Combining Machine Learning With Real-World Data to Identify Gaps in Clinical Practice Guidelines: Feasibility Study Using the Prospective German Stroke Registry and the National Acute Ischemic Stroke Guidelines
JMIR Medical Informatics · 2025
DOI: 10.2196/69282 ↗Kurz gefasst
Beobachtungsstudie in der Zeitschrift JMIR Medical Informatics, 2025. Verfasst von Sandrine Müller und 9 weiteren Autor:innen. Beteiligte Einrichtung: Fraunhofer Institute for Digital Medicine, Bremen, Germany. Hauptthemen laut MEDLINE: Machine Learning, Ischemic Stroke, Practice Guidelines as Topic. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Clinical practice guidelines (CPGs) serve as essential tools for guiding clinicians in providing appropriate patient care. However, clinical practice does not always reflect CPGs. This is particularly critical in acute diseases requiring immediate treatment, such as acute ischemic stroke, one of the leading causes of morbidity and mortality worldwide. Adherence to CPGs improves patient outcomes, yet guidelines may not address all patient scenarios, resulting in variability in treatment decisions. Identifying such gaps would augment CPGs but is challenging when using traditional methods.
Objective
This study aims to leverage real-world data coupled with machine learning (ML) techniques to systematically identify and quantify gaps in German thrombolysis-in-stroke guidelines.
Methods
We analyzed observational data from the German Stroke Registry – Endovascular Treatment (GSR-ET), a prospective national registry involving 18,069 patients from 25 stroke centers in whom endovascular treatment of a large vessel occlusion was attempted between 2015 and 2023. Key variables included demographic, clinical and imaging information, treatment details, and outcomes. A random forest model was used to predict intravenous thrombolysis treatment decisions based on three different sets of features: (1) guideline-recommended features, (2) clinician-selected features, and (3) features as documented in the GSR-ET before thrombolytic treatment. Feature importance scores, permutation importance, and Shapley Additive Explanations values were used, with clinician guidance, to interpret the model and identify key factors associated with guideline deviations and independent clinician judgments.
Results
Of all GSR-ET patients, 13,440 (74.4%) were analyzed after excluding those with incomplete or implausible data. The random forest model’s performance, measured by area under the receiver operating characteristics curve, was 0.71 (95% CI 0.68‐0.73), 0.74 (95% CI 0.73‐0.75), and 0.77 (95% CI 0.76‐0.78) for the guideline-recommended, clinician-selected, and GSR-ET feature sets, respectively. Across all sets, time from symptom onset to admission was the most important predictor of thrombolysis treatment decisions. Age, which according to the German guidelines is not to be considered for thrombolysis administration, emerged as a significant predictor in the GSR-ET feature set, suggesting a potential gap between guidelines and clinical practice.
Conclusions
In our study, we introduce an innovative approach that combines real-world data with ML techniques to identify discrepancies between CPGs and actual clinical decision-making. Using intravenous thrombolysis in large vessel occlusion stroke as a model, our findings suggest that treatment decisions may be influenced by factors not explicitly included in the current German guideline, such as patient age and pre-stroke functional status. This approach may help uncover clinically relevant variables for potential inclusion in future guideline refinements.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Fraunhofer Institute for Digital Medicine, Bremen, Germany.
- Constructor University, Bremen, Germany.
- Department of Mathematics and Computer Science, University of Bremen, Bremen, Germany.
- Department of Neurology & Stroke, University of Tübingen, Hoppe-Seyler-Str. 3, Tübingen, 72076, Germany, 49 1724682284.
- Hertie Institute for Clinical Brain Research, Tübingen, Germany.
- Department of Diagnostic and Interventional Neuroradiology, University of Tübingen, Tübingen, Germany.
ORCID-Profile: Sandrine Müller, Susanne Diekmann, Markus Wenzel, Horst Karl Hahn, Johannes Tuennerhoff, Ulrike Ernemann, Florian Hennersdorf, Max Westphal, Sven Poli
Zitieren
APA
Müller, S., Diekmann, S., Wenzel, M., Hahn, H. K., Tuennerhoff, J., Ernemann, U., Hennersdorf, F., German Stroke Registry Investigators, Westphal, M., & Poli, S. (2025). Combining Machine Learning With Real-World Data to Identify Gaps in Clinical Practice Guidelines: Feasibility Study Using the Prospective German Stroke Registry and the National Acute Ischemic Stroke Guidelines. JMIR Medical Informatics. https://doi.org/10.2196/69282
Vancouver
Müller S, Diekmann S, Wenzel M, Hahn HK, Tuennerhoff J, Ernemann U, et al. Combining Machine Learning With Real-World Data to Identify Gaps in Clinical Practice Guidelines: Feasibility Study Using the Prospective German Stroke Registry and the National Acute Ischemic Stroke Guidelines. JMIR Medical Informatics. 2025. doi:10.2196/69282
BibTeX
@article{Mller2025,
author = {Müller, Sandrine and Diekmann, Susanne and Wenzel, Markus and Hahn, Horst Karl and Tuennerhoff, Johannes and Ernemann, Ulrike and Hennersdorf, Florian and German Stroke Registry Investigators, German Stroke Registry Investigators and Westphal, Max and Poli, Sven},
title = {Combining Machine Learning With Real-World Data to Identify Gaps in Clinical Practice Guidelines: Feasibility Study Using the Prospective German Stroke Registry and the National Acute Ischemic Stroke Guidelines},
journal = {JMIR Medical Informatics},
year = {2025},
doi = {10.2196/69282}
}
EUVIMED