FairCareNLP: An AI-driven patient review analyzer for healthcare
PLOS One · 04.05.2026 · 21 (5) · e0337676
DOI: 10.1371/journal.pone.0337676 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.05.2026. Verfasst von Sayyed Mohammad Pourya Momtaz Esfahani und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto, Toronto, Canada. Hauptthemen laut MEDLINE: Natural Language Processing, Delivery of Health Care. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Objective
To develop and evaluate an automatic patient review analyzer that applies advanced Natural Language Processing (NLP) and machine learning methods to improve the efficiency, fairness, and accuracy of healthcare feedback analysis. Materials and methods We designed a multi-component pipeline incorporating sentiment analysis, key theme extraction, clinical Named Entity Recognition (NER), and fairness modules. Bias mitigation was addressed through the integration of three complementary approaches: adversarial debiasing, Hard Debiasing, and Iterative Null-space Projection (INLP). Multiple BERT-based models (DistilBERT, BioBERT, RoBERTa-base, BERT-base-uncased) were trained and evaluated under varying hyperparameters and fairness/adversarial loss configurations. Model performance was assessed using accuracy, F1, recall, precision, AUC, Equalized Odds (EOD), and Word Embedding Association Test (WEAT) metrics.
Results
Adversarial loss ( λ adv > 0 ) consistently decreased model performance across accuracy, F1, precision, and recall. In contrast, Hard Debiasing and INLP improved WEAT scores while preserving or enhancing other metrics, with INLP yielding the best overall performance. Specifically, INLP with fairness loss improved EOD by 14%, gender WEAT scores by 15%, and achieved slight gains for ethnicity and socioeconomic WEAT scores. The best model achieved accuracy of 0.856, F1 score of 0.812, recall of 0.798, and precision of 0.829. The key theme analysis module identified 82% of expert-labeled themes, though 21% of patient comments lacked expert labels for valence or related attributes.
Discussion
Our results demonstrate the trade-offs between fairness and performance in bias mitigation strategies. While adversarial debiasing reduced predictive accuracy, INLP and Hard Debiasing improved fairness without significant degradation in task performance. Gender bias was easier to mitigate than multi-class sensitive attributes such as ethnicity and income. This difference indicates a need for fairness techniques designed for multi-class sensitive attributes.
Conclusion
This work presents an NLP pipeline for patient feedback analysis with multiple debiasing strategies. This pipeline improves the fairness and accuracy of insights from unstructured patient reviews and supports inclusive patient-centered care.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto, Toronto, Canada.
- Department of Computer Science, Cornell University, New York, United States of America.
- Faculty of Information, University of Toronto, Toronto, Canada.
- Schwartz Reisman Institute, University of Toronto, Toronto, Canada.
ORCID-Profile: Sayyed Mohammad Pourya Momtaz Esfahani, Christoffer Dharma, Mohammad Noaeen, Zahra Shakeri
Förderung
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Momtaz Esfahani, S. M. P., Seeman, D., Dharma, C., Noaeen, M., Guha, S., & Shakeri, Z. (2026). FairCareNLP: An AI-driven patient review analyzer for healthcare. PLOS One, 21(5), e0337676. https://doi.org/10.1371/journal.pone.0337676
Vancouver
Momtaz Esfahani SMP, Seeman D, Dharma C, Noaeen M, Guha S, Shakeri Z. FairCareNLP: An AI-driven patient review analyzer for healthcare. PLOS One. 2026;21(5):e0337676. doi:10.1371/journal.pone.0337676
BibTeX
@article{MomtazEsfahani2026,
author = {Momtaz Esfahani, Sayyed Mohammad Pourya and Seeman, Davey and Dharma, Christoffer and Noaeen, Mohammad and Guha, Shion and Shakeri, Zahra},
title = {FairCareNLP: An AI-driven patient review analyzer for healthcare},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {5},
pages = {e0337676},
doi = {10.1371/journal.pone.0337676}
}
EUVIMED