Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China.
Department of Surgical Oncology, Second affiliated hospital, Zhejiang University School of Medicine, Hangzhou, China.
Artif Intell Med. 2021 Mar;113:102024. doi: 10.1016/j.artmed.2021.102024. Epub 2021 Jan 23.
Clinical decision support assisted by prediction models usually faces the challenges of limited clinical data and a lack of labels when the model is developed with data from a single medical institution. Accordingly, research on multicenter clinical collaborative networks, which can provide external medical data, has received increasing attention. With the increasing availability of machine learning techniques such as transfer learning, leveraging large-scale patient data from multiple hospitals to build data-driven predictive models with clinical application potential provides an alternative solution to address the problem of limited patient data.
A multicenter hybrid semi-supervised transfer learning model (MHSTL) is proposed in this study on the basis of unified common data model to ensure multicenter data standardized representation. Then the hospital-specific features, along with the co-occurrence features across domains, are aligned through a representation learning architecture that is built based on deep neural networks and the newly proposed neural decision forest model. In this process, limited patient data from the target hospital, both labeled and unlabeled, are incorporated during the feature adaptation process, thereby contributing to better model performance. Without patient-level data sharing, the proposed model learning strategy which overcomes feature misalignment and distribution divergence, enables the multi-source transfer learning process in the case of insufficient and unlabeled patient data at target hospital.
The effectiveness of the proposed transfer learning model was evaluated on a collaborative research network of colorectal cancer patients in the US and China. The results demonstrate that the proposed model can achieve much better performance for predicting target risk with limited resources on patient data than baseline models . Better discrimination and calibration ability are also observed when sufficient labeled data are not available in the target hospital for prognosis prediction tasks . Further exploratory experiments show that the proposed approach exhibits good model generalizability regardless of the data heterogeneity. With the help of the SHapley Additive exPlanations for model interpretation, the effectiveness of incorporating hospital-specific features in the transfer learning model is shown.
In this study, the proposed method can develop prediction models from multiple source hospitals and exhibit good performance by leveraging cross-domain hospital-specific feature information, therefore enhancing the model prediction when applied to single medical institution with limited patient data.
临床决策支持通常会受到模型开发时所使用的单一医疗机构数据有限且缺乏标签的挑战。因此，研究多中心临床协作网络，以提供外部医疗数据，受到了越来越多的关注。随着迁移学习等机器学习技术的日益普及，可以利用来自多个医院的大规模患者数据来构建具有临床应用潜力的数据驱动预测模型，这为解决患者数据有限的问题提供了另一种解决方案。
本研究在统一通用数据模型的基础上提出了一种多中心混合半监督迁移学习模型（MHSTL），以确保多中心数据的标准化表示。然后，通过基于深度神经网络和新提出的神经决策森林模型构建的表示学习架构，对齐医院特有的特征以及跨域的共同出现特征。在这个过程中，在特征适配过程中纳入目标医院的有限患者数据（包括有标签和无标签数据），从而提高模型性能。在不共享患者级数据的情况下，所提出的模型学习策略克服了特征失配和分布发散问题，从而实现了在目标医院患者数据不足和无标签的情况下进行多源迁移学习过程。
该迁移学习模型的有效性在中国和美国的结直肠癌患者协作研究网络上进行了评估。结果表明，与基线模型相比，该模型在利用有限的患者数据资源预测目标风险时可以实现更好的性能。在目标医院没有足够的有标签数据进行预后预测任务时，也观察到更好的区分和校准能力。进一步的探索性实验表明，无论数据异质性如何，所提出的方法都表现出良好的模型泛化能力。借助模型解释的 Shapley Additive exPlanations（SHAP）方法，证明了在迁移学习模型中纳入医院特有特征的有效性。
本研究提出的方法可以从多个源医院开发预测模型，并通过利用跨域医院特有特征信息来提高模型性能，从而在应用于患者数据有限的单一医疗机构时增强模型预测能力。
