Ensemble-Based Multi-Class and Multi-Label Text Classification for Noisy Clinical Dialogues
Applied Sciences · 10.03.2026 · 16 (6) · 2645
DOI: 10.3390/app16062645 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 10.03.2026. Verfasst von Małgorzata Lucińska und 8 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Centre for Research and Development.
Abstract (Originalsprache)
Multi-class and multi-label classification of medical dialogues remains a challenging task due to high linguistic variability and transcription noise. This study proposes an ensemble approach based on three fine-tuned Polish T5 (Text-to-Text Transfer Transformer) models trained on partially overlapping clinical dialogue datasets. The models are evaluated exclusively on low-quality, highly noisy, automatically transcribed conversations to assess real-world robustness. The results demonstrate that the ensemble of models improves classification stability and outperforms the best single model, increasing the F1-score by 21.8% for internal medicine dialogues and by 44.9% for paediatric interviews. The proposed method shows potential for practical deployment in clinical decision support and automated medical documentation systems.
Förderung
- National Centre for Research and Development
Zitieren
APA
Lucińska, M., Płaza, M., Kęczkowska, J., Kurek, K., Wykrota, K., Deniziak, S., Twardowski, K., Koruba, Z., & Płaza, M. (2026). Ensemble-Based Multi-Class and Multi-Label Text Classification for Noisy Clinical Dialogues. Applied Sciences, 16(6), 2645. https://doi.org/10.3390/app16062645
Vancouver
Lucińska M, Płaza M, Kęczkowska J, Kurek K, Wykrota K, Deniziak S, et al. Ensemble-Based Multi-Class and Multi-Label Text Classification for Noisy Clinical Dialogues. Applied Sciences. 2026;16(6):2645. doi:10.3390/app16062645
BibTeX
@article{Luciska2026,
author = {Lucińska, Małgorzata and Płaza, Małgorzata and Kęczkowska, Justyna and Kurek, Kacper and Wykrota, Karol and Deniziak, Stanisław and Twardowski, Karol and Koruba, Zbigniew and Płaza, Mirosław},
title = {Ensemble-Based Multi-Class and Multi-Label Text Classification for Noisy Clinical Dialogues},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {6},
pages = {2645},
doi = {10.3390/app16062645}
}
EUVIMED