Integrating the interpretable machine learning Score For Emergency Risk Prediction (SERP) with emergency department triage to better predict 30-Day mortality

OBJECTIVE: This study integrates a machine learning (ML) based Score for Emergency Risk Prediction (SERP), developed using objective mortality endpoints with the Patient Acuity Category Scale (PACS) and evaluated its effectiveness in clinical use. METHODS: This single-centre, retrospective cohort study included all ED patients from a large tertiary hospital between 1 January 2018 and 31 December 2019. Using a reclassification framework, SERP was incorporated into PACS to derive two enhanced triage models. PACS+ model 1 downtriaged patients with low predicted 30-day mortality risk and up-triaged those with high risk. PACS+ model 2 up-triaged only high-risk patients, while low-risk patients retained their original category. Predictive performance in the test cohort was assessed using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). RESULTS: The derivation cohort included 97,188 ED visits, and test cohort included 97,212 ED visits. In the derivation set, the mean (SD) age of patients was 58.97 (18.41) years old and 47,993 (49.4%) were females. Of all patients, 19.9%, 57.5%, 22.5%, and 0.2% were triaged to PACS categories 1-4 respectively. The 30-day mortality rate in the derivation set was 2.8% and 2.7% in the validation cohort. For 30-day mortality prediction, PACS+ model 1 (AUC 0.828 [95% CI 0.820-0.836]) and PACS+ model 2 (AUC 0.812 [95% CI 0.805-0.818]) outperformed PACS (AUC 0.722 [95% CI 0.714-0.729]). PACS+ model 1 consistently achieved greater net benefit across the range of clinical thresholds. CONCLUSION: Integrating ML-based SERP with PACS improved 30-day mortality prediction in ED triage.