Predicting common maternal postpartum complications: leveraging health administrative data and machine learning

Objective We aimed to predict the risk of common maternal postpartum complications requiring an inpatient episode of care. Design and setting Maternal data from the beginning of gestation up to and including the delivery, and neonatal data recorded at delivery, were used to predict postpartum complications. Sample Administrative health data of all inpatient live births (n = 422 509) in the Australian state of Queensland between January 2009 and October 2015. Method Gradient boosted trees were used with five-fold cross-validation to compare model performance. The best performing models for each outcome were then assessed in the independent validation data using the area under the receiver operating curve (AUC-ROC). Main outcome measure Postpartum complications occurring in the first 12 weeks after delivery requiring hospital admission. Results Postpartum hypertensive disorders obtained good discrimination in the independent validation data (AUC = 0.879, 95% CI 0.846-0.912), as did obstetric surgical wound infection (AUC = 0.856, 95% CI 0.838-0.873), whereas postpartum sepsis and haemorrhage obtained poor discrimination. Conclusions Our study suggests that routinely collected health data have the potential to play an important role in helping determine women's risk of common postpartum complications leading to hospital admission. This information can be presented to clinical staff after delivery to help guide immediate postpartum care, delayed discharge, and post-discharge patient follow up. For such a system to be effective and valued, it must produce accurate predictions, and our findings suggest areas where routine data collection could be strengthened to this end. Tweetable abstract Improved prediction of maternal postnatal hypertensive disorders and wound infection via machine learning.