Artificial intelligence technologies in ultrasound-based monitoring of labour progress: a scoping review

Background/Aims Artificial intelligence can be used in birth monitoring, where advanced algorithms can predict outcomes, detect preterm birth risks and identify pregnancy complications. This review aimed to map the existing evidence on the use of artificial intelligence in ultrasound-based monitoring of labour progress. Methods Five databases were systematically searched: Cochrane Review Library, CINAHL, Medline, EMBASE, Scopus and Web of Science. Primary studies published between 2000 and 2025 that explored using artificial intelligence for ultrasound, vaginal examination or to estimate the progress of labour were included. Results A total of 14 articles were included, involving 145 085 women and labour/birth records. Key areas where artificial intelligence was used included automated fetal head position assessment, segmentation of anatomical structures and predicting dystocia and mode of birth. Challenges remained in validation, standardisation, regulatory approval and integration to clinical workflows. Conclusions Integrating artificial intelligence into vaginal examinations and labour monitoring could enhance safety, accuracy, and efficiency. Implications for practice Further validation with larger datasets and live patient studies is recommended before widespread clinical implementation.