Topic Modeling for Interpretable Text Classification From EHRs

Frontiers in Big Data, vol. 5, pp. 846930

Abstract

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.

Authors 6

1. Emil Rijcken corresponding

   Utrecht University · Eindhoven University of Technology

   Affiliation as printed

   Department of Information and Computing Sciences, Utrecht University, Utrecht, Netherlands

   Jheronimus Academy of Data Science, Eindhoven University of Technology, Eindhoven, Netherlands

2. Uzay Kaymak

   Eindhoven University of Technology

   Affiliation as printed

   Jheronimus Academy of Data Science, Eindhoven University of Technology, Eindhoven, Netherlands

3. Floortje E. Scheepers

   University Medical Center Utrecht

   Affiliation as printed

   University Medical Center Utrecht, Utrecht, Netherlands

4. Pablo J. Mosteiro

   Utrecht University

   Affiliation as printed

   Department of Information and Computing Sciences, Utrecht University, Utrecht, Netherlands

5. Kalliopi Zervanou Aachen Leiden Institute of Advanced Computer Science Faculty of Science, Leiden University Public Health and Primary Care

   Leiden University · Leiden University Medical Center

   Affiliation as printed

   Leiden Institute of Advanced Computer Science (LIACS), Faculty of Science, Leiden University, Leiden, Netherlands

   Public Health and Primary Care (PHEG), Leiden University Medical Center, Leiden University, Leiden, Netherlands

6. Marco René Spruit Aachen Leiden Institute of Advanced Computer Science Faculty of Science, Leiden University Public Health and Primary Care

   Leiden University · Utrecht University · Leiden University Medical Center

   Affiliation as printed

   Department of Information and Computing Sciences, Utrecht University, Utrecht, Netherlands

   Leiden Institute of Advanced Computer Science (LIACS), Faculty of Science, Leiden University, Leiden, Netherlands

   Public Health and Primary Care (PHEG), Leiden University Medical Center, Leiden University, Leiden, Netherlands