Multi-label text classification via secondary use of large clinical real-world data sets.

Autor: Veeranki SPK; Steiermärkische Krankenanstaltengesellschaft m.b.H. (KAGes), Billrothgasse 18a, 8010, Graz, Austria.; Institute of Neural Engineering, Graz University of Technology, Stremayrgasse 16/IV, 8010, Graz, Austria.; Center for Health and Bioresources, AIT Austrian Institute of Technology GmbH, Reininghausstrasse 13, 8020, Graz, Austria., Abdulnazar A; Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Auenbruggerplatz 2, 8036, Graz, Austria., Kramer D; Steiermärkische Krankenanstaltengesellschaft m.b.H. (KAGes), Billrothgasse 18a, 8010, Graz, Austria.; Predicting Health GmbH, Ruckerlberggasse 13, 8010, Graz, Austria., Kreuzthaler M; Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Auenbruggerplatz 2, 8036, Graz, Austria. markus.kreuzthaler@medunigraz.at., Lumenta DB; Research Unit for Digital Surgery, Division of Plastic, Aesthetic and Reconstructive Surgery, Department of Surgery, Medical University of Graz, Auenbruggerplatz 29/4, 8036, Graz, Austria.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2024 Nov 06; Vol. 14 (1), pp. 26972. Date of Electronic Publication: 2024 Nov 06.
DOI: 10.1038/s41598-024-76424-8
Abstrakt: Procedural coding presents a taxing challenge for clinicians. However, recent advances in natural language processing offer a promising avenue for developing applications that assist clinicians, thereby alleviating their administrative burdens. This study seeks to create an application capable of predicting procedure codes by analysing clinicians' operative notes, aiming to streamline their workflow and enhance efficiency. We downstreamed an existing and a native German medical BERT model in a secondary use scenario, utilizing already coded surgery notes to model the coding procedure as a multi-label classification task. In comparison to the transformer-based architecture, we were levering the non-contextual model fastText, a convolutional neural network, a support vector machine and logistic regression for a comparative analysis of possible coding performance. About 350,000 notes were used for model adaption. By considering the top five suggested procedure codes from medBERT.de, surgeryBERT.at, fastText, a convolutional neural network, a support vector machine and a logistic regression, the mean average precision achieved was 0.880, 0.867, 0.870, 0.851, 0.870 and 0.805 respectively. Support vector machines performed better for surgery reports with a sequence length greater than 512, achieving a mean average precision of 0.872 in comparison to 0.840 for fastText, 0.837 for medBERT.de and 0.820 for surgeryBERT.at. A prototypical front-end application for coding support was additionally implemented. The problem of predicting procedure codes from a given operative report can be successfully modelled as a multi-label classification task, with a promising performance. Support vector machines as a classical machine learning method outperformed the non-contextual fastText approach. FastText with less demanding hardware resources has reached a similar performance to BERT-based models and has shown to be more suitable for explaining the predictions efficiently.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje