Automatic Patient Note Assessment without Strong Supervision
Jianing Zhou, Vyom Nayan Thakkar, Rachel Yudkowsky, Suma Bhat, William F. Bond
Abstract
Training of physicians requires significant practice writing patient notes that document the patient’s medical and health information and physician diagnostic reasoning. Assessment and feedback of the patient note requires experienced faculty, consumes significant amounts of time and delays feedback to learners. Grading patient notes is thus a tedious and expensive process for humans that could be improved with the addition of natural language processing. However, the large manual effort required to create labeled datasets increases the challenge, particularly when test cases change. Therefore, traditional supervised NLP methods relying on labelled datasets are impractical in such a low-resource scenario. In our work, we proposed an unsupervised framework as a simple baseline and a weakly supervised method utilizing transfer learning for automatic assessment of patient notes under a low-resource scenario. Experiments on our self-collected datasets show that our weakly-supervised methods could provide reliable assessment for patient notes with accuracy of 0.92.- Anthology ID:
- 2022.louhi-1.14
- Volume:
- Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates (Hybrid)
- Editors:
- Alberto Lavelli, Eben Holderness, Antonio Jimeno Yepes, Anne-Lyse Minard, James Pustejovsky, Fabio Rinaldi
- Venue:
- Louhi
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 116–126
- Language:
- URL:
- https://aclanthology.org/2022.louhi-1.14
- DOI:
- 10.18653/v1/2022.louhi-1.14
- Cite (ACL):
- Jianing Zhou, Vyom Nayan Thakkar, Rachel Yudkowsky, Suma Bhat, and William F. Bond. 2022. Automatic Patient Note Assessment without Strong Supervision. In Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI), pages 116–126, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- Automatic Patient Note Assessment without Strong Supervision (Zhou et al., Louhi 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.louhi-1.14.pdf