Key points are not available for this paper at this time.
Clinical text in electronic health records (EHR) holds vital cues into a patient's journey, often absent in structured EHR data. Evidence-based healthcare decisions demand accurate extraction and modeling of these cues. The goal of our study is to predict Type-II Diabetes by utilizing concept-based models of visit sequences from longitudinal EHR data. We undertake the challenging task of fine-grained temporal information extraction from clinical text using a recent span-based approach with pre-trained transformers. We achieve a new state-of-the-art in end-to-end relation extraction from 2012 clinical temporal relations corpus. We propose to apply our model to a new dataset and extract patient-centric temporal knowledge graphs from their visits-fusing temporal orderings within documents and across visits. Beyond the current focus of our work on Type-II Diabetes risk prediction from EHR, our versatile framework can be extended to other domains including web-based healthcare systems for personalized medicine. It can not only model health outcomes having long progression timelines but also various socio-economic outcomes such as conflict, natural disasters, and financial markets by leveraging news, reports, and social-media text for extracting and modeling irregular time-series and help inform a variety of web-based applications and policies.
Rochana Chaturvedi (Sun,) studied this question.