Aplicaciones de la Inteligencia Artificial en Enfermería para la Detección Temprana del Deterioro Clínico: Una Revisión Rápida

Avixely Vargas Blanco
Departamento de Enfermería, Investigación. Clínica Bíblica, San José, Costa Rica.

Resumen

El deterioro clínico hospitalario suele estar precedido por cambios fisiológicos y en algunos casos comportamentales sutiles que con frecuencia pasan desapercibidos. La enfermería, responsable de la valoración continua, ocupa una posición estratégica para su detección temprana. Las herramientas basadas en inteligencia artificial (IA) emergen como aliadas potenciales para anticipar eventos adversos, aunque la evidencia se encuentra dispersa y el rol específico de enfermería no siempre se establece de manera explícita. Para ello se llevó a cabo una revisión rápida siguiendo los lineamientos PRISMA, se incluyeron estudios publicados entre 2018–2025 en español e inglés que describen el uso de IA por enfermería para la detección temprana del deterioro clínico en pacientes hospitalizados. Se consultaron las bases de datos PubMed/MEDLINE, Science Direct, Cochrane y LILACS. Se incluyeron 30 artículos, donde predominaron sistemas de alerta temprana basados en aprendizaje automático, puntajes predictivos y sistemas de soporte de decisiones clínicas (CDSS) integrados al expediente electrónico. Estas herramientas permiten identificar riesgo entre 8 y 42 horas antes del evento, superando a puntajes en escalas tradicionales y algunos estudios mostraron reducción significativa de la mortalidad (16.9% vs 24.6%) y estancia hospitalaria (23.0 vs 27.5 días). La enfermería emergió como fuente primaria de datos, principal usuaria y líder del escalamiento oportuno del cuidado. Las barreras más frecuentes fueron fatiga de alertas, baja interpretabilidad e integración limitada al flujo clínico. En general, la IA ofrece la posibilidad de potenciar la detección temprana del deterioro cuando se integra en procesos liderados por enfermería y complementa el juicio clínico, pero su impacto depende menos de la precisión algorítmica que de un diseño centrado en la persona, contemplación ética y formación profesional.

Palabras claves

Inteligencia Artificial, Enfermería, Deterioro Clínico, Puntuación de Alerta Temprana, Pacientes, Hospitalización.

Abstract

In-hospital clinical deterioration is often preceded by subtle physiological and, in some cases, behavioral changes that frequently go unnoticed. Nursing, responsible for continuous patient assessment, occupies a strategic position for early detection. Artificial intelligence (AI)–based tools are emerging as potential allies to anticipate adverse events; however, the evidence remains fragmented and the specific role of nursing is not always explicitly defined. To address this gap, a rapid review was conducted following PRISMA guidelines, including studies published between 2018 and 2025 in Spanish and English that described the use of AI by nursing for the early detection of clinical deterioration in hospitalized patients. The databases PubMed/MEDLINE, ScienceDirect, Cochrane, and LILACS were searched. Thirty articles were included, with a predominance of machine learning–based early warning systems, predictive scores, and clinical decision support systems (CDSS) integrated into the electronic health record. These tools enable risk identification 8 to 42 hours prior to the event, outperforming traditional scoring systems, and some studies reported significant reductions in mortality (16.9% vs. 24.6%) and length of stay (23.0 vs. 27.5 days). Nursing emerged as the primary source of data, the main user, and the leader in timely escalation of care. The most frequent barriers were alert fatigue, low interpretability, and limited integration into clinical workflows. Overall, AI offers the potential to enhance early detection of deterioration when embedded within nurse-led processes and used to complement clinical judgment; however, its impact depends less on algorithmic precision than on person-centered design, ethical consideration, and professional training.

Keywords

Artificial Intelligence, Nursing, Clinical Deterioration, Early Warning Scores, Patients, Hospitalization.

