Purpose of Review
To discuss the methodological challenges in developing risk prediction models in perinatal epidemiology and barriers to their implementation in clinical practice.
Recent Findings
In perinatal epidemiology, risk prediction models have been created to examine the risk of adverse health outcomes in pregnancy, delivery, and post-partum periods. However, only a limited number of prediction models are being used to guide clinical decisions.
Summary
The accuracy and utility of prediction models for clinical decision making are contingent on the use of robust methods to develop risk prediction models and appropriate metrics to assess their performance and clinical impact. In order to increase the transportability (i.e., generalizability) of prediction models, careful consideration of the patient populations represented in the data used to develop and externally validate prediction models and the mechanism for data collection are needed. The era of big data provides researchers the opportunity to leverage existing databases, such as birth and pregnancy registries, through linkage to electronic health records, disease registries, and census data in order to enrich the breadth of clinical and sociodemographic information available for prediction modeling. However, these data sources introduce new challenges that require thorough assessment to evaluate their impact on the accuracy of resulting prediction models and their transportability to the general population.