Uso de la Inteligencia Artificial como Sistema de Apoyo a la Decisión Clínica en el Manejo del Dolor Lumbar Crónico. Una Revisión de Alcance con Componente Conceptual Aplicado
Este artículo es de acceso abierto y puedes leerlo íntegramente
Descargas
Resumen
Antecedentes y Objetivos: La alta prevalencia del dolor lumbar crónico y la creciente demanda asistencial requieren modelos de gestión en fisioterapia más eficientes. La Inteligencia Artificial (IA) se presenta como una herramienta de soporte, aunque su integración clínica plantea dudas éticas y técnicas. El objetivo principal fue revisar la literatura reciente sobre sistemas de apoyo a la decisión clínica (CDSS, por sus siglas en inglés) en fisioterapia lumbar y explicar sus implicaciones para el diseño de asistentes clínicos supervisados.
Métodos: Se realizó una revisión de alcance (scoping review) con componente conceptual aplicado mediante búsqueda estructurada en PubMed, Web of Science, Scopus, Cochrane y PEDro. Se seleccionaron estudios originales publicados en los últimos 5 años que aplicaron algoritmos de aprendizaje automático o herramientas digitales en el manejo del dolor lumbar.
Resultados: La evidencia indica que los algoritmos de aprendizaje automático poseen una alta capacidad predictiva para el triaje y el pronóstico funcional, mostrando un rendimiento equivalente o, en ocasiones, superior a las herramientas convencionales. En el ámbito terapéutico, las intervenciones digitales muestran resultados positivos en adherencia y monitorización remota, aunque su eficacia directa sobre el dolor es variable. La falta de transparencia de los algoritmos se identificó como la principal barrera de confianza.
Discusión: Los resultados sugieren que la utilidad actual de la IA reside en el filtrado de seguridad y la estratificación de pacientes, más que en la prescripción autónoma. Se discute la necesidad de implementar modelos con supervisión humana obligatoria para mitigar riesgos. Como implicación práctica derivada de la revisión, se plantea la viabilidad teórica de asistentes basados en reglas clínicas estrictas para la detección de banderas rojas y arquitecturas RAG (Retrieval-Augmented Generation) para personalizar la educación sin alucinaciones.
Conclusiones: La IA es una tecnología válida para apoyar el triaje y optimizar recursos, pero requiere validación externa y transparencia. La profesión debe liderar la integración de estos “copilotos” digitales para descargar tareas burocráticas y reforzar la alianza terapéutica, evitando la automatización no supervisada.
Palabras clave
- Inteligencia Artificial
- Sistemas de Apoyo a la Decisión Clínica
- Fisioterapia
- Dolor Lumbar Crónico
- Aprendizaje Automático
- Telerrehabilitación
Referencias
Seas A, Zachem TJ, Valan B, Goertz C, Nischal S, Chen SF, et al. Machine learning in the diagnosis, management, and care of patients with low back pain: a scoping review of the literature and future directions. Spine J. 2025; 25(1):18–31. doi: 10.1016/j.spinee.2024.09.010 DOI: https://doi.org/10.1016/j.spinee.2024.09.010
Hasan F, Mudey A, Joshi A. Role of Internet of Things (IoT), Artificial Intelligence and Machine Learning in Musculoskeletal Pain: A Scoping Review. Cureus. 2023; 15(4):e37352. doi: 10.7759/cureus.37352 DOI: https://doi.org/10.7759/cureus.37352
