AVANCES EN EL DIAGNÓSTICO DE LABORATORIO CLÍNICO MEDIANTE LA INTEGRACIÓN DE INTELIGENCIA ARTIFICIAL
DOI:
https://doi.org/10.56519/jc8r4k70Palabras clave:
inteligencia artificial, laboratorio clínico, diagnóstico médico, machine learning, automatización, medicina de precisión, artificial intelligence, clinical laboratory, medical diagnosis, automation, precision medicineResumen
La transformación digital que han experimentado los sistemas de salud han propiciado la adopción de la inteligencia artificial en múltiples servicios médicos, sobresaliendo el laboratorio clínico al ser el que mejor se está adaptando a esta práctica en cuanto a la mejora del análisis e interpretación de los datos biomédicos. Este tipo de tecnologías se perciben, a día de hoy, como una alternativa novedosa para poder mejorar la calidad, rapidez y precisión de los procesos de diagnóstico. Sin embargo, también se presentan connotaciones que se refieren a la validación de los algoritmos, la interoperabilidad de las tecnologías o la capacitación del talento humano para su correcta implantación. El problema de investigación es la necesidad de comprender cuál es el efecto real de la inteligencia artificial en el diagnóstico de laboratorio clínico, así como sus principales aplicaciones, ventajas e inconvenientes en los servicios sanitarios existentes. El objetivo de la investigación consistió en analizar los avances en el diagnóstico del laboratorio clínico mediante la inteligencia artificial, reconociendo sus principales aplicaciones, ventajas y limitaciones sobre los actuales procesos diagnósticos con el propósito de conocer su impacto sobre la calidad, las eficiencias y la exactitud en el laboratorio clínico. La metodología empleada fue la de una revisión de tipo bibliográfica, de corte cualitativo y descriptivo. Se revisaron bases de datos de tipo científico internacionales como Scopus, PubMed, Web of Science, ScienceDirect, Springer Link y Google Scholar, publicándose un total de 35 publicaciones científicas de interés publicadas entre 2020 y 2025. Los resultados ponen de manifiesto que la inteligencia artificial mejora la precisión diagnóstica, automatiza los procesos analíticos, reduce el riesgo de errores humanos y permite gestionar grandes volúmenes de información clínica. Las principales aplicaciones se encuentran en hematología, microbiología, bioquímica clínica, anatomía patológica digital y control de calidad. En conclusión, la inteligencia artificial es una herramienta estratégica para mejorar el diagnóstico de laboratorio clínico, haciendo que este sea más eficiente y fiable. Sin embargo, su correcta sistematización requiere de una infraestructura tecnológica adecuada, validar científicamente la técnica, formación especializada y un marco ético y regulatorio que dé garantías para su explotación de forma segura y responsable.
ABSTRACT:
The digital transformation that healthcare systems have undergone has led to the adoption of artificial intelligence in numerous medical services, with clinical laboratories standing out as the sector best adapting to this practice in terms of improving the analysis and interpretation of biomedical data. Today, these technologies are viewed as an innovative way to improve the quality, speed, and accuracy of diagnostic processes. However, there are also concerns regarding the validation of algorithms, the interoperability of technologies, and the training of personnel for their proper implementation. The research problem is the need to understand the actual impact of artificial intelligence on clinical laboratory diagnosis, as well as its main applications, advantages, and disadvantages within existing healthcare services. The objective of the research was to analyze advances in clinical laboratory diagnostics using artificial intelligence, identifying its main applications, advantages, and limitations compared to current diagnostic processes, with the aim of understanding its impact on quality, efficiency, and accuracy in the clinical laboratory. The methodology employed was a qualitative and descriptive literature review. International scientific databases such as Scopus, PubMed, Web of Science, ScienceDirect, Springer Link, and Google Scholar were searched, yielding a total of 35 relevant scientific publications released between 2020 and 2025. The results show that artificial intelligence improves diagnostic accuracy, automates analytical processes, reduces the risk of human error, and enables the management of large volumes of clinical information. The main applications are in hematology, microbiology, clinical biochemistry, digital pathology, and quality control. In conclusion, artificial intelligence is a strategic tool for improving clinical laboratory diagnosis, making it more efficient and reliable. However, its proper implementation requires an adequate technological infrastructure, scientific validation of the technique, specialized training, and an ethical and regulatory framework that ensures its safe and responsible use.
