可计算放射治疗表型的开发与验证
本研究基于2014至2023年美国退伍军人健康数据,利用结构化编码与非结构化临床笔记开发并验证了一种识别接受放射治疗患者的可计算表型算法。最终队列纳入589318名接受放射肿瘤治疗的患者,其中355276名有放射治疗实施编码,与人工病历审查数据比对显示高度一致,证实算法准确性。该方法有望实现更精确的放疗病例表型分型。
要点
- 基于行政编码与临床笔记文本可自动识别接受放疗的患者队列。
- 最终队列含589318名退伍军人,其中355276名有放疗实施编码。
- 算法与病历审查数据高度一致,验证了识别准确性。
核心结论
- 自动化提取医疗记录可用于识别接受放射治疗的患者队列。
- 该算法可能促进更精确的放疗病例表型分型并加深对队列的理解。
研究设计与样本
- 回顾性队列研究,数据来源为2014至2023年退伍军人放射肿瘤诊疗的转诊、就诊及计费记录。
- 按诊疗流程和放疗类型对行政编码分类并分析使用模式,同时对临床笔记元数据字段进行关键词搜索并按放疗流程分类。
- 通过将算法构建的队列与病历审查队列比较来验证算法。
主要发现
- 最终队列包含589318名接受放射肿瘤治疗的退伍军人。
- 其中355276名退伍军人有指示放射治疗实施的编码。
- 最常见治疗为图像引导放疗、三维适形放疗、调强放疗和立体定向放射外科/立体定向体部放疗。
- 解剖部位特异性计费编码使用不足。
- 临床笔记分析识别出1341个放射肿瘤内容唯一标签,在204064名患者中找到947928份笔记。
临床怎么用
- 可利用结构化编码与非结构化临床笔记自动识别接受放疗的患者队列。
- 该算法可用于放疗病例的精确表型分型,支持治疗结局研究。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: This study aims to develop a robust methodology using structured and semistructured health data to identify patients who have undergone radiation therapy, thereby facilitating future research on treatment outcomes. METHODS AND MATERIALS: In this retrospective cohort study, we identified Veterans receiving radiation oncology care through documentation of referrals, encounters, and billing codes from 2014 to 2023. We classified administrative codes based on the process of care and type of radiation received and then analyzed utilization patterns. Unstructured data analysis was performed using keyword search of relevant clinical notes in the metadata fields and categorizing those notes by radiation oncology processes. To validate our algorithm, we compared the cohort we developed using existing data sources to a cohort that was chart reviewed. RESULTS: The final cohort included 589,318 Veterans with radiation oncology care. Among these, 355,276 Veterans had codes indicating radiation therapy delivery. The most common treatments were image guided radiation therapy, 3-dimensional conformal radiation therapy, intensity modulated radiation therapy, and stereotactic radiosurgery/stereotactic body radiation therapy. Anatomy-specific billing codes were underutilized. Clinical note analysis identified 1341 unique labels for radiation oncology content, with 947,928 notes found for 204,064 patients. Validation against chart-reviewed data sets showed strong concordance and confirmed the accuracy of our algorithm in identifying radiation oncology care. CONCLUSIONS: Automated extraction of medical records can be used to identify cohorts of patients who have undergone radiation therapy. Employing this algorithm may facilitate more precise phenotyping of radiation therapy cases and thus significantly enhance our understanding of these cohorts.
引用
- Madison CJ, Lynch JA, Duvall SL, et al. Development and Validation of a Computable Radiation Therapy Phenotype. Int J Radiat Oncol Biol Phys. 2025. PMID: 40374061. doi:10.1016/j.ijrobp.2025.05.001
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。