Toh ZA, Berg B, Han QYC, Hey HWD, Pikkarainen M, Grotle M, et al. Clinical Decision Support System Used in Spinal Disorders: Scoping Review. J Med Internet Res. 2024; 26:e53951. doi: 10.2196/53951 DOI: https://doi.org/10.2196/53951
Alonso-García M, Sarría-Santamera A. The Economic and Social Burden of Low Back Pain in Spain: A National Assessment of the Economic and Social Impact of Low Back Pain in Spain. Spine (Phila Pa 1976). 2020; 45(16):E1026-E1032. doi: 10.1097/BRS.0000000000003476 DOI: https://doi.org/10.1097/BRS.0000000000003476
Dal Prete A, Gandolla M, Andreoni G, Braghin F. Low Back Exoskeletons in Industry 5.0: From Machines to Perceiving Co-Pilots—A State-of-the-Art Review. Sensors. 2025; 25(7):1958. doi: 10.3390/s25071958 DOI: https://doi.org/10.3390/s25071958
Falla D, Devecchi V, Jiménez-Grande D, Rügamer D, Liew BXW. Machine learning approaches applied in spinal pain research. J Electromyogr Kinesiol. 2021;61:102599. doi: 10.1016/j.jelekin.2021.102599 DOI: https://doi.org/10.1016/j.jelekin.2021.102599
Rajan PV, Eisenberg J, Selverian S, Wawrose R, Yoon ST. The cost-effectiveness of physical therapy versus laminectomy for lumbar spinal stenosis: a Markov decision analysis. Spine J. 2025; 25(8):1608–17. doi: 10.1016/j.spinee.2025.02.008 DOI: https://doi.org/10.1016/j.spinee.2025.02.008
Tropea P, Schlieter H, Sterpi I, Judica E, Gand K, Caprino M, et al. Rehabilitation, the Great Absentee of Virtual Coaching in Medical Care: Scoping Review. J Med Internet Res. 2019; 21(10):e12805. doi: 10.2196/12805 DOI: https://doi.org/10.2196/12805
Chen K, Zhai X, Sun K, Wang H, Yang C, Li M. A narrative review of machine learning as promising revolution in clinical practice of scoliosis. Ann Transl Med. 2021; 9(1):67. doi: 10.21037/atm-20-5495 DOI: https://doi.org/10.21037/atm-20-5495
Ren G, Yu K, Xie Z, Wang P, Zhang W, Huang Y, et al. Current Applications of Machine Learning in Spine: From Clinical View. Global Spine J. 2022; 12(8):1827–40. doi: 10.1177/21925682211035363 DOI: https://doi.org/10.1177/21925682211035363
Jawed AM, Zhang L, Zhang Z, Liu Q, Ahmed W, Wang H. Artificial intelligence and machine learning in spine care: Advancing precision diagnosis, treatment, and rehabilitation. World J Orthop. 2025; 16(8):107064. doi: 10.5312/wjo.v16.i8.107064 DOI: https://doi.org/10.5312/wjo.v16.i8.107064
Kim HB, Kim HS, Kim SJ, Yoo JI. Spine muscle auto segmentation techniques in MRI imaging: a systematic review. BMC Musculoskelet Disord. 2024; 25(1):716. doi: 10.1186/s12891-024-07777-4 DOI: https://doi.org/10.1186/s12891-024-07777-4
Luo M, Duan Z, Gao J, Sun Y, Chen L, Feng X. Evaluating the role of ChatGPT in rehabilitation medicine: a narrative review. Front Digit Health. 2025;7:1618510. doi: 10.3389/fdgth.2025.1618510 DOI: https://doi.org/10.3389/fdgth.2025.1618510
Khan MA, Koh RGL, Rashidiani S, Liu T, Tucci V, Kumbhare D, et al. Cracking the Chronic Pain code: A scoping review of Artificial Intelligence in Chronic Pain research. Artif Intell Med. 2024;151:102849. doi: 10.1016/j.artmed.2024.102849 DOI: https://doi.org/10.1016/j.artmed.2024.102849
Hill CJ, Banerjee A, Hill J, Stapleton C. Diagnostic clinical prediction rules for categorising low back pain: A systematic review. Musculoskeletal Care. 2023; 21(4):1482–96. doi: 10.1002/msc.1816 DOI: https://doi.org/10.1002/msc.1816
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. doi: 10.1136/bmj.n71 DOI: https://doi.org/10.1136/bmj.n71
