Summary of A Dataset and Benchmark For Hospital Course Summarization with Adapted Large Language Models, by Asad Aali et al.
A Dataset and Benchmark for Hospital Course Summarization with Adapted Large Language Models
by Asad Aali, Dave Van Veen, Yamin Ishraq Arefeen, Jason Hom, Christian Bluethgen, Eduardo Pontes Reis, Sergios Gatidis, Namuun Clifford, Joseph Daws, Arash S. Tehrani, Jangwon Kim, Akshay S. Chaudhari
First submitted to arxiv on: 8 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 This research paper introduces a novel approach to automating Brief Hospital Course (BHC) summaries from clinical notes using Large Language Models (LLMs). The authors develop a pre-processed dataset, MIMIC-IV-BHC, and adapt three open-source LLMs and two proprietary LLMs for BHC synthesis. They evaluate the models’ performance across multiple context-length inputs using natural language similarity metrics and conduct a clinical study with five clinicians to assess their potential to enhance clinical decision-making. The results show that GPT-4 with in-context learning outperforms other domain-adapted models, demonstrating improved summary quality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research paper explores how computers can help summarize hospital stays into easy-to-understand documents. Doctors and nurses write these summaries, but computers could do it faster and more accurately. The researchers created a special set of data to train computer models to do this task. They tested three types of computer models and found that one type, called GPT-4, was particularly good at creating helpful summaries. |
Keywords
* Artificial intelligence * Context length * Gpt
