Journal
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
Volume 26, Issue 1, Pages 423-435Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JBHI.2021.3089287
Keywords
Predictive models; Physiology; Biological system modeling; Hospitals; Oxygen; Data models; Tools; Ensemble Learning; Gradient Boost; Imbalanced time-series; Long Short Term Memory networks (LSTM); Clinical Outcome Prediction; Outlier Detection; Machine Learning; Mortality Prediction; Stacked Ensemble
Categories
Funding
- NIHR Biomedical Research Centre at SLaM
- Kings College London, London, U.K
- NIHR University College London Hospitals Biomedical Research Centre
- Health Data Research (HDR), U.K
- BigData@Heart Consortium [116074]
- UKRI Innovation Fellowship, Health Data Research U.K [MR/S00310X/1]
- HDR U.K [MR/S004149/1]
- Wellcome Institutional Translation Partnership Award [PIII054]
- King's Medical Research Trust studentship
- London AI Medical Imaging Centre for Value-Based Healthcare (AI4VBH)
- NIHR Applied Research Collaboration South London at King's College Hospital NHS Foundation Trust
- MRC
- MRC [MR/S00310X/1] Funding Source: UKRI
Ask authors/readers for more resources
Accurate prognosis is crucial for clinical decision making, resource management, and personalized care. This study introduces a highly-scalable and robust machine learning framework for automatically predicting adverse events during hospital admission using time-series data of vital signs and laboratory results. The model outperforms existing platforms in both ICU and general ward settings, achieving high precision and recall rates.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available