A Aplicação de Algoritmos de Machine Learning Integrada ao Prontuário Eletrônico na Predição de Doenças Crônicas na Atenção Primária

Andresa Jardim Bueno Damasio da Silva; Ivan Torres Pisa; Cláudia Galindo Novoa; Vladimir Camelo Pinto

doi:10.36489/saudecoletiva.2025v16i101p17422-17433

Autores/as

Andresa Jardim Bueno Damasio da Silva Especialista em Saúde da Família - UNIFESP 2016 Especialista em Informática em Saúde - UNIFESP 2025. Gerente de Serviços de Saúde - OS Monte Azul https://orcid.org/0009-0009-2592-5855
Ivan Torres Pisa Professor; UNIFESP. Livre docente em informática em saúde; UNIFESP; 2013 https://orcid.org/0000-0002-5106-3904
Cláudia Galindo Novoa Professor Associado UNIFESP
Vladimir Camelo Pinto Doutorando em Sistemas de Informação - EACH-USP 2025 Mestre em CIências (Informática em Saúde) - UNIFESP 2008 Bacharel em Ciência da Computação - UNICSUL 2004 Professor EBTT no Instituto Federal de São Paulo (IFSP)

DOI:

https://doi.org/10.36489/saudecoletiva.2025v16i101p17422-17433

Palabras clave:

Inteligência Artificial, Historia Clínica Electrónica, Atención Primaria, Predicción de Enfermedades

Resumen

OBJETIVO: Identificar la aplicación de la Inteligencia Artificial integrada en la Historia Clínica Electrónica en atención primaria para la predicción de enfermedades crónicas. MÉTODO: Se utilizaron las bases de datos PubMed y Biblioteca Virtual de Salud. Los criterios de inclusión utilizados fueron: Artículos publicados entre 2019 y 2024, y estudios relacionados con la predicción de enfermedades en contextos de atención primaria utilizando Inteligencia Artificial. RESULTADOS: Los estudios mostraron mejoras en el diagnóstico precoz, la identificación de factores de riesgo y la reducción de hospitalizaciones, aunque persisten retos como la interoperabilidad limitada y la dependencia de datos de calidad. CONCLUSIÓN: A partir de los análisis del potencial y las limitaciones de la integración de la Inteligencia Artificial con los Registros Electrónicos de Pacientes en la gestión de enfermedades crónicas, se recomienda que los esfuerzos futuros se centren en estandarizar los datos y mejorar la infraestructura técnica para optimizar el impacto en la atención primaria.

Citas

Raat W, Smeets M, Henrard S, Aertgeerts B, Penders J, Droogne W, Mullens W, Janssens S, Vaes B. Machine learning optimization of an electronic health record audit for heart failure in primary care. ESC Heart Fail . 2021;9(1):39-47. Disponível em: https://doi.org/10.1002/ehf2.13724.

Zafari H, Langlois S, Zulkernine F, Kosowan L, Singer A. AI in predicting COPD in the Canadian population. Biosystems [Internet]. 2022; 211:104585. Disponível em: https://doi.org/10.1016/j.biosystems.2021.104585.

Mosa AI, Watts D, Tangri N. Impacting management of chronic kidney disease through primary care practice audits: a quality improvement study. Can J Kidney Health Dis. 2022; 9:205435812211448. Disponível em: https://doi.org/10.1177/20543581221144840.

Gomes SA, Montanini JF, Rocha Sobrinho HM. O uso da Inteligência Artificial na Medicina: os benefícios e desafios da parceria homem-tecnologia na saúde. Rev Eletronica Acervo Saude. 2024; 24(12):e18374. Disponível em: https://doi.org/10.25248/reas.e18374.2024.

Rafiq M, Mazzocato P, Guttmann C, Spaak J, Savage C. Predictive analytics support for complex chronic medical conditions: an experience-based co-design study of physician managers’ needs and preferences. SSRN Electron J. 2021. Disponível em: https://doi.org/10.2139/ssrn.3976786

Sá-Silva JR, Almeida CD, Guindani JF. Pesquisa documental: pistas teóricas e metodológicas. Rev Bras Hist Ciênc Soc. 2009;1(1).

Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, Shamseer L, Tetzlaff JM, Akl EA, Brennan SE, Chou R, Glanville J, Grimshaw JM, Hróbjartsson A, Lalu MM, Li T, Loder EW, Mayo-Wilson E, McDonald S, McGuinness LA, Stewart LA, Thomas J, Tricco AC, Welch VA, Whiting P, Moher D. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. J Clin Epidemiol. 2021;134:178-89. Disponível em: https://doi.org/10.1016/j.jclinepi.2021.03.001.

