A Knowledge Distillation Ensemble Framework for Predicting Short- and Long-Term Hospitalization Outcomes from Electronic Health Records Data

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

The ability to perform accurate prognosis 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 and readmission from time-series of vital signs and laboratory results obtained within the first 24 hours of hospital admission. The stacked ensemble 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 by incorporating static features. The model is used to assess a patient's risk of adversity and provides visual justifications of its prediction. Results of three case studies show that the model outperforms existing platforms in ICU and general ward settings, achieving average Precision-Recall Areas Under the Curve (PR-AUCs) of 0.891 (95% CI: 0.878-0.939) for mortality and 0.908 (95% CI: 0.870-0.935) in predicting ICU admission and readmission.

Original languageEnglish
Pages (from-to)423-435
Number of pages13
JournalIEEE Journal of Biomedical and Health Informatics
Volume26
Issue number1
DOIs
Publication statusPublished - Jan 2022

Keywords

  • Biological system modeling
  • Clinical Outcome Prediction
  • Data models
  • Ensemble Learning
  • Gradient Boost
  • Hospitals
  • Imbalanced time-series
  • Long Short Term Memory networks (LSTM)
  • Machine Learning
  • Mortality Prediction
  • Outlier Detection
  • Oxygen
  • Physiology
  • Predictive models
  • Stacked Ensemble
  • Tools

Fingerprint

Dive into the research topics of 'A Knowledge Distillation Ensemble Framework for Predicting Short- and Long-Term Hospitalization Outcomes from Electronic Health Records Data'. Together they form a unique fingerprint.

Cite this