Key result
A deep recurrent neural network model for predicting transfer to ICU or death showed very poor performance (AUPRC 0.042; 95% CI 0.04-0.043), comparable to logistic regression and early warning scores.
Why the study?
Existing early warning scores show only moderate performance and are often evaluated using aggregated measures over time rather than pragmatic evaluations assessing multiple predictions per patient-day.
Does a deep recurrent neural network model improve the real-time prediction of clinical deterioration (transfer to ICU or death) in inpatient adults compared to standard early warning scores?
Cohort (n=146,446)
Yes
Does a deep recurrent neural network model improve the real-time prediction of clinical deterioration (transfer to ICU or death) in inpatient adults compared to standard early warning scores?
Commonly used early warning scores and deep learning models show very poor performance for real-time prediction of clinical deterioration in ward patients when assessed using simulated prospective validation.
Deep learning models add no predictive value over early warning scores for ward deterioration; leaves open development of superior real-time tools.
No abstract yet. The journal hasn't published one we can show.
No takes yet. Share an insight, caveat, or question.
Shah et al. (2021) conducted a cohort in Clinical deterioration (n=146,446). Deep recurrent neural network deterioration model vs. Logistic regression model, NEWS, MEWS, and qSOFA was evaluated on 24-hour composite outcome of transfer to ICU or death (AUPRC 0.042, 95% CI 0.04-0.043). A deep recurrent neural network model for predicting transfer to ICU or death showed very poor performance (AUPRC 0.042; 95% CI 0.04-0.043), comparable to logistic regression and early warning scores.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: