O2 supplementation disambiguation in clinical narratives to support retrospective COVID-19 studies
BMC Medical Informatics and Decision Making · 2024
DOI: 10.1186/s12911-024-02425-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift BMC Medical Informatics and Decision Making, 2024. Verfasst von Akhila Abdulnazar und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Graz, Austria. Hauptthemen laut MEDLINE: COVID-19, Oxides, Calcium Compounds. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Oxygen saturation, a key indicator of COVID-19 severity, poses challenges, especially in cases of silent hypoxemia. Electronic health records (EHRs) often contain supplemental oxygen information within clinical narratives. Streamlining patient identification based on oxygen levels is crucial for COVID-19 research, underscoring the need for automated classifiers in discharge summaries to ease the manual review burden on physicians.
Method
We analysed text lines extracted from anonymised COVID-19 patient discharge summaries in German to perform a binary classification task, differentiating patients who received oxygen supplementation and those who did not. Various machine learning (ML) algorithms, including classical ML to deep learning (DL) models, were compared. Classifier decisions were explained using Local Interpretable Model-agnostic Explanations (LIME), which visualize the model decisions.
Result
Classical ML to DL models achieved comparable performance in classification, with an F-measure varying between 0.942 and 0.955, whereas the classical ML approaches were faster. Visualisation of embedding representation of input data reveals notable variations in the encoding patterns between classic and DL encoders. Furthermore, LIME explanations provide insights into the most relevant features at token level that contribute to these observed differences.
Conclusion
Despite a general tendency towards deep learning, these use cases show that classical approaches yield comparable results at lower computational cost. Model prediction explanations using LIME in textual and visual layouts provided a qualitative explanation for the model performance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Graz, Austria.
- CBmed GmbH - Center for Biomarker Research in Medicine, Graz, Austria.
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Medical University of Graz, Graz, Austria.
- Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Graz, Austria. markus.kreuzthaler@medunigraz.at.
Zitieren
APA
Abdulnazar, A., Kugic, A., Schulz, S., Stadlbauer, V., & Kreuzthaler, M. (2024). O2 supplementation disambiguation in clinical narratives to support retrospective COVID-19 studies. BMC Medical Informatics and Decision Making. https://doi.org/10.1186/s12911-024-02425-2
Vancouver
Abdulnazar A, Kugic A, Schulz S, Stadlbauer V, Kreuzthaler M. O2 supplementation disambiguation in clinical narratives to support retrospective COVID-19 studies. BMC Medical Informatics and Decision Making. 2024. doi:10.1186/s12911-024-02425-2
BibTeX
@article{Abdulnazar2024,
author = {Abdulnazar, Akhila and Kugic, Amila and Schulz, Stefan and Stadlbauer, Vanessa and Kreuzthaler, Markus},
title = {O2 supplementation disambiguation in clinical narratives to support retrospective COVID-19 studies},
journal = {BMC Medical Informatics and Decision Making},
year = {2024},
doi = {10.1186/s12911-024-02425-2}
}
EUVIMED