| Autor: |
Jawad BN; Department of Clinical Research, Copenhagen University Hospital Amager and Hvidovre, 2650 Hvidovre, Denmark.; Department of Clinical Medicine, University of Copenhagen, 2200 Copenhagen, Denmark., Altintas I; Department of Clinical Research, Copenhagen University Hospital Amager and Hvidovre, 2650 Hvidovre, Denmark.; Department of Clinical Medicine, University of Copenhagen, 2200 Copenhagen, Denmark.; Emergency Department, Copenhagen University Hospital Amager and Hvidovre, 2650 Hvidovre, Denmark., Eugen-Olsen J; Department of Clinical Research, Copenhagen University Hospital Amager and Hvidovre, 2650 Hvidovre, Denmark., Niazi S; Department of Cardiology, North Zealand Hospital, 3400 Hillerød, Denmark., Mansouri A; Emergency Medical Services, Capital Region, 2750 Ballerup, Denmark., Rasmussen LJH; Department of Clinical Research, Copenhagen University Hospital Amager and Hvidovre, 2650 Hvidovre, Denmark., Schultz M; Department of Geriatrics, Copenhagen University Hospital Amager and Hvidovre, 2650 Hvidovre, Denmark., Iversen K; Department of Clinical Medicine, University of Copenhagen, 2200 Copenhagen, Denmark.; Department of Emergency Medicine, Copenhagen University Hospital Herlev and Gentofte, 2730 Herlev, Denmark.; Department of Cardiology, Copenhagen University Hospital Herlev and Gentofte, 2730 Herlev, Denmark., Normann Holm N; Department of Clinical Research, Copenhagen University Hospital Amager and Hvidovre, 2650 Hvidovre, Denmark.; Department of Applied Mathematics and Computer Science, Technical University of Denmark, 2800 Kongens Lyngby, Denmark., Kallemose T; Department of Clinical Research, Copenhagen University Hospital Amager and Hvidovre, 2650 Hvidovre, Denmark., Andersen O; Department of Clinical Research, Copenhagen University Hospital Amager and Hvidovre, 2650 Hvidovre, Denmark.; Department of Clinical Medicine, University of Copenhagen, 2200 Copenhagen, Denmark.; Emergency Department, Copenhagen University Hospital Amager and Hvidovre, 2650 Hvidovre, Denmark., Nehlin JO; Department of Clinical Research, Copenhagen University Hospital Amager and Hvidovre, 2650 Hvidovre, Denmark. |
| Abstrakt: |
Background : Predicting mortality in emergency departments (EDs) using machine learning models presents challenges, particularly in balancing simplicity with performance. This study aims to develop models that are both simple and effective for predicting short- and long-term mortality in ED patients. Our approach uses a minimal set of variables derived from one single blood sample obtained at admission. Methods : Data from three cohorts at two large Danish university hospitals were analyzed, including one retrospective and two prospective cohorts where prognostic models were applied to predict individual mortality risk, spanning the years 2013-2022. Routine biochemistry analyzed in blood samples collected at admission was the primary data source for the prediction models. The outcomes were mortality at 10, 30, 90, and 365 days after admission to the ED. The models were developed using Light Gradient Boosting Machines. The evaluation of mortality predictions involved metrics such as Area Under the Receiver Operating Characteristic Curve (AUC), sensitivity, specificity, negative predictive values, positive predictive values, and Matthews correlation coefficient (MCC). Results : A total of 43,648 unique patients with 65,484 admissions were analyzed. The models showed high accuracy, with very good to excellent AUC values between 0.87 and 0.93 across different time intervals. Conclusions : This study demonstrates that a single assessment of routine clinical biochemistry upon admission can serve as a powerful predictor for both short-term and long-term mortality in ED admissions. |