Butzin-Dozier Z, Ji Y, Li H, Coyle J, Shi J, Phillips RV, Mertens A, Pirracchio R, van der Laan MJ, Patel RC, Colford JM, Hubbard AE. Predicting long COVID in the national COVID cohort collaborative using super learner: cohort study (preprint). JMIR Public Health Surveill. 2023. Disponível em: https://doi.org/10.2196/53322.

Hrabok M, Engbers JD, Wiebe S, Sajobi TT, Subota A, Almohawes A, Federico P, Hanson A, Klein KM, Peedicail J, Pillay N, Singh S, Josephson CB. Primary care electronic medical records can be used to predict risk and identify potentially modifiable factors for early and late death in adult onset epilepsy. Epilepsia. 2020. Disponível em: https://doi.org/10.1111/epi.16738.

Nadarajah R, Wu J, Hogg D, Raveendra K, Nakao YM, Nakao K, Arbel R, Haim M, Zahger D, Parry J, Bates C, Cowan C, Gale CP. Prediction of short-term atrial fibrillation risk using primary care electronic health records. Heart. 2023 heartjnl—2022-322076. Disponível

em: https://doi.org/10.1136/heartjnl-2022-322076.

Ställberg B, Lisspers K, Larsson K, Janson C, Müller M, Łuczko M, Kjøller Bjerregaard B, Bacher G, Holzhauer B, Goyal P, Johansson G. Predicting hospitalization due to COPD exacerbations in swedish primary care patients using machine learning – based on the ARCTIC study. Int J Chronic Obstr Pulm Dis [Internet]. 2021;16:677-88. Disponível em: https://doi.org/10.2147/copd.s293099.

Emeihe EV, Nwankwo EI, Ajegbile MD, Olaboye JA, Maha CC. The impact of artificial intelligence on early diagnosis of chronic diseases in rural areas. Comput Sci Amp IT Res J. 2024;5(8):1828-54. Disponível em: https://doi.org/10.51594/csitrj.v5i8.1447.

Freek A, Elgalb A, Gerges M. AI for Early Disease Detection: Developing models for early diagnosis of diseases like cancer or Alzheimer’s using biomarkers and imaging data. J AI Powered Med Innov (Int Online ISSN 3078 1930). 2024;3(1):1-24. Disponível

em: https://doi.org/10.60087/japmi.vol.03.issue.01.id.001.

Wake AP, Pawar AP. Review paper on early detection of chronic kidney disease using predictive AI. Int J Res Appl Sci Eng Technol. 2024 ;12(11):2378-80. Disponível em: https://doi.org/10.22214/ijraset.2024.65604.

Moreno-Sánchez PA. Data-driven early diagnosis of Chronic Kidney Disease: development and evaluation of an explainable AI model. IEEE Access. 2023 [citado 23 jun 2025]:1. Disponível em: https://doi.org/10.1109/access.2023.3264270.

Panguraj AR. Exploring how llms can analyse patient data, medical literature, and symptoms to assist in the early detection of chronic conditions like diabetes, cancer, or cardiovascular diseases. Interantional J Sci Res Eng Manag. 23 jan 2025 [citado 23 jun 2025];09(01):1-7. Disponível em: https://doi.org/10.55041/ijsrem22924.

Bhatt P, Liu J, Gong Y, Wang J, Guo Y. Emerging artificial intelligence-empowered mobile health: a scoping review (preprint). JMIR mHealth uHealth [Internet]. 18 nov 2021 [citado 23 jun 2025]. Disponível em: https://doi.org/10.2196/35053.

Mirkin S, Albensi BC. Should artificial intelligence be used in conjunction with Neuroimaging in the diagnosis of Alzheimer’s disease? Front Aging Neurosci [Internet]. 18 abr 2023 [citado 23 jun 2025];15. Disponível em: https://doi.org/10.3389/fnagi.2023.1094233.

Alshuhri M, Al-Musawi SG, Al-Alwany AA, Uinarni H, Rasulova I, Rodrigues P, Alkhafaji AT, Alshanberi AM, Alawadi AH, Abbas AH. Artificial intelligence in cancer diagnosis: opportunities and challenges. Pathol Res Pract [Internet]. Nov 2023

[citado 23 jun 2025]:154996. Disponível em: https://doi.org/10.1016/j.prp.2023.154996.