Multi-Task Training with In-Domain Language Models for Diagnostic Reasoning

Brihat Sharma, Yanjun Gao, Timothy Miller, Matthew Churpek, Majid Afshar, Dmitriy Dligach


Abstract
Generative artificial intelligence (AI) is a promising direction for augmenting clinical diagnostic decision support and reducing diagnostic errors, a leading contributor to medical errors. To further the development of clinical AI systems, the Diagnostic Reasoning Benchmark (DR.BENCH) was introduced as a comprehensive generative AI framework, comprised of six tasks representing key components in clinical reasoning. We present a comparative analysis of in-domain versus out-of-domain language models as well as multi-task versus single task training with a focus on the problem summarization task in DR.BENCH. We demonstrate that a multi-task, clinically-trained language model outperforms its general domain counterpart by a large margin, establishing a new state-of-the-art performance, with a ROUGE-L score of 28.55. This research underscores the value of domain-specific training for optimizing clinical diagnostic reasoning tasks.
Anthology ID:
2023.clinicalnlp-1.10
Volume:
Proceedings of the 5th Clinical Natural Language Processing Workshop
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Tristan Naumann, Asma Ben Abacha, Steven Bethard, Kirk Roberts, Anna Rumshisky
Venue:
ClinicalNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
78–85
Language:
URL:
https://aclanthology.org/2023.clinicalnlp-1.10
DOI:
10.18653/v1/2023.clinicalnlp-1.10
Bibkey:
Cite (ACL):
Brihat Sharma, Yanjun Gao, Timothy Miller, Matthew Churpek, Majid Afshar, and Dmitriy Dligach. 2023. Multi-Task Training with In-Domain Language Models for Diagnostic Reasoning. In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 78–85, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Multi-Task Training with In-Domain Language Models for Diagnostic Reasoning (Sharma et al., ClinicalNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.clinicalnlp-1.10.pdf
Video:
 https://aclanthology.org/2023.clinicalnlp-1.10.mp4