Learning Predictive Models from Electronic Health Records

University dissertation from Stockholm : Department of Computer and Systems Sciences, Stockholm University

Abstract: The ongoing digitization of healthcare, which has been much accelerated by the widespread adoption of electronic health records, generates unprecedented amounts of clinical data in a readily computable form. This, in turn, affords great opportunities for making meaningful secondary use of clinical data in the endeavor to improve healthcare, as well as to support epidemiology and medical research. To that end, there is a need for techniques capable of effectively and efficiently analyzing large amounts of clinical data. While machine learning provides the necessary tools, learning effective predictive models from electronic health records comes with many challenges due to the complexity of the data. Electronic health records contain heterogeneous and longitudinal data that jointly provides a rich perspective of patient trajectories in the healthcare process. The diverse characteristics of the data need to be properly accounted for when learning predictive models from clinical data. However, how best to represent healthcare data for predictive modeling has been insufficiently studied. This thesis addresses several of the technical challenges involved in learning effective predictive models from electronic health records.Methods are developed to address the challenges of (i) representing heterogeneous types of data, (ii) leveraging the concept hierarchy of clinical codes, and (iii) modeling the temporality of clinical events. The proposed methods are evaluated empirically in the context of detecting adverse drug events in electronic health records. Various representations of each type of data that account for its unique characteristics are investigated and it is shown that combining multiple representations yields improved predictive performance. It is also demonstrated how the information embedded in the concept hierarchy of clinical codes can be exploited, both for creating enriched feature spaces and for decomposing the predictive task. Moreover, incorporating temporal information leads to more effective predictive models by distinguishing between event occurrences in the patient history. Both single-point representations, using pre-assigned or learned temporal weights, and multivariate time series representations are shown to be more informative than representations in which temporality is ignored. Effective methods for representing heterogeneous and longitudinal data are key for enhancing and truly enabling meaningful secondary use of electronic health records through large-scale analysis of clinical data.