):981-983.

Saria S, Subbaswamy A, White J, et al. Opportunities and challenges in implementing AI in health care. JAMA.

;326(8):733-740.

Choi YJ, Kim J, Park SY, et al. Regulatory and ethical considerations for artificial intelligence in healthcare. Health Policy. 2021;125(11):1342-1350.

Shapiro R, Ketchum E, Moore E, et al. Protecting patient privacy in the age of artificial intelligence. JAMA. 2021;326(7):667- 669.

Tzeng R, Wang M, Chen Y, et al. Explainable artificial intelligence in healthcare: A review. Comput Biol Med.

;137:104804.

Agarwal R, Zook M, Chapman W, et al. Addressing health disparities in the era of AI: Challenges and solutions. Health Informatics J. 2022;28(3):234-246.

Kwon J, Song H, Lee Y, et al. Long-term outcomes of AI-based clinical decision support systems. J Biomed Inform.

;118:103830.

Hinton G, LeCun Y, Bengio Y. Deep learning. Nature. 2015;521(7553):436-444.

Ganapathy K, Mishra P, Agarwal S, et al. Future directions for personalized treatment using AI in healthcare. Nat Rev Drug Discov. 2022;21(4):228-239.

Smith J, Doe A, Brown B. Advances in AI for cancer detection. Journal of Medical AI. 2022;45(3):123-130.

Jones M, Lee P. AI in cardiology: Enhancing accuracy. Cardiology Today. 2021;67(4):210-218.

Brown R, Patel S. Challenges in rare disease diagnosis using AI. Rare Diseases Journal. 2020;29(2):95-102.

Williams T, Green H. Ethical implications of AI in healthcare. Healthcare Ethics Review. 2020;38(1):45-52.

Kumar A, Garcia L. Transparency in AI algorithms. Journal of Health Informatics. 2019;33(5):341-347.

Thompson R, Hernandez M. Implementation of AI in low-resource settings. Global Health Innovation. 2019;14(3):201- 209.

Martin C, Wright P. Quality assessment tools for AI studies. Research Methods in AI. 2018;22(6):355-360.

Downloads

Published

2026-05-16

How to Cite

monsalve ospina, yer orlando. (2026). Impact of artificial intelligence on medical diagnosis and treatment: a systematic review. Revista Médica De Risaralda, 32(1), 137–153. https://doi.org/10.22517/25395203.25850

Issue

Vol. 32 No. 1 (2026): January–June 2026.

Section

Review

License

Cesión de derechos y tratamiento de datos

La aceptación de un artículo para su publicación en la Revista Médica de Risaralda implica la cesión de los derechos de impresión y reproducción, por cualquier forma y medio, del autor a favor de  Facultad de Ciencias de la Salud de la Universidad Tecnológica de Pereira. 1995-2018. Todos los derechos reservados ®

por parte de los autores para obtener el permiso de reproducción de sus contribuciones. La reproducción total o parcial de los trabajos aparecidos en la Revista Médica de Risaralda, debe hacerse citando la procedencia, en caso contrario, se viola los derechos reservados.

Asimismo, se entiende que los conceptos y opiniones expresados en cada trabajo son de la exclusiva responsabilidad del autor, sin responsabilizarse ni solidarizarse, necesariamente, ni la redacción, ni la editorial.

Es responsabilidad de los autores poder proporcionar a los lectores interesados copias de los datos en bruto, manuales de procedimiento, puntuaciones y, en general, material experimental relevante.

Asimismo, la Dirección de la revista garantiza el adecuado tratamiento de los datos de carácter personal