Liao ChihYing, Chu ChinNan, Lin TingChun, Chou TzuYao, Tsai MengHsiun
Department of Radiation Oncology, China Medical University Hospital, Taichung City 404, Taiwan.
Graduate Institute of Clinical Medical Science, China Medical University, Taichung City 404, Taiwan.
Cancers (Basel). 2025 Jul 15;17(14):2345. doi: 10.3390/cancers17142345.
Electronic patient-reported outcomes (ePROs) enable real-time symptom monitoring and early intervention in oncology. Large language models (LLMs), when combined with retrieval-augmented generation (RAG), offer scalable Artificial Intelligence (AI)-driven education tailored to individual patient needs. However, few studies have examined the feasibility and clinical impact of integrating ePRO with LLM-RAG feedback during radiotherapy in high-toxicity settings such as head and neck cancer.
This prospective observational study enrolled 42 patients with head and neck cancer undergoing radiotherapy from January to December 2024. Patients completed ePRO entries twice weekly using a web-based platform. Following each entry, an LLM-RAG system (Gemini 1.5-based) generated real-time educational feedback using National Comprehensive Cancer Network (NCCN) guidelines and institutional resources. Primary outcomes included percentage weight loss and treatment interruption days. Statistical analyses included -tests, linear regression, and receiver operating characteristic (ROC) analysis. A threshold of ≥6 ePRO entries was used for subgroup analysis.
Patients had a mean age of 53.6 years and submitted an average of 8.0 ePRO entries. Frequent ePRO users (≥6 entries) had significantly less weight loss (4.45% vs. 7.57%, = 0.021) and fewer treatment interruptions (0.67 vs. 2.50 days, = 0.002). Chemotherapy, moderate-to-severe pain, and lower ePRO submission frequency were associated with greater weight loss. ePRO submission frequency was negatively correlated with both weight loss and treatment interruption days. The most commonly reported symptoms were appetite loss, fatigue, and nausea.
Integrating LLM-RAG feedback with ePRO systems is feasible and may enhance symptom control, treatment continuity, and patient engagement in head and neck cancer radiotherapy. Further studies are warranted to validate the clinical benefits of AI-supported ePRO platforms in routine care.
电子患者报告结局（ePROs）能够实现肿瘤学中的实时症状监测和早期干预。大语言模型（LLMs）与检索增强生成（RAG）相结合时，可提供针对个体患者需求的可扩展人工智能（AI）驱动的教育。然而，很少有研究探讨在头颈部癌等高毒性放疗环境中，将ePRO与LLM-RAG反馈相结合的可行性和临床影响。
这项前瞻性观察性研究纳入了2024年1月至12月期间接受放疗的42名头颈部癌患者。患者使用基于网络的平台每周完成两次ePRO条目填写。每次条目填写后，一个基于LLM-RAG的系统（基于Gemini 1.5）使用美国国立综合癌症网络（NCCN）指南和机构资源生成实时教育反馈。主要结局包括体重减轻百分比和治疗中断天数。统计分析包括t检验、线性回归和受试者工作特征（ROC）分析。亚组分析采用≥6条ePRO条目的阈值。
患者的平均年龄为53.6岁，平均提交8.0条ePRO条目。频繁使用ePRO的用户（≥6条条目）体重减轻明显较少（4.45%对7.57%，P = 0.021），治疗中断天数也较少（0.67天对2.50天，P = 0.002）。化疗、中重度疼痛和较低的ePRO提交频率与更大的体重减轻相关。ePRO提交频率与体重减轻和治疗中断天数均呈负相关。最常报告的症状是食欲减退、疲劳和恶心。
将LLM-RAG反馈与ePRO系统相结合是可行的，可能会增强头颈部癌放疗中的症状控制、治疗连续性和患者参与度。有必要进行进一步研究以验证人工智能支持的ePRO平台在常规护理中的临床益处。
