摘要：Extensive monitoring in intensive care units (ICUs) generates large quantities of data which contain numerous trends that are difficult for clinicians to systematically evaluate. Current approaches to such heterogeneity in electronic health records (EHRs) discard pertinent information. We present a deep learning pipeline that uses all uncurated chart, lab, and output events for prediction of in-hospital mortality without variable selection. Over 21,000 ICU patients and tens of thousands of variables derived from the MIMIC-III database were used to train and validate our model. Recordings in the first few hours of a patient’s stay were found to be strongly predictive of mortality, outperforming models using SAPS II and OASIS scores, AUROC 0.72 and 0.76 at 24 h respectively, within just 12 h of ICU admission. Our model achieves a very strong predictive performance of AUROC 0.85 (95% CI 0.83–0.86) after 48 h. Predictive performance increases over the first 48 h, but suffers from diminishing returns, providing rationale for time-limited trials of critical care and suggesting that the timing of decision making can be optimised and individualised.
其他摘要：Abstract Extensive monitoring in intensive care units (ICUs) generates large quantities of data which contain numerous trends that are difficult for clinicians to systematically evaluate. Current approaches to such heterogeneity in electronic health records (EHRs) discard pertinent information. We present a deep learning pipeline that uses all uncurated chart, lab, and output events for prediction of in-hospital mortality without variable selection. Over 21,000 ICU patients and tens of thousands of variables derived from the MIMIC-III database were used to train and validate our model. Recordings in the first few hours of a patient’s stay were found to be strongly predictive of mortality, outperforming models using SAPS II and OASIS scores, AUROC 0.72 and 0.76 at 24 h respectively, within just 12 h of ICU admission. Our model achieves a very strong predictive performance of AUROC 0.85 (95% CI 0.83–0.86) after 48 h. Predictive performance increases over the first 48 h, but suffers from diminishing returns, providing rationale for time-limited trials of critical care and suggesting that the timing of decision making can be optimised and individualised.
