sing Machine Learning to Predict Complications in Pregnancy: A Systematic Revie

Autor(es)

Bertini, Ayleen ^{[1, 2]} ; Salas, Rodrigo ^{[3, 4]} ; Chabert, Steren ^{[3, 4, 5]} ; Sobrevia, Luis ^{[6, 7, 8, 9, 10, 11]} ; Pardo, Fabian ^{[1, 7, 12]}

Afiliação do(s) autor(es):Mostrar menos -

^[1] Univ Valparaiso, Metabol Dis Res Lab MDRL, Interdisciplinary Ctr Res Terr Hlth Aconcagua Val, Ctr Biomed Res CIB, Valparaiso - Chile

^[2] Univ Valparaiso, Fac Med, PhD Program Doctorado Ciencias & Ingn La Salud, Valparaiso - Chile

^[3] Univ Valparaiso, Fac Engn, Sch Biomed Engn, Valparaiso - Chile

^[4] Univ Valparaiso, Ctr Invest & Desarrollo Ingn Salud CINGS, Valparaiso - Chile

^[5] Inst Milenio Intelligent Healthcare Engn, Valparaiso - Chile

^[6] Univ Groningen, Univ Med Ctr Groningen, Dept Pathol & Med Biol, Groningen - Netherlands

^[7] Pontificia Univ Catolica Chile, Div Obstet & Gynaecol, Sch Med, Fac Med, Cellular & Mol Physiol Lab CMPL, Santiago - Chile

^[8] Univ Seville, Dept Physiol, Fac Pharm, Seville - Spain

^[9] Univ Queensland, Fac Med & Biomed Sci, Ctr Clin Res UQCCR, Herston, Qld - Australia

^[10] Sao Paulo State Univ UNESP, Fac Med, Med Sch, Sao Paulo - Brazil

^[11] Tecnol Monterrey, Eutra, Inst Obes Res, Sch Med & Hlth Sci, Monterrey - Mexico

^[12] Univ Valparaiso, Sch Med, Fac Med, Campus San Felipe, San Felipe - Chile

• Tipo de documento: Artigo de Revisão
• Fonte: FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY; v. 9, JAN 19 2022.
• Citações Web of Science: 0

Resumo

Introduction: Artificial intelligence is widely used in medical field, and machine learning has been increasingly used in health care, prediction, and diagnosis and as a method of determining priority. Machine learning methods have been features of several tools in the fields of obstetrics and childcare. This present review aims to summarize the machine learning techniques to predict perinatal complications.Objective: To identify the applicability and performance of machine learning methods used to identify pregnancy complications.Methods: A total of 98 articles were obtained with the keywords ``machine learning,{''} ``deep learning,{''} ``artificial intelligence,{''} and accordingly as they related to perinatal complications ({''}complications in pregnancy,{''} ``pregnancy complications{''}) from three scientific databases: PubMed, Scopus, and Web of Science. These were managed on the Mendeley platform and classified using the PRISMA method.Results: A total of 31 articles were selected after elimination according to inclusion and exclusion criteria. The features used to predict perinatal complications were primarily electronic medical records (48%), medical images (29%), and biological markers (19%), while 4% were based on other types of features, such as sensors and fetal heart rate. The main perinatal complications considered in the application of machine learning thus far are pre-eclampsia and prematurity. In the 31 studies, a total of sixteen complications were predicted. The main precision metric used is the AUC. The machine learning methods with the best results were the prediction of prematurity from medical images using the support vector machine technique, with an accuracy of 95.7%, and the prediction of neonatal mortality with the XGBoost technique, with 99.7% accuracy.Conclusion: It is important to continue promoting this area of research and promote solutions with multicenter clinical applicability through machine learning to reduce perinatal complications. This systematic review contributes significantly to the specialized literature on artificial intelligence and women's health. (AU)

• Processo FAPESP: 16/01743-5 - Coorte da tríade gestacional: hiperglicemia, incontinência urinária e perfil clínico, molecular e ômico da miopatia hiperglicêmica na predição de incontinência e disfunção muscular e pesquisa translacional com biodevice para regeneração muscular em ratas
• Beneficiário: Marilza Vieira Cunha Rudge
• Modalidade de apoio: Auxílio à Pesquisa - Temático