Summary of Prism: Patient Records Interpretation For Semantic Clinical Trial Matching Using Large Language Models, by Shashi Kant Gupta et al.
PRISM: Patient Records Interpretation for Semantic Clinical Trial Matching using Large Language Models
by Shashi Kant Gupta, Aditya Basu, Mauro Nievas, Jerrin Thomas, Nathan Wolfrath, Adhitya Ramamurthi, Bradley Taylor, Anai N. Kothari, Regina Schwind, Therica M. Miller, Sorena Nadaf-Rahrov, Yanshan Wang, Hrituraj Singh
First submitted to arxiv on: 23 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 an end-to-end large-scale empirical evaluation of clinical trial matching using real-world electronic health records (EHRs). Recent advancements in Large Language Models (LLMs) have made it possible to automate patient-trial matching, but current approaches are limited to constrained datasets. This study showcases the capability of LLMs to accurately match patients with appropriate clinical trials. The authors perform experiments with proprietary LLMs, including GPT-4 and GPT-3.5, as well as their custom fine-tuned model called OncoLLM. They find that OncoLLM outperforms GPT-3.5 and matches the performance of qualified medical doctors on real-world EHRs from a single cancer center in the United States. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at how to match patients with clinical trials more efficiently. Right now, this process is done by hand and takes a lot of time. It’s hard to scale up because it requires checking patient records against very strict rules about who can participate in each trial. This means many people might miss out on helpful treatments. The authors are using special computer models called Large Language Models (LLMs) to automate this process. They’re testing these models on real-world medical data and finding that they can accurately match patients with trials. |
Keywords
» Artificial intelligence » Gpt
