Skip to content
Review Open access

ARTIFICIAL INTELLIGENCE IN FETAL MEDICINE: APPLICATIONS IN DIAGNOSIS AND GESTATIONAL RISK PREDICTION

Nov 2026 · Revista de Estudos Interdisciplinares · 0 citations · 1 references

Abstract

The incorporation of artificial intelligence into obstetric care has expanded the possibilities for image processing, pattern recognition, and integrated analysis of clinical information, with particularly relevant applications in fetal medicine. Machine learning and deep learning algorithms have been investigated for automating ultrasonographic measurements, identifying anatomical structures, detecting fetal anomalies, and estimating the risk of gestational complications. In this context, the ability to analyze large volumes of data and identify complex relationships may complement traditional methods of maternal-fetal assessment and contribute to greater precision and earlier stratification of risk. This review aimed to analyze the main applications of artificial intelligence in fetal medicine, with emphasis on image-based diagnosis and the prediction of adverse gestational outcomes. This is a narrative literature review, guided by a structured question based on the PICo strategy and directed at studies on artificial intelligence, machine learning, fetal ultrasound, and predictive models applied to pregnancy. The evidence points to applications in the automated identification of ultrasonographic planes, fetal biometry, assessment of anatomical structures, and recognition of cardiac and other organ abnormalities, in addition to the development of models to estimate the risk of preeclampsia, preterm birth, fetal growth restriction, and other adverse outcomes. Despite promising results, limitations related to the quality and representativeness of datasets, external validation, algorithm interpretability, biases, and integration into clinical workflows remain relevant. It is concluded that artificial intelligence has the potential to complement assessment in fetal medicine, but its safe incorporation depends on robust clinical validation, professional supervision, and demonstration of benefit in real-world care settings.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.