机器学习模型预测左侧乳腺癌放疗DIBH不合格:开发、验证与临床影响分析
这项前瞻性队列研究用202例患者数据开发机器学习模型,仅基于首日DIBH评估数据预测左侧乳腺癌患者DIBH不合格。未校准梯度提升集成模型表现最佳(AUC 0.803,95%CI 0.686-0.941;Recall 0.526)。临床影响研究提示该模型最多可减少20%的额外DIBH评估需求,且未将合格患者误分类。
要点
- 模型仅用首日DIBH评估数据预测不合格,最佳模型AUC为0.803(95%CI 0.686-0.941)。
- 临床影响研究提示模型最多减少20%额外DIBH评估需求,且未误分类合格患者。
- 作者认为该模型可作为资源有限或繁忙科室患者选择的决策辅助工具。
核心结论
- 开发的机器学习模型仅用首日DIBH评估数据即可准确预测DIBH不合格,作者认为可作为资源有限或繁忙科室患者选择的决策辅助工具。
- 作者指出需外部验证以确认其普遍适用性。
研究设计与样本
- 前瞻性队列研究,使用2023年1月至12月收集的202例患者数据开发模型。
- 最佳模型在2024年1月至3月的前瞻性数据集47例患者中进行时间验证。
- 另在2024年4月至8月的前瞻性队列64例患者中开展临床影响研究,通过比较模型预测与临床团队决定是否行DIBH治疗来评估实用价值。
主要发现
- 未校准梯度提升集成模型表现最高,AUC(95%CI)=0.803(0.686-0.941),Recall=0.526,决策曲线分析净获益最佳。
- 关键预测因素包括平均屏气持续时间和较低屏气幅度水平。
- 临床影响研究提示模型最多减少20%的额外DIBH评估需求,且未将合格患者误分类。
关键数值与推荐
- 模型纳入变量包括上、下及平均屏气幅度、平均屏气持续时间、屏气一致性。
- 评估了九种机器学习算法和三种建模策略,并用决策曲线分析选择最佳模型。
临床怎么用
- 作者认为该模型可作为资源有限或繁忙科室中患者选择的决策辅助工具。
局限性
- 作者指出需外部验证以确认模型的普遍适用性。
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
OBJECTIVE: Multi-day assessments accurately identify patients with left-sided breast cancer who are ineligible for irradiation in Deep Inspiration Breath Hold (DIBH) and minimise on-couch treatment time in those who are eligible. The challenge of implementing multi-day assessments in resource-constrained settings motivated the development of a machine learning (ML) model using data only from the 1st day of assessment to predict DIBH ineligibility. METHODS: This prospective cohort study used data from 202 patients collected between January and December 2023 for model development. Patient-related and DIBH assessment-related variables (upper, lower, and average breath-hold amplitude; average breath-hold duration; breath-hold consistency) were included. Nine ML algorithms (and three modelling strategies) were evaluated, and a decision curve analysis was used to select the best model. The best model was temporally validated on a prospective dataset of 47 patients (January to March 2024). Further, a clinical impact study on another prospective cohort of 64 patients (April to August 2024) was performed, to assess its practical utility by comparing its predictions with the clinical team's decision to treat a patient in DIBH or not. RESULTS: The uncalibrated gradient-boosting ensemble model demonstrated the highest performance [AUC (95 % CI) = 0.803 (0.686-0.941); Recall = 0.526] and net benefit in decision curve analysis. Key predictors included average breath-hold duration and lower breath-hold amplitude levels. The clinical impact study suggests that the model reduces the need for additional DIBH assessments by up to 20 % without misclassifying eligible patients. CONCLUSION: The developed ML model accurately predicts DIBH ineligibility using only first-day DIBH assessment data and could be a decision aid for patient selection in resource-constrained or busy departments. External validation is necessary to confirm its generalizability.
引用
- Chufal KS, Ahmad I, Miller AA, et al. Machine learning model for predicting DIBH non-eligibility in left-sided breast cancer radiotherapy: Development, validation and clinical impact analysis. Radiother Oncol. 2025. PMID: 39894262. doi:10.1016/j.radonc.2025.110764
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。