Computerized predictive models in hospital settings for detecting severe maternal complications: a systematic review protocol

Read full text Summarise with VIRAT
Authors: Graziele Telles Vieira, Stefhanie Conceição de Jesus, Fiona Ann Lynn, Tifany Colomé Leal, Laís Antunes Wilhelm, Maria de Lourdes de Souza
Cited by: 0
References: 8

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

CONTEXT: Maternal mortality remains a public health problem, especially in low- and middle-income countries. Complications such as hypertension, gestational diabetes, pre-eclampsia, postpartum hemorrhage, and infections are among the main causes of preventable deaths. In this scenario, computerized predictive models have emerged as tools for the early identification of risks and the prevention of serious complications associated with maternal death in hospital care. Therefore, this systematic review is designed to assess the available evidence on the effectiveness of these models when applied in intra-hospital environments in relation to adverse outcomes associated with maternal mortality. METHODOLOGY: The review will be conducted following established methodological guidance and reported in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols (PRISMA-P). Randomized and non-randomized studies will be included, identified through systematic searches in nine data sources: Base de Dados de Enfermagem, Cumulative Index to Nursing and Allied Health Literature, The Cochrane Library, Excerpta Medica Database, Latin American and Caribbean Health Sciences Literature, Medical Literature Analysis and Retrieval System Online via Public Medline, Scientific Electronic Library Online, Scopus - Abstract and Citation Database, and Web of Science. Studies in Portuguese, English, and Spanish will be included, without restrictions in terms of publication date. Data selection and extraction will be conducted independently by two researchers, with disagreements resolved by a third. Methodological quality will be assessed using the GRADE and ROBINS-I tools. The synthesis will be narrative according to the SWiM guidelines, with the possibility of carrying out a meta-analysis, if feasible. DISCUSSION: The results aim to expand knowledge about the use of predictive technologies in maternal health, offering support for clinical decisions, educational strategies, and health service planning in hospital settings. SYSTEMATIC REVIEW REGISTRATION: PROSPERO CRD42024573613.

Fields of Study & Subjects

Artificial Intelligence in Healthcare Maternal and fetal healthcare Maternal and Neonatal Healthcare

Publication details

Journal / source
Systematic Reviews
Volume
15
Issue
1
Publication date
29 March 2026
Language
EN