| Title: |
Machine learning vs. rule-based methods for document classification of electronic health records within mental health care: A systematic literature review |
| Authors: |
Rijcken, Emil; Zervanou, Kalliopi; Mosteiro, Pablo; Scheepers, Floortje; Spruit, Marco; Kaymak, Uzay; Sub Natural Language Processing; Sub Data Intensive Systems; Methodology and Statistics for the Behavioural and Social Sciences; Leerstoel Schoot |
| Publication Year: |
2025 |
| Subject Terms: |
Document classification; Electronic health records; Machine learning; Mental healthcare; Natural language processing; Rule-based methods; SDG 3 - Good Health and Well-being |
| Description: |
Document classification is a widely used task for analyzing mental healthcare texts. This systematic literature review focuses on the document classification of electronic health records in mental healthcare. Over the last decade, there has been a shift from rule-based to machine-learning methods. Despite this shift, no systematic comparison of these two approaches exists for mental healthcare applications. This review examines the evolution, applications, and performance of these methods over time. We find that for most of the last decade, rule-based methods have outperformed machine-learning approaches. However, with the development of more advanced machine-learning techniques, performance has improved. In particular, Transformer-based models enable machine learning approaches to outperform rule-based methods for the first time. |
| Document Type: |
article in journal/newspaper |
| File Description: |
application/pdf |
| Language: |
English |
| ISSN: |
2949-7191 |
| Relation: |
https://dspace.library.uu.nl/handle/1874/475149 |
| Availability: |
https://dspace.library.uu.nl/handle/1874/475149 |
| Rights: |
info:eu-repo/semantics/OpenAccess |
| Accession Number: |
edsbas.A0C557D7 |
| Database: |
BASE |