An efficient representation of chronological events in medical texts
This work addresses the challenge of extracting sequential patterns from medical texts for practitioners, though it appears incremental as it applies an existing mathematical framework to a specific domain.
The authors tackled the problem of capturing sequential information in longitudinal electronic health records (EHRs) by proposing a path signature framework for representing chronological events in clinical notes, resulting in a 15.4% increase in risk prediction AUC for Alzheimer's disease survival compared to a baseline model.
In this work we addressed the problem of capturing sequential information contained in longitudinal electronic health records (EHRs). Clinical notes, which is a particular type of EHR data, are a rich source of information and practitioners often develop clever solutions how to maximise the sequential information contained in free-texts. We proposed a systematic methodology for learning from chronological events available in clinical notes. The proposed methodological {\it path signature} framework creates a non-parametric hierarchical representation of sequential events of any type and can be used as features for downstream statistical learning tasks. The methodology was developed and externally validated using the largest in the UK secondary care mental health EHR data on a specific task of predicting survival risk of patients diagnosed with Alzheimer's disease. The signature-based model was compared to a common survival random forest model. Our results showed a 15.4$\%$ increase of risk prediction AUC at the time point of 20 months after the first admission to a specialist memory clinic and the signature method outperformed the baseline mixed-effects model by 13.2 $\%$.