Dynamic Prediction of Emergency Department Admissions Using Explainable Artificial Intelligence: A Large-Scale Temporal Validation Study
Dynamische Vorhersage von Notaufnahme-Aufnahmen mit Explainable Artificial Intelligence: eine groß angelegte temporale Validierungsstudie
Journal of Clinical Medicine · 07.11.2026 · 15 (21) · 8694
DOI: 10.3390/jcm15218694 ↗Auf einen Blick
In 387.407 Patient:innen-Kontakten sagte ein dynamisches Explainable Boosting Machine Krankenhausaufnahmen in der Notaufnahme voraus. Die Leistung verbesserte sich über 120 Minuten nur gering.
Fragestellung
Kann ein transparentes, dynamisches Machine-Learning-Modell Krankenhausaufnahmen in der Notaufnahme vorhersagen?
Methode
Retrospektive Kohortenstudie mit zeitlicher Validierung in MIMIC-IV-ED; Training 2008–2016, Test 2017–2019; Vergleich mit HGB und logistischer Regression.
Ergebnisse
Bei T = 0 lag die ROC-AUC bei 0,8048 (95 %-KI 0,800–0,806) und die PR-AUC bei 0,7395 (95 %-KI 0,732–0,742). Bei T = 120: ROC-AUC 0,8168 (95 %-KI 0,813–0,819), PR-AUC 0,7595 (95 %-KI 0,754–0,763), Sensitivität 80,74 %, Spezifität 65,09 %, PPV 61,16 %.
Einschränkungen
Prospektive Validierung vor klinischem Einsatz erforderlich.
Schlussfolgerung der Autor:innen
Durch die Modellierung früher Notaufnahme-Verläufe erreicht das EBM eine Diskrimination nahe an Black-Box-Ensemblemodellen bei voller Transparenz. Für den klinischen Einsatz ist laut Autor:innen eine prospektive Validierung nötig.
Kernaussagen
- EBM: ROC-AUC 0,8168 bei T = 120
- HGB etwas höher: ROC-AUC 0,8208
- Logistische Regression deutlich schwächer: ROC-AUC 0,7420
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Journal of Clinical Medicine, online erschienen am 07.11.2026. Verfasst von Furkan Şakiroğlu und 1 weiteren Autor:innen. Beteiligte Einrichtung: İbni Sina Family Health Center, Erzurum 25700, Türkiye. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
The clinical adoption of artificial intelligence in emergency departments (ED) is hindered by the “black-box” nature of complex models and retrospective data leakage from downstream laboratory results.
Aims
We aimed to develop a transparent, dynamic machine learning model to predict hospital admissions by establishing a pre-laboratory “information ceiling” using structured electronic health record (EHR) data. Study Design: Retrospective cohort study.
Methods
Utilizing 387,407 patient encounters in the MIMIC-IV-ED (v2.2) database, we developed a dynamic Explainable Boosting Machine (EBM) validated across chronologically distinct anchor_year_group blocks (2008–2016 training vs. 2017–2019 testing) with strict patient-level separation. Anchoring clock-zero (T = 0) at ED arrival (intime) with baseline triage parameters and pre-existing historical records, the model evaluated patients sequentially in 30 min landmarks up to 120 min (T = 120), incorporating timestamped physiological volatility and early medication administrations (pyxis) recorded strictly prior to the prediction landmark and disposition decision. Predictive performance was compared against a black-box HistGradientBoosting (HGB) model and an L2-regularized logistic regression baseline.
Results
The dynamic EBM provided strong baseline discrimination at T = 0 with an ROC-AUC of 0.8048 [95% CI: 0.800–0.806] and a PR-AUC of 0.7395 [95% CI: 0.732–0.742]. Incorporating longitudinal physiological trajectories over a two-hour window yielded a modest, statistically significant improvement at T = 120 (ROC-AUC: 0.8168 [95% CI: 0.813–0.819], PR-AUC: 0.7595 [95% CI: 0.754–0.763], Sensitivity: 80.74%, Specificity: 65.09%, Positive Predictive Value: 61.16%; ΔROC-AUC = +0.0120, p < 0.0001). At T = 120, the opaque HGB benchmark achieved a slightly higher ROC-AUC of 0.8208 [95% CI: 0.817–0.824] (ΔROC-AUC = −0.0040, p = 0.0018), whereas EBM substantially outperformed the linear logistic regression baseline (ROC-AUC: 0.7420 [95% CI: 0.738–0.746]). Without relying on post hoc approximations, EBM generated directly inspectable shape functions capturing non-linear clinical risk relationships, including an observational risk inflection at five home medications and substantial risk penalties for transient hypoxic dips and extreme pulse pressures.
Conclusions
By modeling early ED evaluation as a dynamic trajectory, the EBM achieves discriminative performance closely approaching black-box ensemble methods while maintaining full architectural transparency. Although predicting historical admission decisions requires prospective validation before clinical deployment, this calibrated glass-box framework offers an interpretable foundation for early risk stratification in the ED.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- İbni Sina Family Health Center, Erzurum 25700, Türkiye.
- Biostatistics and Medical İnformatics Department, Faculty of Medicine, İnönü University, Malatya 44280, Türkiye.
ORCID-Profile: Furkan Şakiroğlu, Cemil Çolak
Zitieren
APA
Şakiroğlu, F., & Çolak, C. (2026). Dynamic Prediction of Emergency Department Admissions Using Explainable Artificial Intelligence: A Large-Scale Temporal Validation Study. Journal of Clinical Medicine, 15(21), 8694. https://doi.org/10.3390/jcm15218694
Vancouver
Şakiroğlu F, Çolak C. Dynamic Prediction of Emergency Department Admissions Using Explainable Artificial Intelligence: A Large-Scale Temporal Validation Study. Journal of Clinical Medicine. 2026;15(21):8694. doi:10.3390/jcm15218694
BibTeX
@article{akirolu2026,
author = {Şakiroğlu, Furkan and Çolak, Cemil},
title = {Dynamic Prediction of Emergency Department Admissions Using Explainable Artificial Intelligence: A Large-Scale Temporal Validation Study},
journal = {Journal of Clinical Medicine},
year = {2026},
volume = {15},
number = {21},
pages = {8694},
doi = {10.3390/jcm15218694}
}
EUVIMED