Referencias

1. Gallo RJ, Shieh L, Smith M, Marafino BJ, Geldsetzer P, Asch SM, et al. Effectiveness of an Artificial Intelligence–Enabled Intervention for Detecting Clinical Deterioration. JAMA Intern Med. 2024;184(5):557–62. DOI: 10.1001/jamaintern- med.2024.0084

2. Escobar GJ, Liu VX, Schuler A, Lawson B, Greene JD, Kipnis P. Automated Identification of Adults at Risk for In-Hospital Clinical Deterioration. New England Journal of Medicine. Massachusetts Medical Society; 2020;383(20):1951–60. DOI: 10.1056/nejmsa2001090

3. Muralitharan S, Nelson W, Di S, McGillion M, Devereaux PJ, Barr NG, et al. Machine learning–Based early warning systems for clinical deterioration: Systematic scoping review. J Med Internet Res. JMIR Publications Inc.; 2021;23(2). DOI: 10.2196/25187

4. Ko RE, Kim Z, Jeon B, Ji M, Chung CR, Suh GY, et al. Deep Learning-Based Early Warning Score for Predicting Clinical Deterioration in General Ward Cancer Patients. Cancers (Basel). Multidisciplinary Digital Publishing Institute (MDPI); 2023;15(21). DOI: 10.3390/cancers15215145

5. Linnen DT, Escobar GJ, Hu X, Scruth E, Liu V, Stephens C. Statistical modeling and aggregate-weighted scoring systems in prediction of mortality and ICU transfer: A systematic review. J Hosp Med. Frontline Medical Communications; 2019;14(3):161–9. DOI: 10.12788/jhm.3151

6. El Arab RA, Al Moosa OA, Sagbakken M, Ghannam A, Abuadas FH, Somerville J, et al. Integrative review of artificial intelligence applications in nursing: education, clinical practice, workload management, and professional perceptions. Front Public Health. Frontiers Media SA; 2025;13. DOI: 10.3389/- FPUBH.2025.1619378

7. Schwartz JM, George M, Rossetti SC, Dykes PC, Minshall SR, Lucas E, et al. Factors Influencing Clinician Trust in Predictive Clinical Decision Support Systems for In-Hospital Deterioration: Qualitative Descriptive Study. JMIR Hum Factors. JMIR Publications Inc.; 2022;9(2). DOI: 10.2196/33960

8. Ouzzani M, Hammady H, Fedorowicz Z, Elmagarmid A. Rayyan-a web and mobile app for systematic reviews. Syst Rev. BioMed Central Ltd.; 2016;5(1). DOI: 10.1186/s13643-016-0384-4

9. Haddaway NR, Page MJ, Pritchard CC, McGuinness LA. PRISMA2020: An R package and Shiny app for producing PRISMA 2020-compliant flow diagrams, with interactivity for optimised digital transparency and Open Synthesis. Campbell Systematic Reviews. John Wiley & Sons, Ltd; 2022;18(2):e1230. DOI: 10.1002/cl2.1230

10. Lee RY, Cato KD, Dykes PC, Lowenthal G, Withall JB, Cho S, et al. Influence of the CONCERN Early Warning System on Unanticipated ICU Transfers, In-Hospital Mortality, and Length of Stay: Results from a Multi-site Pragmatic Randomized Controlled Clinical Trial. AMIA Annu Symp Proc [Internet]. 2024 [cited 2026 Jan 27];655–63. Available from: https://pubmed.ncbi.nlm.nih.gov/40417527/

11. Rossetti SC, Dykes PC, Knaplund C, Cho S, Withall J, Lowen- thal G, et al. Multisite Pragmatic Cluster-Randomized Controlled Trial of the CONCERN Early Warning System. medRxiv. 2024; DOI: 10.1101/2024.06.04.24308436  

12. Lee RY, Cato KD, Dykes PC, Lowenthal G, Tuteja S, Rossetti SC. Understanding Clinicians’ Usage Patterns of the CONCERN Early Warning System: Insights from a Multi-Site Pragmatic Cluster Randomized Controlled Trial. Stud Health Technol Inform. IOS Press BV; 2025;329:1256–60. DOI: 10.3233/SHTI251040

13. Blythe R, Naicker S, White N, Donovan R, Scott IA, McKelliget A, et al. Clinician perspectives and recommendations regarding design of clinical prediction models for deteriorating patients in acute care. BMC Med Inform Decis Mak. BioMed Central Ltd; 2024;24(1). DOI: 10.1186/s12911-024-02647-4

14. Xu X, Chen M, Chen L, Huang K, Cao S, Gao W, et al. CKRT coagulation risk prediction and nursing feedback model based on intelligent algorithms. BMC Nephrol. BioMed Central Ltd; 2025;26(1). DOI: 10.1186/s12882-025-04206-z