Maher CG, Sherrington C, Herbert RD, Moseley AM, Elkins M. Reliability of the PEDro Scale for Rating Quality of Randomized Controlled Trials. Phys Ther. 2003; 83(8):713–21. doi: 10.1093/ptj/83.8.713 DOI: https://doi.org/10.1093/ptj/83.8.713
Wells GA, Shea B, O’Connell D, Peterson J, Welch V, Losos M, et al. The Newcastle-Ottawa Scale (NOS) for assessing the quality of nonrandomised studies in meta-analyses [Internet]. Ottawa (ON): Ottawa Hospital Research Institute; [cited 2026 Feb 16]. Available from: http://www.ohri.ca/programs/clinical_epidemiology/oxford.asp
Xiao C, Zhao Y, Li G, Zhang Z, Liu S, Fan W, et al. Clinical Efficacy of Multimodal Exercise Telerehabilitation Based on AI for Chronic Nonspecific Low Back Pain: Randomized Controlled Trial. JMIR Mhealth Uhealth. 2025; 13:e56176. doi: 10.2196/56176 DOI: https://doi.org/10.2196/56176
Cheema C, Baldwin J, Rodeghero J, Werneke MW, Mioduski JE, Jeffries L, et al. Use of machine learning to identify prognostic variables for outcomes in chronic low back pain treatment: a retrospective analysis. J Man Manip Ther. 2025; 33(1):63–72. doi: 10.1080/10669817.2024.2424619 DOI: https://doi.org/10.1080/10669817.2024.2424619
Griefahn A, Avermann F, Zalpour C, Marshall RP, Cordon Morillas I, Luedtke K. Exploring the Effect of an 8-Week AI-Composed Exercise Program on Pain Intensity and Well-Being in Patients With Spinal Pain: Retrospective Cohort Analysis. JMIR Form Res. 2025; 9:e57826. doi: 10.2196/57826 DOI: https://doi.org/10.2196/57826
Alzouhayli K, Schilaty ND, Nagai T, Rigamonti L, McPherson AL, Holmes BD, et al. Artificial intelligence-guided therapy: Clinic versus home users. Long-term differences in patient-reported outcomes in patients with low back pain. J Orthop Rep. 2025; 4(2):100592. doi: 10.1016/j.jorep.2025.100592 DOI: https://doi.org/10.1016/j.jorep.2025.100592
Pfeifer AC, Schröder-Pfeifer P, Schiltenwolf M, Vogt L, Schneider C, Platen P, et al. Finding Predictive Factors of Stabilization Exercise Adherence in Randomized Controlled Trials on Low Back Pain: An Individual Data Reanalysis Using Machine Learning Techniques. Arch Phys Med Rehabil. 2025; 106(5):738–49. doi: 10.1016/j.apmr.2024.12.015 DOI: https://doi.org/10.1016/j.apmr.2024.12.015
Areias AC, Janela D, Moulder RG, Molinos M, Bento V, Moreira C, et al. Applying AI to Safely and Effectively Scale Care to Address Chronic MSK Conditions. J Clin Med. 2024; 13(15):4366. doi: 10.3390/jcm13154366 DOI: https://doi.org/10.3390/jcm13154366
Areias AC, Moulder RG, Molinos M, Janela D, Bento V, Moreira C, et al. Predicting Pain Response to a Remote Musculoskeletal Care Program for Low Back Pain Management: Development of a Prediction Tool. JMIR Med Inform. 2024; 12:e64806. doi: 10.2196/64806 DOI: https://doi.org/10.2196/64806
Zhao X, Dannenberg K, Repsilber D, Gerdle B, Molander P, Hesser H. Prognostic subgroups of chronic pain patients using latent variable mixture modeling within a supervised machine learning framework. Sci Rep. 2024; 14(1):12579. doi: 10.1038/s41598-024-62542-w DOI: https://doi.org/10.1038/s41598-024-62542-w
Bates NA, Huffman A, Goodyear E, Nagai T, Rigamonti L, Breuer L, et al. Physical clinical care and artificial-intelligence-guided core resistance training improve endurance and patient-reported outcomes in subjects with lower back pain. Clin Biomech. 2023;103:105902. doi: 10.1016/j.clinbiomech.2023.105902 DOI: https://doi.org/10.1016/j.clinbiomech.2023.105902
