分布式学习:基于多院数据构建预测模型而不共享原始数据
该研究探讨了分布式学习在无需数据离开医院的前提下,利用5家医疗机构共287例接受根治性放化疗或单纯放疗的肺癌患者数据训练贝叶斯网络模型,预测放疗后呼吸困难。模型在5折交叉验证中AUC为0.61(95%CI,0.51-0.70),外部验证集AUC范围为0.59至0.71。结论表明分布式学习可在规避数据共享障碍的同时构建预测模型。
要点
- 分布式学习可在不共享原始数据的情况下利用多院数据训练预测模型。
- 贝叶斯网络模型预测肺癌放疗后呼吸困难,交叉验证AUC为0.61。
- 外部验证集AUC范围为0.59至0.71,显示一定泛化能力。
核心结论
- 分布式学习可允许基于多院数据学习预测模型,同时避免许多数据共享障碍。
- 该方法可从多院常规患者数据中提取和利用知识,并符合各国及欧洲隐私法律。
研究设计与样本
- 研究纳入5家医疗机构的287例接受根治性放化疗或单纯放疗的肺癌患者临床数据。
- 采用适配分布式学习的贝叶斯网络模型,预测放疗后呼吸困难。
- 模型通过5折交叉验证及外部验证集进行评估。
主要发现
- 模型在5折交叉验证中AUC为0.61(95%CI,0.51-0.70)。
- 模型在外部验证集上AUC范围为0.59至0.71。
临床怎么用
- 分布式学习可在不共享原始数据的前提下,利用多院数据构建和验证放疗毒性预测模型。
- 该方法有助于在遵守隐私法规的同时整合多中心常规数据用于模型开发。
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: One of the major hurdles in enabling personalized medicine is obtaining sufficient patient data to feed into predictive models. Combining data originating from multiple hospitals is difficult because of ethical, legal, political, and administrative barriers associated with data sharing. In order to avoid these issues, a distributed learning approach can be used. Distributed learning is defined as learning from data without the data leaving the hospital. PATIENTS AND METHODS: Clinical data from 287 lung cancer patients, treated with curative intent with chemoradiation (CRT) or radiotherapy (RT) alone were collected from and stored in 5 different medical institutes (123 patients at MAASTRO (Netherlands, Dutch), 24 at Jessa (Belgium, Dutch), 34 at Liege (Belgium, Dutch and French), 48 at Aachen (Germany, German) and 58 at Eindhoven (Netherlands, Dutch)). A Bayesian network model is adapted for distributed learning (watch the animation: http://youtu.be/nQpqMIuHyOk). The model predicts dyspnea, which is a common side effect after radiotherapy treatment of lung cancer. RESULTS: We show that it is possible to use the distributed learning approach to train a Bayesian network model on patient data originating from multiple hospitals without these data leaving the individual hospital. The AUC of the model is 0.61 (95%CI, 0.51-0.70) on a 5-fold cross-validation and ranges from 0.59 to 0.71 on external validation sets. CONCLUSION: Distributed learning can allow the learning of predictive models on data originating from multiple hospitals while avoiding many of the data sharing barriers. Furthermore, the distributed learning approach can be used to extract and employ knowledge from routine patient data from multiple hospitals while being compliant to the various national and European privacy laws.
引用
- Jochems A, Deist TM, van Soest J, et al. Distributed learning: Developing a predictive model based on data from multiple hospitals without data leaving the hospital - A real life proof of concept. Radiother Oncol. 2016. PMID: 28029405. doi:10.1016/j.radonc.2016.10.002
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。