OncoGPT: A Medical Conversational Model Tailored with Oncology Domain Expertise on a Large Language Model Meta-AI (LLaMA)

TL;DR

OncoGPT is a specialized medical conversational model built on LLaMA, fine-tuned with over 180,000 oncology-related interactions to improve accuracy and reliability in oncology advice, and is openly available for research.

Contribution

The paper introduces OncoGPT, a novel oncology-focused conversational model trained on a large, expert-reviewed dataset, enhancing medical dialogue accuracy in the oncology domain.

Findings

Significant improvement in oncology query understanding.

Enhanced reliability in medical advice provision.

Open release of dataset and models for research.

Abstract

In the past year, there has been a growing trend in applying Large Language Models (LLMs) to the field of medicine, particularly with the advent of advanced language models such as ChatGPT developed by OpenAI. However, there is limited research on LLMs specifically addressing oncology-related queries. The primary aim of this research was to develop a specialized language model that demonstrates improved accuracy in providing advice related to oncology. We performed an extensive data collection of online question-answer interactions centered around oncology, sourced from reputable doctor-patient platforms. Following data cleaning and anonymization, a dataset comprising over 180K+ oncology-related conversations was established. The conversations were categorized and meticulously reviewed by field specialists and clinicians to ensure precision. Employing the LLaMA model and other selected open-source datasets, we conducted iterative fine-tuning to enhance the model's proficiency in basic medical conversation and specialized oncology knowledge. We observed a substantial enhancement in the model's understanding of genuine patient inquiries and its reliability in offering oncology-related advice through the utilization of real online question-answer interactions in the fine-tuning process. We release database and models to the research community (https://github.com/OncoGPT1).