Objective This work explores the perceptions of obstetric clinicians about Artificial Intelligence (AI) in order to bridge the gap in uptake of AI between research and medical practice. Identifying potential areas where AI can contribute to clinical practice, enables AI research to align with the needs of clinicians and ultimately patients. Design Qualitative interview study. Setting A national study conducted in the Netherlands. Sample Dutch clinicians working in obstetrics with varying relevant work experience, gender, and age. Methods Thematic analysis of qualitative interview transcripts. Results Thirteen gynaecologists were interviewed about hypothetical scenarios of an implemented AI model. Thematic analysis identified two major themes: perceived usefulness and trust. Usefulness involved AI extending human brain capacity in complex pattern recognition and information processing, reducing contextual influence, and saving time. Trust required validation, explainability and successful personal experience. This result shows two paradoxes: firstly, AI is expected to provide added value by surpassing human capabilities, yet also a need to understand the parameters and their influence on predictions for trust and adoption was expressed. Secondly, participants recognised the value of incorporating numerous parameters into a model, but they also believed that certain contextual factors should only be considered by humans, as it would be undesirable for AI models to utilize that information. Conclusions Obstetricians’ opinions on the potential value of AI highlight the need for clinician-AI researcher collaboration. Trust can be built through conventional means like RCTs and guidelines. Holistic impact metrics, such as changes in workflow, not just clinical outcomes, should guide AI model development. Further research is needed for evaluating evolving AI systems beyond traditional validation methods.

Objective: To calculate maternal mortality ratio (MMR) for 2006-2018 in the Netherlands and compare with 1993-2005. Describe women’s and obstetric characteristics, causes of death and improvable factors. Design: Prospective cohort study. Setting: Nationwide. Population: 2,304,271 livebirths. Methods: Analysis of all maternal deaths between January 1st, 2006, and December, 31st, 2018 as reported to and audited by the national Audit Committee Maternal Mortality and Morbidity. Main outcome measures: MMR, causes of death, improvable factors. Results: Overall MMR was 6.2 per 100,000 livebirths, a decrease from 12.1 in 1993-2005 (Odds Ratio (OR) 0.5, 95%CI 0.4-0.6). Women with non-Western ethnic background had a slightly increased MMR compared to Dutch women (MMR 6.5 vs 5.0, OR 1.3, 95%CI 0.9-1.9), and was particularly increased among women with a background from Surinam/Dutch Antilles (MMR 14.7 OR 2.9, 95%CI 1.6 – 5.3). Half of all women had an uncomplicated medical history (79/161, 49.1%). Of 172 pregnancy-related deaths within one year postpartum, 103 (60%) had a direct and 69 (40%) an indirect cause. Leading causes within 42 days postpartum were cardiac disease (n=21, 14.8%), hypertensive disorders (n=20, 14.1%) and thrombosis (n=19, 13.4%). For deaths up to one year postpartum, suicide was the third commonest cause (n=20, 11.6%). Improvable factors in care were identified in 76 (47.5%) of all deaths. Conclusions: Maternal mortality halved in 2006-2018 compared to 1993-2005. Unlike before, cardiac disease outnumbered hypertensive disorders as main cause of death. Women with a background from Surinam/Dutch Antilles had a threefold higher risk of death compared to Dutch women.