Adapting Open-Source Large Language Models for Cost-Effective, Expert-Level Clinical Note Generation with On-Policy Reinforcement Learning
- URL: http://arxiv.org/abs/2405.00715v4
- Date: Mon, 10 Jun 2024 01:09:03 GMT
- Title: Adapting Open-Source Large Language Models for Cost-Effective, Expert-Level Clinical Note Generation with On-Policy Reinforcement Learning
- Authors: Hanyin Wang, Chufan Gao, Bolun Liu, Qiping Xu, Guleid Hussein, Mohamad El Labban, Kingsley Iheasirim, Hariprasad Korsapati, Chuck Outcalt, Jimeng Sun,
- Abstract summary: This study presents a comprehensive domain- and task-specific adaptation process for the open-source LLaMA-2 13 billion parameter model.
We introduce a new approach, DistillDirect, for performing on-policy reinforcement learning with Gemini 1.0 Pro as the teacher model.
Our model, LLaMA-Clinic, can generate clinical notes comparable in quality to those authored by physicians.
- Score: 19.08691249610632
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Proprietary Large Language Models (LLMs) such as GPT-4 and Gemini have demonstrated promising capabilities in clinical text summarization tasks. However, due to patient data privacy concerns and computational costs, many healthcare providers prefer using small, locally-hosted models over external generic LLMs. This study presents a comprehensive domain- and task-specific adaptation process for the open-source LLaMA-2 13 billion parameter model, enabling it to generate high-quality clinical notes from outpatient patient-doctor dialogues. Our process incorporates continued pre-training, supervised fine-tuning, and reinforcement learning from both AI and human feedback. We introduced a new approach, DistillDirect, for performing on-policy reinforcement learning with Gemini 1.0 Pro as the teacher model. Our resulting model, LLaMA-Clinic, can generate clinical notes comparable in quality to those authored by physicians. In a blinded physician reader study, the majority (90.4%) of individual evaluations rated the notes generated by LLaMA-Clinic as "acceptable" or higher across all three criteria: real-world readiness, completeness, and accuracy. In the more challenging "Assessment and Plan" section, LLaMA-Clinic scored higher (4.2/5) in real-world readiness than physician-authored notes (4.1/5). Our cost analysis for inference shows that our LLaMA-Clinic model achieves a 3.75-fold cost reduction compared to an external generic LLM service. Additionally, we highlight key considerations for future clinical note-generation tasks, emphasizing the importance of pre-defining a best-practice note format, rather than relying on LLMs to determine this for clinical practice. We have made our newly created synthetic clinic dialogue-note dataset and the physician feedback dataset publicly available to foster future research.
Related papers
- SoftTiger: A Clinical Foundation Model for Healthcare Workflows [5.181665205189493]
We introduce SoftTiger, a clinical large language model (CLaM) designed as a foundation model for healthcare.
We collect and annotate data for three subtasks, namely, international patient summary, clinical impression and medical encounter.
We supervised fine-tuned a state-of-the-art LLM using public and credentialed clinical data.
arXiv Detail & Related papers (2024-03-01T04:39:16Z) - AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs.
This setup allows for realistic assessments of LLMs in clinical scenarios.
We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
arXiv Detail & Related papers (2024-02-15T06:46:48Z) - Large Language Model Distilling Medication Recommendation Model [61.89754499292561]
We harness the powerful semantic comprehension and input-agnostic characteristics of Large Language Models (LLMs)
Our research aims to transform existing medication recommendation methodologies using LLMs.
To mitigate this, we have developed a feature-level knowledge distillation technique, which transfers the LLM's proficiency to a more compact model.
arXiv Detail & Related papers (2024-02-05T08:25:22Z) - Distilling Large Language Models for Matching Patients to Clinical
Trials [3.4068841624198942]
The recent success of large language models (LLMs) has paved the way for their adoption in the high-stakes domain of healthcare.
This study presents the first systematic examination of the efficacy of both proprietary (GPT-3.5, and GPT-4) and open-source LLMs (LLAMA 7B,13B, and 70B) for the task of patient-trial matching.
Our findings reveal that open-source LLMs, when fine-tuned on this limited and synthetic dataset, demonstrate performance parity with their proprietary counterparts.
arXiv Detail & Related papers (2023-12-15T17:11:07Z) - Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization [8.456700096020601]
Large language models (LLMs) have shown promise in natural language processing (NLP), but their effectiveness on a diverse range of clinical summarization tasks remains unproven.
In this study, we apply adaptation methods to eight LLMs, spanning four distinct clinical summarization tasks.
A clinical reader study with ten physicians evaluates summary, completeness, correctness, and conciseness; in a majority of cases, summaries from our best adapted LLMs are either equivalent (45%) or superior (36%) compared to summaries from medical experts.
arXiv Detail & Related papers (2023-09-14T05:15:01Z) - Large Language Models for Healthcare Data Augmentation: An Example on
Patient-Trial Matching [49.78442796596806]
We propose an innovative privacy-aware data augmentation approach for patient-trial matching (LLM-PTM)
Our experiments demonstrate a 7.32% average improvement in performance using the proposed LLM-PTM method, and the generalizability to new data is improved by 12.12%.
arXiv Detail & Related papers (2023-03-24T03:14:00Z) - Do We Still Need Clinical Language Models? [15.023633270864675]
We show that relatively small specialized clinical models substantially outperform all in-context learning approaches.
We release the code and the models used under the PhysioNet Credentialed Health Data license and data use agreement.
arXiv Detail & Related papers (2023-02-16T05:08:34Z) - Large Language Models Encode Clinical Knowledge [21.630872464930587]
Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation.
We propose a framework for human evaluation of model answers along multiple axes including factuality, precision, possible harm, and bias.
We show that comprehension, recall of knowledge, and medical reasoning improve with model scale and instruction prompt tuning.
arXiv Detail & Related papers (2022-12-26T14:28:24Z) - Retrieval-Augmented and Knowledge-Grounded Language Models for Faithful Clinical Medicine [68.7814360102644]
We propose the Re$3$Writer method with retrieval-augmented generation and knowledge-grounded reasoning.
We demonstrate the effectiveness of our method in generating patient discharge instructions.
arXiv Detail & Related papers (2022-10-23T16:34:39Z) - Human Evaluation and Correlation with Automatic Metrics in Consultation
Note Generation [56.25869366777579]
In recent years, machine learning models have rapidly become better at generating clinical consultation notes.
We present an extensive human evaluation study where 5 clinicians listen to 57 mock consultations, write their own notes, post-edit a number of automatically generated notes, and extract all the errors.
We find that a simple, character-based Levenshtein distance metric performs on par if not better than common model-based metrics like BertScore.
arXiv Detail & Related papers (2022-04-01T14:04:16Z) - Self-supervised Answer Retrieval on Clinical Notes [68.87777592015402]
We introduce CAPR, a rule-based self-supervision objective for training Transformer language models for domain-specific passage matching.
We apply our objective in four Transformer-based architectures: Contextual Document Vectors, Bi-, Poly- and Cross-encoders.
We report that CAPR outperforms strong baselines in the retrieval of domain-specific passages and effectively generalizes across rule-based and human-labeled passages.
arXiv Detail & Related papers (2021-08-02T10:42:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.