Resumen
Objetivo: Identificar enfoques y la eficacia de la Inteligencia Artificial (IA) en la predicción de factores de riesgo para la sepsis neonatal. Métodos: Se trata de una revisión integradora realizada en las bases de datos PubMed, Scopus, Web of Science e IEEE, utilizando los siguientes descriptores: "neonatal sepsis", "intensive care units, neonatal", "artificial intelligence", "machine learning" y "deep learning". Se incluyeron estudios publicados entre 2014 y 2024 que incluyeron sepsis neonatal en unidades de cuidados intensivos. Resultados: La muestra final consistió en 06 artículos, con una mayor concentración de publicaciones en 2021. La mayoría de los estudios se realizaron en EE.UU., y los diseños de investigación predominantes fueron estudios de cohorte retrospectiva. Se encontró que los modelos de IA, como Random Forest, SVM y Regresión Logística, son eficaces en la predicción de factores de riesgo críticos para la sepsis neonatal, lo que permite intervenciones clínicas más tempranas y precisas, lo que puede mejorar significativamente los resultados clínicos en neonatos vulnerables. Consideraciones finales: Esta revisión destaca el impacto de los modelos de IA en la predicción de la sepsis neonatal, demostrando su potencial para intervenciones clínicas anticipadas. Sin embargo, futuras investigaciones deben centrarse en la validación externa y en la cuidadosa integración de estos modelos en la práctica clínica.
Referencias
ALOWAIS AS, et al. Revolutionizing healthcare: the role of artificial intelligence in clinical practice. BMC Med Educ., 2023; 23(1): 689.
BARTZ-KURYCKI MA, et al. Enhanced neonatal surgical site infection prediction model utilizing statistically and clinically significant variables in combination with a machine learning algorithm. Am. J. Surg., 2018; 216: 764-77.
BRASIL. Ministério da Saúde (MS). Lei no 9.610, de 19 de fevereiro de 1998, que altera, atualiza e consolida a legislação sobre direitos autorais e dá outras providências. Diário Oficial da União. Brasília: Ministério da Saúde, 1998.
BOETTIGER M, et al. Nurses’ early recognition of neonatal sepsis. J Obstet Gynecol Neonatal Nurs., 2017; 46(6): 834-845.
BURDICK H, et al. Validation of a machine learning algorithm for early severe sepsis prediction: a retrospective study predicting severe sepsis up to 48 h in advance using a diverse dataset from 461 US hospitals. BMC Med. Inform. Decis. Mak., 2020; 20: 1-10.
CABRERA-QUIROS L, et al. Prediction of Late-Onset Sepsis in Preterm Infants Using Monitoring Signals and Machine Learning. Crit Care Explor., 2021; 3(1): e0302.
CAMARGO JF, et al. Sepse neonatal precoce: prevalência, complicações e desfechos em recém-nascidos com 35 semanas ou mais de idade gestacional. Rev. paul. Pediatr., 2022; 40: e2020388.
COGGINS SA, et al. Updates in Late-Onset Sepsis: Risk Assessment, Therapy, and Outcomes. Neoreviews, 2022; 23(11): 738-755.
DELANEY RM, et al. The immune system. In: Jnah AJ, Trembath AN, eds. Fetal and Neonatal Physiology for the Advanced Practice Nurse. New York, NY: Springer Publishing Company, 2019; 267-306.
DONG Y, et al. Late-onset sepsis caused by gramnegative bacteria in very low birthweight infants: a systematic review. Expert Rev Anti Infect Ther., 2019; 17(3): 177-88.
FLEUREN LM, et al. Machine learning for the prediction of sepsis: A systematic review and meta-analysis of diagnostic test accuracy. Intensive Care Med., 2020; 46:383–400.
GIANNINI HM. A machine learning algorithm to predict severe sepsis and septic shock: Development, implementation, and impact on clinical practice. Crit. Care Med., 2019; 47: 1485-92.
HELGUERA-REPETTO AC, et al. Neonatal sepsis diagnosis decision-making based on artificial neural networks. Front Pediatr., 2020; 8: 525.
HUANG B, et al. Aiding clinical assessment of neonatal sepsis using hematological analyzer data with machine learning techniques. Int J Lab Hematol., 2021; 43(6): 1341-56.
LANGSETMO L, et al. Advantages and Disadvantages of Random Forest Models for Prediction of Hip Fracture Risk Versus Mortality Risk in the Oldest Old. JBMR Plus, 2023; 7(8): e10757.
OLIVEIRA SG, et al. Septicemia bacteriana do recém-nascido no brasil nos anos de 2013 a 2017. Brazilian Journal of Health Review, 2017; 3(2): 1404–1421.
MANI S, et al. Medical decision support using machine learning for early detection of late-onset neonatal sepsis. J. Am. Med. Inform. Assoc., 2014; 21: 326-36.
MASINO AJ, et al. Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data. PLoS One, 2019; 14(2): e0212665.
MCHUGH ML. Interrater reliability: the kappa statistic. Biochemia Medica, 2012; 22(3): 276-82.
PARVIN S, et al. Analysis of machine learning and deep learning prediction models for sepsis and neonatal sepsis: A systematic review. ICT Express, 2023; 9(6): 1215-25.
PUOPOLO KM, et al. Management of neonates born at ≥35 0/7 weeks’ gestation with suspected or proven early-onset bacterial sepsis. Pediatrics, 2018; 142(6): e20182894.
RAYMOND SL, et al. Immunological Defects in Neonatal Sepsis and Potential Therapeutic Approaches. Front Pediatr., 2017; 5: 14.
REYNA MA, et al. Early prediction of sepsis from clinical data: The PhysioNet/Computing in cardiology challenge 2019. Crit. Care Med., 2019; 210-17.
RUSSELL N, et al. Early-versus late-onset sepsis in neonates - time to shift the paradigm? Clin Microbiol Infect., 2024; 30(1): 38-43.
SCHOBER P, et al. Logistic Regression in Medical Research. Anesth Analg., 2021; 132(2): 365–366.
SAHU P, et al. Prediction modelling in the early detection of neonatal sepsis. World J. Pediatr., 2022; 18: 160-75.
SHANE AL, et al. Neonatal sepsis. Lancet, 2017; 390(10104): 1770-80.
SOUZA MT, et al. Integrative review: what is it? How to do it? Einstein, 2010; 8(1): 102-6.
SOKOU R, et al. Development and validation of a sepsis diagnostic scoring model for neonates with suspected sepsis. Front Pediatr., 2022; 10: 1004727.
STILLWELL S, et al. Evidence– based practice: step by step. Am J Nurs, 2010; 110(5): 41-7.
TANERI PE, et al. Outcomes of interventions in neonatal sepsis: A systematic review of qualitative research. Int J Gynaecol Obstet., 2024.
VERSTRAETE EH, et al. Prediction models for neonatal health care-associated sepsis: A meta-analysis. Pediatrics, 2015; 135: e1002–e1014.
WYNN JL. Defining neonatal sepsis. Curr Opin Pediatr., 2016; 28(2): 135-40.
