Summary of Drhouse: An Llm-empowered Diagnostic Reasoning System Through Harnessing Outcomes From Sensor Data and Expert Knowledge, by Bufang Yang et al.
DrHouse: An LLM-empowered Diagnostic Reasoning System through Harnessing Outcomes from Sensor Data and Expert Knowledge
by Bufang Yang, Siyang Jiang, Lilin Xu, Kaiwei Liu, Hai Li, Guoliang Xing, Hongkai Chen, Xiaofan Jiang, Zhenyu Yan
First submitted to arxiv on: 21 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 introduces DrHouse, a novel large language model (LLM)-based virtual doctor system that leverages sensor data from smart devices to enhance diagnosis accuracy and reliability in digital healthcare. The system incorporates three key contributions: utilizing smart device data, continuously updating medical databases like Up-to-Date and PubMed, and introducing a novel diagnostic algorithm that evaluates potential diseases and their likelihood. Through multi-turn interactions, DrHouse determines the next steps for refining diagnoses. The model achieves up to an 18.8% increase in diagnosis accuracy over state-of-the-art baselines on three public datasets and self-collected data. A user study shows that 75% of medical experts and 91.7% of patients are willing to use DrHouse. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary DrHouse is a new way for doctors to help you feel better using artificial intelligence and smart devices. The current method of describing symptoms can lead to mistakes, so this system uses data from sensors in your home to make a more accurate diagnosis. It also keeps the information up-to-date with the latest medical knowledge. The algorithm helps find the most likely cause of your illness and suggests what tests or further steps are needed. This makes for a more informed doctor’s visit. In tests, DrHouse was able to get better results than other methods, and people who tried it were happy to use it again. |
Keywords
» Artificial intelligence » Large language model » Likelihood
