Medizinische Universität Graz Austria/Österreich - Forschungsportal - Medical University of Graz
Gewählte Publikation:
SHR Neuro Krebs Kardio Lipid Stoffw Microb
Veeranki, SPK; Abdulnazar, A; Kramer, D; Kreuzthaler, M; Lumenta, DB.
Multi-label text classification via secondary use of large clinical real-world data sets.
Sci Rep. 2024; 14(1): 26972
Doi: 10.1038/s41598-024-76424-8
[OPEN ACCESS]
Web of Science
PubMed
FullText
FullText_MUG
- Führende Autor*innen der Med Uni Graz
- Kreuzthaler Markus Eduard
- Co-Autor*innen der Med Uni Graz
- Kuppassery Abdulnazar Akhila Naz
- Lumenta David Benjamin
- Altmetrics:
- Dimensions Citations:
- Plum Analytics:
- Scite (citation analytics):
- Abstract:
- 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.
- Find related publications in this database (using NLM MeSH Indexing)
- Humans - administration & dosage
- Support Vector Machine - administration & dosage
- Natural Language Processing - administration & dosage
- Neural Networks, Computer - administration & dosage
- Logistic Models - administration & dosage
- Electronic Health Records - administration & dosage
- Find related publications in this database (Keywords)
- Natural language processing
- Text classification
- Clinical real world data
- Secondary use