CliniDigest: A Case Study in Large Language Model Based Large-Scale Summarization of Clinical Trial Descriptions
arXiv:2307.14522 · doi:10.1145/3582515.3609559
Abstract
A clinical trial is a study that evaluates new biomedical interventions. To design new trials, researchers draw inspiration from those current and completed. In 2022, there were on average more than 100 clinical trials submitted to ClinicalTrials.gov every day, with each trial having a mean of approximately 1500 words [1]. This makes it nearly impossible to keep up to date. To mitigate this issue, we have created a batch clinical trial summarizer called CliniDigest using GPT-3.5. CliniDigest is, to our knowledge, the first tool able to provide real-time, truthful, and comprehensive summaries of clinical trials. CliniDigest can reduce up to 85 clinical trial descriptions (approximately 10,500 words) into a concise 200-word summary with references and limited hallucinations. We have tested CliniDigest on its ability to summarize 457 trials divided across 27 medical subdomains. For each field, CliniDigest generates summaries of words, each of which utilizes of the sources. A more comprehensive evaluation is planned and outlined in this paper.
arXiv comment7 pages, 3 figures, 3 tables, conference: ACM GoodIt 23'; Second co-author: Tristan Peng; Citation: White, Peng, et al
References in corpus (7)
- A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
- Summarization from Medical Documents: A Survey
- TruthfulQA: Measuring How Models Mimic Human Falsehoods
- Prompt Engineering for Healthcare: Methodologies and Applications
- DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4
- Automatic Text Summarization of COVID-19 Medical Research Articles using BERT and GPT-2
- SPeC: A Soft Prompt-Based Calibration on Performance Variability of Large Language Model in Clinical Notes Summarization