A Knowledge Distillation Ensemble Framework for Predicting Short and Long-term Hospitalisation Outcomes from Electronic Health Records Data
This research provides a robust and scalable machine learning framework for clinicians to accurately predict adverse hospitalisation outcomes, enabling proactive decision-making and resource management for patients.
This paper addresses the challenge of predicting patient mortality and ICU admission from electronic health records, which often suffer from low recall for infrequent positive outcomes. The proposed framework, utilizing an unsupervised LSTM Autoencoder and a gradient boosting model, achieved PR-AUC scores of 0.891 for mortality prediction and 0.908 for ICU admission, outperforming existing models.
The ability to perform accurate prognosis of patients is crucial for proactive clinical decision making, informed resource management and personalised care. Existing outcome prediction models suffer from a low recall of infrequent positive outcomes. We present a highly-scalable and robust machine learning framework to automatically predict adversity represented by mortality and ICU admission from time-series vital signs and laboratory results obtained within the first 24 hours of hospital admission. The stacked platform comprises two components: a) an unsupervised LSTM Autoencoder that learns an optimal representation of the time-series, using it to differentiate the less frequent patterns which conclude with an adverse event from the majority patterns that do not, and b) a gradient boosting model, which relies on the constructed representation to refine prediction, incorporating static features of demographics, admission details and clinical summaries. The model is used to assess a patient's risk of adversity over time and provides visual justifications of its prediction based on the patient's static features and dynamic signals. Results of three case studies for predicting mortality and ICU admission show that the model outperforms all existing outcome prediction models, achieving PR-AUC of 0.891 (95$%$ CI: 0.878 - 0.969) in predicting mortality in ICU and general ward settings and 0.908 (95$%$ CI: 0.870-0.935) in predicting ICU admission.