SoftTiger: A Clinical Foundation Model for Healthcare Workflows

TL;DR

SoftTiger is a specialized large language model designed for healthcare workflows, capable of structuring clinical notes and supporting various clinical tasks, aiming to advance healthcare digitalization.

Contribution

The paper introduces SoftTiger, a novel clinical LLM trained on annotated clinical data, supporting multiple clinical tasks and addressing healthcare-specific modeling challenges.

Findings

SoftTiger outperforms popular open-source models and GPT-3.5 in evaluations.

Supports basic to complex clinical tasks, including abbreviation expansion and temporal info extraction.

Publicly released models and datasets to aid healthcare AI development.

Abstract

We introduce SoftTiger, a clinical large language model (CLaM) designed as a foundation model for healthcare workflows. The narrative and unstructured nature of clinical notes is a major obstacle for healthcare intelligentization. We address a critical problem of structuring clinical notes into clinical data, according to international interoperability standards. We collect and annotate data for three subtasks, namely, international patient summary, clinical impression and medical encounter. We then supervised fine-tuned a state-of-the-art LLM using public and credentialed clinical data. The training is orchestrated in a way that the target model can first support basic clinical tasks such as abbreviation expansion and temporal information extraction, and then learn to perform more complex downstream clinical tasks. Moreover, we address several modeling challenges in the healthcare context, e.g., extra long context window. Our blind pairwise evaluation shows that SoftTiger outperforms other popular open-source models and GPT-3.5, comparable to Gemini-pro, with a mild gap from GPT-4. We believe that LLMs may become a step-stone towards healthcare digitalization and democratization. Therefore, we publicly release SoftTiger models at scales of 13 billion and 70 billion parameters, as well as datasets and code for our innovative scalable evaluation, hopefully, making a significant contribution to the healthcare industry.