Explainable Machine Learning Models for Rapid Risk Stratification in the Emergency Department: A Multicenter Study
The Journal of Applied Laboratory Medicine · 01.03.2024 · 9 (2) · 212-222
DOI: 10.1093/jalm/jfad094 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift The Journal of Applied Laboratory Medicine, online erschienen am 15.12.2023. Verfasst von William P T M van Doorn und 6 weiteren Autor:innen. Beteiligte Einrichtung: Central Diagnostic Laboratory, Department of Clinical Chemistry, Maastricht University Medical Center, Maastricht, the Netherlands. Hauptthemen laut MEDLINE: Academic Medical Centers, Algorithms. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Noyons Stipendium from the Dutch Federation of Clinical Chemistry.
Abstract (Originalsprache)
Background
Risk stratification of patients presenting to the emergency department (ED) is important for appropriate triage. Diagnostic laboratory tests are an essential part of the workup and risk stratification of these patients. Using machine learning, the prognostic power and clinical value of these tests can be amplified greatly. In this study, we applied machine learning to develop an accurate and explainable clinical decision support tool model that predicts the likelihood of 31-day mortality in ED patients (the RISKINDEX). This tool was developed and evaluated in four Dutch hospitals.
Methods
Machine learning models included patient characteristics and available laboratory data collected within the first 2 h after ED presentation, and were trained using 5 years of data from consecutive ED patients from the Maastricht University Medical Center (Maastricht), Meander Medical Center (Amersfoort), and Zuyderland Medical Center (Sittard and Heerlen). A sixth year of data was used to evaluate the models using area under the receiver-operating-characteristic curve (AUROC) and calibration curves. The Shapley additive explanations (SHAP) algorithm was used to obtain explainable machine learning models.
Results
The present study included 266 327 patients with 7.1 million laboratory results available. Models show high diagnostic performance with AUROCs of 0.94, 0.98, 0.88, and 0.90 for Maastricht, Amersfoort, Sittard and Heerlen, respectively. The SHAP algorithm was utilized to visualize patient characteristics and laboratory data patterns that underlie individual RISKINDEX predictions.
Conclusions
Our clinical decision support tool has excellent diagnostic performance in predicting 31-day mortality in ED patients. Follow-up studies will assess whether implementation of these algorithms can improve clinically relevant end points.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Central Diagnostic Laboratory, Department of Clinical Chemistry, Maastricht University Medical Center, Maastricht, the Netherlands.
- CARIM School for Cardiovascular Diseases, Maastricht University, Maastricht, the Netherlands.
- Department of Clinical Chemistry & Hematology, Zuyderland Medical Center, Heerlen, the Netherlands.
- Department of Internal Medicine, Division of General Internal Medicine, Section Acute Medicine, Maastricht University Medical Center, Maastricht University, Maastricht, the Netherlands.
- Laboratory of Clinical Chemistry, Meander Medical Center, Amersfoort, the Netherlands.
- CAPHRI School for Care and Public Health Research Institute, Maastricht University, Maastricht, the Netherlands.
Förderung
- Noyons Stipendium from the Dutch Federation of Clinical Chemistry
Zitieren
APA
van Doorn, W. P. T. M., Helmich, F., van Dam, P. M. E. L., Jacobs, L. H. J., Stassen, P. M., Bekers, O., & Meex, S. J. R. (2024). Explainable Machine Learning Models for Rapid Risk Stratification in the Emergency Department: A Multicenter Study. The Journal of Applied Laboratory Medicine, 9(2), 212-222. https://doi.org/10.1093/jalm/jfad094
Vancouver
van Doorn WPTM, Helmich F, van Dam PMEL, Jacobs LHJ, Stassen PM, Bekers O, et al. Explainable Machine Learning Models for Rapid Risk Stratification in the Emergency Department: A Multicenter Study. The Journal of Applied Laboratory Medicine. 2024;9(2):212-222. doi:10.1093/jalm/jfad094
BibTeX
@article{vanDoorn2024,
author = {van Doorn, William P T M and Helmich, Floris and van Dam, Paul M E L and Jacobs, Leo H J and Stassen, Patricia M and Bekers, Otto and Meex, Steven J R},
title = {Explainable Machine Learning Models for Rapid Risk Stratification in the Emergency Department: A Multicenter Study},
journal = {The Journal of Applied Laboratory Medicine},
year = {2024},
volume = {9},
number = {2},
pages = {212--222},
doi = {10.1093/jalm/jfad094}
}
EUVIMED