Using Explainable Artificial Intelligence Models (ML) to Predict Suspected Diagnoses as Clinical Decision Support

Studies in health technology and informatics, vol. 294, pp. 573–574

Abstract

The complexity of emergency cases and the number of emergency patients have increased dramatically. Due to a reduced or even missing specialist medical staff in the emergency departments (EDs), medical knowledge is often used without professional supervision for the diagnosis. The result is a failure in diagnosis and treatment, even death in the worst case. Secondary: high expenditure of time and high costs. Using accurate patient data from the German national registry of the medical emergency departments (AKTIN-registry, Home - Notaufnahmeregister (aktin.org)), the most 20 frequent diagnoses were selected for creating explainable artificial intelligence (XAI) models as part of the ENSURE project (ENSURE (umg.eu)). 137.152 samples and 51 features (vital signs and symptoms) were analyzed. The XAI models achieved a mean area under the curve (AUC) one-vs-rest of 0.98 for logistic regression (LR) and 0.99 for the random forest (RF), and predictive accuracies of 0.927 (LR) and 0.99 (RF). Based on its grade of explainability and performance, the best model will be incorporated into a portable CDSS to improve diagnoses and outcomes of ED treatment and reduce cost. The CDSS will be tested in a clinical pilot study at EDs of selected hospitals in Germany.

Authors 10

1. Zully Ritter

   Universitätsmedizin Göttingen · University of Göttingen

   Affiliation as printed

   Institute of Medical Informatics, University Medicine Göttingen, Georg-August University, Göttingen, Germany

2. Stefan Vogel

   Universitätsmedizin Göttingen · University of Göttingen

   Affiliation as printed

   Institute of Medical Informatics, University Medicine Göttingen, Georg-August University, Göttingen, Germany

3. Frank Christian Schultze

   Universitätsmedizin Göttingen · University of Göttingen

   Affiliation as printed

   Central Emergency Department, University Medicine Göttingen, Georg-August University, Göttingen, Germany

4. Kerstin Pischek-Koch

   Universitätsmedizin Göttingen · University of Göttingen

   Affiliation as printed

   Institute of Medical Informatics, University Medicine Göttingen, Georg-August University, Göttingen, Germany

5. Wiebke Schirrmeister

   Otto-von-Guericke-Universität Magdeburg

   Affiliation as printed

   Department of Trauma Surgery, Otto-von-Guericke University Magdeburg, Magdeburg, Germany

6. Felix Walcher Aachen Institute of Medical Informatics Medical Faculty

   RWTH Aachen University · Otto-von-Guericke-Universität Magdeburg

   Affiliation as printed

   Department of Trauma Surgery, Otto-von-Guericke University Magdeburg, Magdeburg, Germany

   Institute of Medical Informatics, Medical Faculty of RWTH Aachen University, Aachen, Germany

   Department of Trauma Surgery, Otto-von-Guericke University Magdeburg, Magdeburg, Germany; Institute of Medical Informatics, Medical Faculty of RWTH Aachen University, Aachen, Germany

7. Rainer Röhrig Aachen Institute of Medical Informatics Medical Faculty

   RWTH Aachen University

   Affiliation as printed

   AKTIN-Research Group, Germany

   Institute of Medical Informatics, Medical Faculty of RWTH Aachen University, Aachen, Germany

   AKTIN-Research Group, Germany; Institute of Medical Informatics, Medical Faculty of RWTH Aachen University, Aachen, Germany

8. Tibor Kesztyüs

   Universitätsmedizin Göttingen · University of Göttingen

   Affiliation as printed

   Institute of Medical Informatics, University Medicine Göttingen, Georg-August University, Göttingen, Germany

9. Dagmar Krefting

   Universitätsmedizin Göttingen · University of Göttingen

   Affiliation as printed

   Institute of Medical Informatics, University Medicine Göttingen, Georg-August University, Göttingen, Germany

10. Sabine Blaschke Aachen Institute of Medical Informatics Medical Faculty

    Universitätsmedizin Göttingen · University of Göttingen · RWTH Aachen University

    Affiliation as printed

    Central Emergency Department, University Medicine Göttingen, Georg-August University, Göttingen, Germany

    Institute of Medical Informatics, Medical Faculty of RWTH Aachen University, Aachen, Germany