Topic Modeling for Interpretable Text Classification From EHRs
| Autor: | Rijcken, Emil, Kaymak, Uzay, Scheepers, F.E., Mosteiro Romero, Pablo, Zervanou, Kalliopi, Spruit, Marco, Sub Natural Language Processing, Natural Language Processing |
|---|---|
| Přispěvatelé: | Sub Natural Language Processing, Natural Language Processing, JADS Research, JADS Den Bosch (TU/e), EAISI Health, EAISI Foundational |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
rechtvaardigheid en sterke instellingen
SDG 16 - Peace text classification SDG 16 – Vrede SDG 16 - Peace Justice and Strong Institutions topic modeling Justice and Strong Institutions psychiatry electronic health records Artificial Intelligence explainability Computer Science (miscellaneous) information extraction natural language processing interpretability Information Systems |
| Zdroj: | Frontiers in Big Data, 5, 1. Frontiers Media SA Frontiers in Big Data, 5:846930. Frontiers Media S.A. |
| ISSN: | 2624-909X |
| DOI: | 10.3389/fdata.2022.846930 |
| Popis: | The clinical notes in electronic health records have many possibilities for predictive tasks in text classification. The interpretability of these classification models for the clinical domain is critical for decision making. Using topic models for text classification of electronic health records for a predictive task allows for the use of topics as features, thus making the text classification more interpretable. However, selecting the most effective topic model is not trivial. In this work, we propose considerations for selecting a suitable topic model based on the predictive performance and interpretability measure for text classification. We compare 17 different topic models in terms of both interpretability and predictive performance in an inpatient violence prediction task using clinical notes. We find no correlation between interpretability and predictive performance. In addition, our results show that although no model outperforms the other models on both variables, our proposed fuzzy topic modeling algorithm (FLSA-W) performs best in most settings for interpretability, whereas two state-of-the-art methods (ProdLDA and LSI) achieve the best predictive performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|