Using Machine Learning to Model Older Adult Inpatient Trajectories From Electronic Health Records Data

Electronic Health Records (EHR) data can provide novel insights into inpatient trajectories. Blood tests and vital signs from de-identified patients' hospital admission episodes (AE) were represented as multivariate time-series (MVTS) to train unsupervised Hidden Markov Models (HMM) and represent each AE day as one of 17 states. All HMM states were clinically interpreted based on their patterns of MVTS variables and relationships with clinical information. Visualization differentiated patients progressing toward stable 'discharge-like' states versus those remaining at risk of inpatient mortality (IM). Chi-square tests confirmed these relationships (two states associated with IM; 12 states with ≥1 diagnosis). Logistic Regression and Random Forest (RF) models trained with MVTS data rather than states had higher prediction performances of IM, but results were comparable (best RF model AUC-ROC: MVTS data = 0.85; HMM states = 0.79). ML models extracted clinically interpretable signals from hospital data. The potential of ML to develop decision-support tools for EHR systems warrants investigation.
This research was supported by the NIHR Cambridge Biomedical Research Centre (BRC-1215-20014). VLK was funded by a MRC/NIHR Clinical Academic Research Partnership Grant (CARP; grant code: MR/T023902/1). VT is supported by Cancer Research UK. EB and TF were funded by the EMBL European Bioinformatics Institute (EMBL-EBI).