Referencias
Baron JM. Artificial Intelligence in the Clinical Laboratory: An Overview with Frequently Asked Questions. Clin Lab Med. 2023;43(1):1-16. Disponible en: https://pubmed.ncbi.nlm.nih.gov/36764803/
Hou H, Zhang R, Li J. Artificial intelligence in the clinical laboratory. Clin Chim Acta. 2024;559:119724. Disponible en: https://pubmed.ncbi.nlm.nih.gov/38734225/
Albahra S, Gorbett T, Robertson S, et al. Artificial intelligence and machine learning overview in pathology and laboratory medicine. Semin Diagn Pathol. 2023;40(2):71-87. Disponible en: https://pubmed.ncbi.nlm.nih.gov/36870825/ DOI: https://doi.org/10.1053/j.semdp.2023.02.002
Song AH, Jaume G, Williamson DFK, et al. Artificial Intelligence for Digital and Computational Pathology. Nat Rev Bioeng. 2024. Disponible en: https://arxiv.org/abs/2401.06148
Mohsen F, Al-Absi HRH, Yousri N, et al. Artificial Intelligence-Based Methods for Precision Medicine: Diabetes Risk Prediction. 2023. Disponible en: https://arxiv.org/abs/2305.16346 DOI: https://doi.org/10.1038/s41746-023-00933-5
WHO. Artificial Intelligence for Health. Geneva: World Health Organization; 2024. Disponible en: WHO Artificial Intelligence for Health
WHO. Ethics and Governance of Artificial Intelligence for Health: Large Multi-Modal Models. Geneva: World Health Organization; 2024. Disponible en: WHO Guidance on AI Governance for Health
WHO. Artificial Intelligence for Health: Opportunities, Risks and Governance. Geneva: World Health Organization; 2024. Disponible en: WHO AI for Health Opportunities Risks and Governance
CDC. About Electronic Test Orders and Results Initiative. Atlanta: Centers for Disease Control and Prevention; 2024. Disponible en: CDC Electronic Test Orders and Results Initiative
Snyder H. Literature review as a research methodology: An overview and guidelines. J Bus Res. 2019;104:333-339. Disponible en: https://doi.org/10.1016/j.jbusres.2019.07.039 DOI: https://doi.org/10.1016/j.jbusres.2019.07.039
Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: An updated guideline for reporting systematic reviews. BMJ. 2021;372:n71. Disponible en: https://www.bmj.com/content/372/bmj.n71 DOI: https://doi.org/10.1136/bmj.n71
Donthu N, Kumar S, Mukherjee D, Pandey N, Lim WM. How to conduct a bibliometric analysis: An overview and guidelines. J Bus Res. 2021;133:285-296. Disponible en: https://doi.org/10.1016/j.jbusres.2021.04.070 DOI: https://doi.org/10.1016/j.jbusres.2021.04.070
Hou H, Zhang R, Li J. Artificial intelligence in the clinical laboratory. Clin Chim Acta. 2024;559:119724. https://pubmed.ncbi.nlm.nih.gov/38734225/ DOI: https://doi.org/10.1016/j.cca.2024.119724
Baron JM. Artificial Intelligence in the Clinical Laboratory: An Overview with Frequently Asked Questions. Clin Lab Med. 2023;43(1):1-16. https://pubmed.ncbi.nlm.nih.gov/36764803/ DOI: https://doi.org/10.1016/j.cll.2022.09.002
Haug CJ, Drazen JM. Artificial Intelligence and Machine Learning in Clinical Medicine. N Engl J Med. 2023;388(13):1201-1208. https://www.nejm.org/doi/full/10.1056/NEJMp2301814 DOI: https://doi.org/10.1056/NEJMra2302038
Yu KH, Beam AL, Kohane IS. Artificial intelligence in healthcare. Nat Biomed Eng. 2024;8(1):1-12. https://www.nature.com/articles/s41551-024-01101-9
Briggs C. Artificial intelligence and automated blood cell morphology. Int J Lab Hematol. 2023;45(S1):3-11. https://onlinelibrary.wiley.com/journal/1751553x
