Clinical information extraction for preterm birth risk prediction

This paper contributes to the pursuit of leveraging unstructured medical notes to structured clinical decision making. In particular, we present a pipeline for clinical information extraction from medical notes related to preterm birth, and discuss the main challenges as well as its potential for clinical practice. A large collection of medical notes, created by staff during hospitalizations of patients who were at risk of delivering preterm, was gathered and analyzed. Based on an annotated collection of notes, we trained and evaluated information extraction components to discover clinical entities such as symptoms, events, anatomical sites and procedures, as well as attributes linked to these clinical entities. In a retrospective study, we show that these are highly informative for clinical decision support models that are trained to predict whether delivery is likely to occur within specific time windows, in combination with structured information from electronic health records. [Display omitted] •Unstructured medical notes contain valuable information for decision support models for preterm birth risk prediction.•Open source software, biomedical ontologies and active learning enable fast development of customized clinical NLP models.•Features extracted using information extraction lead to more interpretable predictive models.•Information extraction is essential to foster trust from users of decision support models in high-stakes settings.