Summary of Conversational Disease Diagnosis Via External Planner-controlled Large Language Models, by Zhoujian Sun et al.
Conversational Disease Diagnosis via External Planner-Controlled Large Language Models
by Zhoujian Sun, Cheng Luo, Ziyi Liu, Zhengxing Huang
First submitted to arxiv on: 4 Apr 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a large language model (LLM) based diagnostic system that enhances planning capabilities by emulating doctors. The system involves two external planners: one using reinforcement learning to formulate disease screening questions and conduct initial diagnoses, and another using LLMs to parse medical guidelines and conduct differential diagnoses. The system is evaluated on real patient electronic medical record data through simulated dialogues between virtual patients and doctors. The results show impressive performance in both disease screening and differential diagnoses tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study creates a computer program that helps doctors make diagnoses more accurately by using artificial intelligence (AI) like large language models (LLMs). The program is designed to work with real medical records and has two main parts: one that figures out what questions to ask patients, and another that uses LLMs to look at medical guidelines. By testing the program with fake patient cases, researchers showed it can make good diagnoses for different diseases. |
Keywords
» Artificial intelligence » Large language model » Reinforcement learning
