University of Texas Health Science Center at Houston, Houston, Texas, USA.
Vanderbilt University, Nashville, Tennessee, USA.
Stud Health Technol Inform. 2024 Aug 22;316:1255-1259. doi: 10.3233/SHTI240639.
This paper presents a chatbot that simplifies accessing and understanding the open-access records of adverse events related to medical devices in the MAUDE database. The chatbot is powered by generative AI technology, enabling count and search queries. The chatbot uses the openFDA API and GPT-4 model to interpret users' natural language queries, generate appropriate API calls, and summarize adverse event reports. The chatbot also provides a downloadable link to the original reports. The model's performance in generating accurate API calls was assessed and improved by training it with few-shot examples of query-URL pairs. Additionally, the quality of content-based summaries was evaluated by human expert ratings. This initiative is a significant step towards making patient safety data accessible, replicable, and easily manageable by a broader range of researchers.
这篇论文提出了一个聊天机器人，旨在简化访问和理解 MAUDE 数据库中与医疗器械相关的不良事件的开放获取记录。该聊天机器人由生成式人工智能技术提供支持，支持计数和搜索查询。聊天机器人使用 openFDA API 和 GPT-4 模型来解释用户的自然语言查询，生成适当的 API 调用，并总结不良事件报告。聊天机器人还提供了原始报告的可下载链接。通过使用少量查询-URL 对示例对模型进行训练，评估并改进了模型生成准确 API 调用的性能。此外，通过人类专家评分评估了基于内容的摘要的质量。这一举措是朝着使更广泛的研究人员能够访问、复制和轻松管理患者安全数据迈出的重要一步。