Marcuzzi A, Nordstoga AL, Bach K, Aasdahl L, Nilsen TIL, Bardal EM, et al. Effect of an Artificial Intelligence–Based Self-Management App on Musculoskeletal Health in Patients With Neck and/or Low Back Pain Referred to Specialist Care: A Randomized Clinical Trial. JAMA Netw Open. 2023; 6(6):e2320400. doi: 10.1001/jamanetworkopen.2023.20400 DOI: https://doi.org/10.1001/jamanetworkopen.2023.20400
Tun Firzara AM, Teo CH, Teh S, Su JY, Zaini HSM, Suhaimi AB, et al. Evaluation of an electronic clinical decision support system (DeSSBack) to improve low back pain management: a pilot cluster randomized controlled trial. Fam Pract. 2023; 40(5–6):742–52. doi: 10.1093/fampra/cmad044 DOI: https://doi.org/10.1093/fampra/cmad044
Park C, Yi C, Choi WJ, Lim HS, Yoon HU, You SJH. Long-term effects of deep-learning digital therapeutics on pain, movement control, and preliminary cost-effectiveness in low back pain: a randomized controlled trial. Digit Health. 2023;9:20552076231217816. doi: 10.1177/20552076231217817 DOI: https://doi.org/10.1177/20552076231217817
Hartmann R, Avermann F, Zalpour C, Griefahn A. Impact of an AI app-based exercise program for people with low back pain compared to standard care: A longitudinal cohort-study. Health Sci Rep. 2023; 6(1):e1060. doi: 10.1002/hsr2.1060 DOI: https://doi.org/10.1002/hsr2.1060
Nordstoga AL, Aasdahl L, Sandal LF, Dalager T, Kongsvold A, Mork PJ, et al. The Role of Pain Duration and Pain Intensity on the Effectiveness of App-Delivered Self-Management for Low Back Pain (selfBACK): Secondary Analysis of a Randomized Controlled Trial. JMIR Mhealth Uhealth. 2023; 11:e40422. doi: 10.2196/40422 DOI: https://doi.org/10.2196/40422
Strigo IA, Simmons AN, Giebler J, Schilling JM, Moeller-Bertram T. Unsupervised learning for prognostic validity in patients with chronic pain in transdisciplinary pain care. Sci Rep. 2023; 13(1):7603. doi: 10.1038/s41598-023-34611-z DOI: https://doi.org/10.1038/s41598-023-34611-z
Zmudzki F, Smeets RJEM. Machine learning clinical decision support for interdisciplinary multimodal chronic musculoskeletal pain treatment. Front Pain Res. 2023;4:1177070. doi: 10.3389/fpain.2023.1177070 DOI: https://doi.org/10.3389/fpain.2023.1177070
Knoop J, van Lankveld W, Beijer L, Geerdink FJB, Heymans MW, Hoogeboom TJ, et al. Development and internal validation of a machine learning prediction model for low back pain non-recovery in patients with an acute episode consulting a physiotherapist in primary care. BMC Musculoskelet Disord. 2022; 23(1):834. doi: 10.1186/s12891-022-05718-7 DOI: https://doi.org/10.1186/s12891-022-05718-7
Park J, Chung S, Park JH. Real-Time Exercise Feedback through a Convolutional Neural Network: A Machine Learning-Based Motion-Detecting Mobile Exercise Coaching Application. Yonsei Med J. 2022; 63 Suppl:S34–42. doi: 10.3349/ymj.2022.63.S34 DOI: https://doi.org/10.3349/ymj.2022.63.S34
Anan T, Kajiki S, Oka H, Fujii T, Kawamata K, Mori K, et al. Effects of an artificial intelligence-assisted health program on workers with neck/shoulder pain/stiffness and low back pain: Randomized controlled trial. JMIR Mhealth Uhealth. 2021; 9(9):e27535. doi: 10.2196/27535 DOI: https://doi.org/10.2196/27535
Soer R. Artificial intelligence in musculoskeletal rehabilitation. J Back Musculoskelet Rehabil. 2023; 36(5):993–4. doi: 10.3233/BMR-235003 DOI: https://doi.org/10.3233/BMR-235003
Descargas
Licencia
Derechos de autor 2026 Marcos Campillos Lázaro

Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.