15. Collins Rossetti S, Knaplund C, Albers D, Tariq A, Tang K, Vawdrey D, et al. Leveraging Clinical Expertise as a Feature-not an Outcome-of Predictive Models: Evaluation of an Early Warning System Use Case. AMIA Annu Symp Proc [Internet]. 2020 [cited 2026 Jan 27];323–32. Available from: https://pmc.ncbi.nlm.nih.gov/articles/PMC7153052/

16. Scherer J de S, Pereira JS, Debastiani MS, Bica CG. Beyond technology: Can artificial intelligence support clinical decisions in the prediction of sepsis? Rev Bras Enferm. Associacao Brasilerira de Enfermagem; 2022;75(5). DOI: 10.1590/0034-7167-2021-0586

17. Kim Y, Kim M, Kim Y, Choi M. Using nursing data for machine learning-based prediction modeling in intensive care units: A scoping review. Int J Nurs Stud. Elsevier Ltd; 2025;169. DOI: 10.1016/j.ijnurstu.2025.105133

18. Klumpner TT, Kountanis JA, Langen ES, Smith RD, Tremper KK. Use of a novel electronic maternal surveillance system to generate automated alerts on the labor and delivery unit. BMC Anesthesiol. BioMed Central Ltd.; 2018;18(1). DOI: 10.1186/s12871-018-0540-6

19. Wan YKJ, Wright MC, McFarland MM, Dishman D, Nies MA, Rush A, et al. Information displays for automated surveillance algorithms of in-hospital patient deterioration: a scoping review. Journal of the American Medical Informatics Association. Oxford University Press; 2024;31(1):256–73. DOI: 10.1093/jamia/ocad203

20. Weenk M, Bredie SJ, Koeneman M, Hesselink G, Van Goor H, Van De Belt TH. Continuous monitoring of vital signs in the general ward using wearable devices: Randomized controlled trial. J Med Internet Res. JMIR Publications Inc.; 2020;22(6). DOI: 10.2196/15471

21. Ginestra JC, Giannini HM, Schweickert WD, Meadows L, Lynch MJ, Pavan K, et al. Clinician Perception of a Machine Learning–Based Early Warning System Designed to Predict Severe Sepsis and Septic Shock. Crit Care Med. Lippincott Williams and Wilkins; 2019;47(11):1477–84. DOI: 10.1097/CCM.0000000000003803

22. Gonçalves LS, Amaro MLM, Schamne FK, Gariba IMP. Nursing Documentation and Activities when Using a Clinical Decision Support System for Sepsis and Clinical Deterioration Management. Stud Health Technol Inform. IOS Press BV; 2022;294:153–4. DOI: 10.3233/SHTI220426  

23. Wan YKJ, Abdelrahman SE, Facelli JC, Madaras-Kelly K, Kawamoto K, Dishman D, et al. Conceptual framework for prediction models of patient deterioration based on nursing documentation patterns: reproducibility and generalizability with a large number of hospitals across the United States. J Biomed Inform. Academic Press Inc.; 2025;169. DOI: 10.1016/j.jbi.2025.104887

24, Romero-Brufau S, Whitford D, Johnson MG, Hickman J, Morlan BW, Therneau T, et al. Using machine learning to improve the accuracy of patient deterioration predictions: Mayo Clinic Early Warning Score (MC-EWS). Journal of the American Medical Informatics Association. Oxford University Press; 2021;28(6):1207–15. DOI: 10.1093/jamia/ocaa347

25. Jahandideh S, Ozavci G, Sahle BW, Kouzani AZ, Magrabi F, Bucknall T. Evaluation of machine learning-based models for prediction of clinical deterioration: A systematic literature review. Int J Med Inform. Elsevier Ireland Ltd; 2023;175. DOI: 10.1016/j.ijmedinf.2023.105084

26. Wang L, Liu Q, Wu C, Hou M, Li Z. Establishment and validation of the prediction model based on lymphocyte subsets for acute kidney injury in sepsis patients. Front Immunol. Frontiers Media SA; 2025;16. DOI: 10.3389/fimmu.2025.1674673

