arXiv Open Access 2023

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

Brihat Sharma Yanjun Gao Timothy Miller Matthew M. Churpek Majid Afshar +1 lainnya
Lihat Sumber

Abstrak

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 (Gao et al., 2023). 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.

Topik & Kata Kunci

Penulis (6)

B

Brihat Sharma

Y

Yanjun Gao

T

Timothy Miller

M

Matthew M. Churpek

M

Majid Afshar

D

Dmitriy Dligach

Format Sitasi

Sharma, B., Gao, Y., Miller, T., Churpek, M.M., Afshar, M., Dligach, D. (2023). Multi-Task Training with In-Domain Language Models for Diagnostic Reasoning. https://arxiv.org/abs/2306.04551

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2023
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