Patient-centered research is increasingly important in narrowing the gap between research and patient care, yet incorporating patient perspectives into health research has been inconsistent. We propose an automated framework leveraging innovative natural language processing (NLP) and artificial intelligence (AI) with patient portal messages to generate research ideas that prioritize important patient issues. We further quantified the quality of AI-generated research topics. To define patient clinical concerns, we analyzed 614,464 patient messages from 25,549 individuals with breast or skin cancer obtained from a large academic hospital (2013 to 2024), constructing a 2-staged unsupervised NLP topic model. Then, we generated research topics to resolve the defined issues using a widely used AI (ChatGPT-4o, OpenAI Inc, April 2024 version) with prompt-engineering strategies. We guided AI to perform multi-level tasks: 1) knowledge interpretation and summarization (e.g., interpreting and summarizing the NLP-defined topics), 2) knowledge generation (e.g., generating research ideas corresponding to patients issues), 3) self-reflection and correction (e.g., ensuring and revising the research ideas after searching for scientific articles), and 4) self-reassurance (e.g., confirming and finalizing the research ideas). Six highly experienced breast oncologists and dermatologists assessed the significance and novelty of AI-generated research topics using a 5-point Likert scale (1-exceptional, 5-poor). One-third of the AI-suggested research topics were highly significant and novel when both scores were lower than the average. Two-thirds of the AI-suggested topics were novel in both cancers. Our findings demonstrate that AI-generated research topics reflecting patient perspectives via a large volume of patient messages can meaningfully guide future directions in patient-centered health research.

翻译：以患者为中心的研究对于缩小研究与临床护理之间的差距日益重要，然而将患者视角纳入健康研究的过程仍不一致。我们提出一个自动化框架，利用创新的自然语言处理（NLP）和人工智能（AI）技术，结合患者门户消息，生成优先关注重要患者议题的研究构想。我们进一步量化了AI生成研究主题的质量。为界定患者的临床关切，我们分析了来自一家大型学术医院（2013年至2024年）25,549名乳腺癌或皮肤癌患者的614,464条消息，构建了一个两阶段无监督NLP主题模型。随后，我们使用广泛应用的AI（ChatGPT-4o，OpenAI公司，2024年4月版本）结合提示工程策略，生成旨在解决所界定问题的研究主题。我们引导AI执行多层次任务：1）知识解释与总结（例如，解释和总结NLP定义的主题），2）知识生成（例如，生成与患者问题对应的研究构想），3）自我反思与修正（例如，在检索科学文献后确保并修订研究构想），以及4）自我确认（例如，确认并最终确定研究构想）。六位经验丰富的乳腺肿瘤学家和皮肤科医生使用5点李克特量表（1-极佳，5-极差）评估了AI生成研究主题的重要性和新颖性。当两项得分均低于平均值时，三分之一由AI建议的研究主题具有高度重要性和新颖性。在两种癌症中，三分之二的AI建议主题具有新颖性。我们的研究结果表明，通过大量患者消息反映患者视角的AI生成研究主题，能够有意义地指导未来以患者为中心的健康研究方向。