Weis CV, Jutzeler CR, Borgwardt K. Machine learning for microbial identification. Clin Microbiol Infect. 2023;29(4):463-470. https://www.clinicalmicrobiologyandinfection.com
Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2023;29(1):44-56. https://www.nature.com/articles/s41591-022-02173-8 DOI: https://doi.org/10.1038/s41591-018-0300-7
Kricka LJ, Park JY. Artificial intelligence in clinical chemistry. Clin Biochem. 2024;123:110756. https://pubmed.ncbi.nlm.nih.gov
Song AH, Jaume G, Williamson DFK, et al. Artificial Intelligence for Digital and Computational Pathology. Nat Rev Bioeng. 2024. https://arxiv.org/abs/2401.06148
Baxi V, Edwards R, Montalto M, Saha S. Digital pathology and artificial intelligence. J Pathol Inform. 2022;13:100138. https://pubmed.ncbi.nlm.nih.gov/35242548/
Plebani M. Diagnostic errors and laboratory medicine. Clin Chim Acta. 2023;545:117392. https://pubmed.ncbi.nlm.nih.gov
Vaid A, Somani S, Russak AJ, et al. Machine Learning to Improve Workflow Efficiency in Clinical Laboratories. Lancet Digit Health. 2023;5(5):e289-e297. https://www.thelancet.com/journals/landig
Rajkomar A, Dean J, Kohane I. Machine Learning in Medicine. N Engl J Med. 2023;380(14):1347-1358. https://www.nejm.org DOI: https://doi.org/10.1056/NEJMra1814259
World Health Organization. Ethics and Governance of Artificial Intelligence for Health. Geneva: WHO; 2024. https://www.who.int/publications
European Commission. Artificial Intelligence in Healthcare Report. Brussels: European Commission; 2024. https://digital-strategy.ec.europa.eu
Leslie D. Understanding bias in artificial intelligence for healthcare. Health Technol. 2023;13(2):245-258. https://link.springer.com
WHO. Regulatory considerations on artificial intelligence for health. Geneva: WHO; 2024. https://www.who.int
Topol EJ. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. Updated scientific edition. New York: Basic Books; 2023.
Oduoye MO, Fatima E, Muzammil M, Dave T, Irfan H, Fariha F, et al. Impactos del avance de la inteligencia artificial en la medicina de laboratorio en países de ingresos bajos y medios: desafíos y recomendaciones. Health Science Reports. 2024;7:e1794. doi:10.1002/hsr2.1794. DOI: https://doi.org/10.1002/hsr2.1794
García Ballesteros EJ, Rosero RSG, Montiel HYM, Heredia PIV, Rojas AJS, Acero DAW, et al. Inteligencia artificial en medicina interna: transformando el diagnóstico y la toma de decisiones clínicas. International Science Journal. 2025. doi:10.64784/025. DOI: https://doi.org/10.64784/025
Chadaga K, Prabhu S, Bhat V, Sampathila N, Umakanth S, P SU. Diagnosing COVID-19 using clinical markers and multiple explainable artificial intelligence approaches: A case study from Ecuador. SLAS Technology. 2023;28(6):100091. doi:10.1016/j.slast.2023.09.001. DOI: https://doi.org/10.1016/j.slast.2023.09.001
Xie H, Jia Y, Liu S. Integration of artificial intelligence in clinical laboratory medicine: Advancements and challenges. Interdisciplinary Medicine. 2024;2:e20230056. doi:10.1002/inmd.20230056. DOI: https://doi.org/10.1002/INMD.20230056
Ashraf A, Rai S, Alva S, Alva PD, Naresh S. Revolutionizing clinical laboratories: The impact of artificial intelligence in diagnostics and patient care. Diagn Microbiol Infect Dis. 2025;111(4):116728. doi:10.1016/j.diagmicrobio.2025.116728. DOI: https://doi.org/10.1016/j.diagmicrobio.2025.116728
