Predictive Model for Late Stillbirth Among Antenatal Hypertensive Women

Daily huddles in antenatal clinics: An effective tool to optimize quality of antenatal care

Daily huddles are 15 golden minutes in antenatal clinics which can aid in the reduction of maternal and perinatal morbidity as well as mortality.

Machine Learning for Predicting Stillbirth: A Systematic Review

Stillbirth is a major global issue, with over 5 million cases each year. The multifactorial nature of stillbirth makes it difficult to predict. Artificial intelligence (AI) and machine learning (ML) have the potential to enhance clinical decision-making and enable precise assessments. This study reviewed the literature on predictive ML models for stillbirth highlighting input characteristics, performance metrics, and validation. The PubMed, Cochrane, and Web of Science databases were searched for studies using AI to develop predictive models for stillbirth. Findings were analyzed qualitatively using narrative synthesis and graphics. Risk of bias and the applicability of the studies were assessed using PROBAST. Model design and performance were discussed. Eight studies involving 14,840,654 women with gestational ages ranging from 20 weeks to full term were included in the qualitative analysis. Most studies used neural networks, random forests, and logistic regression algorithms. The number of predictive features varied from 14 to 53. Only 50% of studies validated the models. Cross-validation was commonly employed, and only 25% of studies performed external validation. All studies reported area under the curve as a performance metric (range 0.54-0.9), and five studies reported sensitivity (range, 60- 90%) and specificity (range, 64 - 93.3%). A stacked ensemble model that analyzed 53 features performed better than other models (AUC = 0.9; sensitivity and specificity > 85%). Available ML models can attain a considerable degree of accuracy for prediction of stillbirth; however, these models require further development before they can be applied in a clinical setting.

Prediction Models for Adverse Pregnancy Outcomes in India: Methodological Considerations for an Emerging Topic

Stillbirth is over-represented in lower and lower-middle-income countries and understandably this has motivated greater research investment in the development of prediction models. Prediction is particularly challenging for pregnancy outcomes because only part of the population is represented in observational research. Notably, unrecognised pregnancies and miscarriages are typically excluded from the development of prediction models and the consequences of such selection are not well understood. Other methodological challenges in developing stillbirth prediction models are within the control of the researcher. Identifying whether the intended model is for aetiological explanation versus prediction, attainment of a sufficiently large representative sample, and internal and external validation are among such methodological considerations. These considerations are discussed in relation to a recently published study on prediction of stillbirth after 28 weeks of pregnancy for women with hypertensive disorders of pregnancy in India. The predictive ability of this model amounts to the flip of a coin. Future screening based on such a model may be expensive, increase psychological distress among patients and introduce additional iatrogenic perinatal morbidities from over-treatment. Future research should address the methodological considerations described in this article.