Ding Hanlin, Xia Wenjie, Zhou Yujia, Wei Lei, Feng Yipeng, Wang Zi, Song Xuming, Li Rutao, Mao Qixing, Chen Bing, Wang Hui, Huang Xing, Zhu Bin, Jiang Dongyu, Sun Jingyu, Dong Gaochao, Jiang Feng
Department of Thoracic Surgery, Nanjing Medical University Affiliated Cancer Hospital & Jiangsu Cancer Hospital & Jiangsu Institute of Cancer Research, 21009, Nanjing, China.
Jiangsu Key Laboratory of Molecular and Translational Cancer Research, Cancer Institute of Jiangsu Province, Nanjing, China.
NPJ Digit Med. 2025 Feb 2;8(1):77. doi: 10.1038/s41746-025-01472-x.
This study investigates the application of prompt engineering to optimize prompt-driven ChatGPT for generating electronic medical records (EMRs) during lung nodule screening. We assessed the performance of ChatGPT in generating EMRs from patient-provider verbal consultations and integrated this approach into practical tools, such as WeChat mini-programs, accessible to patients before hospital visits. The findings highlight ChatGPT's potential to enhance workflow efficiency and improve diagnostic processes in clinical settings.
本研究探讨了提示工程在优化基于提示的ChatGPT以生成肺结节筛查期间的电子病历(EMR)方面的应用。我们评估了ChatGPT从患者与医疗服务提供者的口头会诊中生成EMR的性能,并将这种方法集成到实用工具中,如患者在就诊前可访问的微信小程序。研究结果凸显了ChatGPT在提高临床工作流程效率和改善诊断过程方面的潜力。