27. He Y, Huang J, Li N, Zhou G, Liu J. Artificial intelligence-driven prediction and interpretation of central line-associated bloodstream infections in ICU: insights from the MIMIC-IV database. Front Public Health. Frontiers Media SA; 2025;13. DOI: 10.3389/fpubh.2025.1675077

28. Jeffery AD, Dietrich MS, Fabbri D, Kennedy B, Novak LL, Coco J, et al. Advancing in-hospital clinical deterioration prediction models. American Journal of Critical Care. American Association of Critical Care Nurses; 2018;27(5):381–91. DOI: 10.4037/ajcc2018957

29. Van Der Vegt AH, Campbell V, Mitchell I, Malycha J, Simpson J, Flenady T, et al. Systematic review and longitudinal analysis of implementing Artificial Intelligence to predict clinical deterioration in adult hospitals: What is known and what remains uncertain. Journal of the American Medical Informatics Association. Oxford University Press; 2024;31(2):509–24. DOI: 10.1093/jamia/ocad220

30. Lei L, Zhang S, Yang L, Yang C, Liu Z, Xu H, et al. Machine learning-based prediction of delirium 24 h after pediatric intensive care unit admission in critically ill children: A prospective cohort study. Int J Nurs Stud. Elsevier Ltd; 2023;146:104565. DOI: 10.1016/j.ijnurstu.2023.104565

31. Dai L, Wu Z, Pan X, Zheng D, Kang M, Zhou M, et al. Design and implementation of an automatic nursing assessment system based on CDSS technology. Int J Med Inform. Elsevier Ireland Ltd; 2024;183. DOI: 10.1016/j.ijmedinf.2023.105323

32. Wang F, Zhu Y, Wang L, Huang C, Mei R, Deng L e., et al. Machine learning risk prediction model for bloodstream infections related to totally implantable venous access ports in patients with cancer. Asia Pac J Oncol Nurs. Asian Onscology Nursing Society; 2024;11(8). DOI: 10.1016/j.apjon.2024.100546  

33. Conway A, Jungquist CR, Chang K, Kamboj N, Sutherland J, Mafeld S, et al. Predicting Prolonged Apnea During Nurse-Administered Procedural Sedation: Machine Learning Study. JMIR Perioper Med. JMIR Publications Inc.; 2021;4(2):e29200. DOI: 10.2196/29200

34. Keim-Malpass J, Moorman LP. Nursing and precision predictive analytics monitoring in the acute and intensive care setting: An emerging role for responding to COVID-19 and beyond. Int J Nurs Stud Adv. Elsevier B.V.; 2021;3. DOI: 10.1016/j.ijnsa.2021.100019

35. Laursen SH, Hæsum LKE, Egmose J, Kronborg T, Udsen FW, Hejlesen OK, et al. Implementation of an algorithm for predicting exacerbations in telemonitoring: A multimethod study of patients’ and clinicians’ experiences. Int J Nurs Stud Adv. Elsevier B.V.; 2024;7. DOI: 10.1016/j.ijnsa.2024.100257

36. Do TC, Yang HJ, Kim SH, Kho BG, Park JK. Multi-horizon event detection for in-hospital clinical deterioration using dual-channel graph attention network. Int J Med Inform. Elsevier Ireland Ltd; 2025;195. DOI: 10.1016/j.ijmedinf.2024.105745

37. Thiele D, Rodseth R, Friedland R, Berger F, Mathew C, Maslo C, et al. Machine Learning Models for the Early Real-Time Prediction of Deterioration in Intensive Care Units—A Novel Approach to the Early Identification of High-Risk Patients. J Clin Med. Multidisciplinary Digital Publishing Institute (MDPI); 2025;14(2). DOI: 10.3390/jcm14020350

38. Yuan S, Yang Z, Li J, Wu C, Liu S. AI-Powered early warning systems for clinical deterioration significantly improve patient outcomes: a meta-analysis. BMC Med Inform Decis Mak. BioMed Central Ltd; 2025;25(1). DOI: 10.1186/s12911-025-03048-x

39. Cao Y, Deng L, Liu X, Feng Z, Gao Y. Ethical challenges in the algorithmic era: a systematic rapid review of risk insights and governance pathways for nursing predictive analytics and early warning systems. BMC Med Ethics. BioMed Central Ltd; 2025;26(1). DOI: 10.1186/s12910-025-01308-z