Lopes Ricardo R, Mamprin Marco, Zelis Jo M, Tonino Pim A L, van Mourik Martijn S, Vis Marije M, Zinger Svitlana, de Mol Bas A J M, de With Peter H N, Marquering Henk A
Department of Biomedical Engineering and Physics, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands.
Department of Radiology and Nuclear Medicine, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, Netherlands.
Front Cardiovasc Med. 2021 Nov 12;8:787246. doi: 10.3389/fcvm.2021.787246. eCollection 2021.
Machine learning models have been developed for numerous medical prognostic purposes. These models are commonly developed using data from single centers or regional registries. Including data from multiple centers improves robustness and accuracy of prognostic models. However, data sharing between multiple centers is complex, mainly because of regulations and patient privacy issues. We aim to overcome data sharing impediments by using distributed ML and local learning followed by model integration. We applied these techniques to develop 1-year TAVI mortality estimation models with data from two centers without sharing any data. A distributed ML technique and local learning followed by model integration was used to develop models to predict 1-year mortality after TAVI. We included two populations with 1,160 (Center A) and 631 (Center B) patients. Five traditional ML algorithms were implemented. The results were compared to models created individually on each center. The combined learning techniques outperformed the mono-center models. For center A, the combined local XGBoost achieved an AUC of 0.67 (compared to a mono-center AUC of 0.65) and, for center B, a distributed neural network achieved an AUC of 0.68 (compared to a mono-center AUC of 0.64). This study shows that distributed ML and combined local models techniques, can overcome data sharing limitations and result in more accurate models for TAVI mortality estimation. We have shown improved prognostic accuracy for both centers and can also be used as an alternative to overcome the problem of limited amounts of data when creating prognostic models.
机器学习模型已被开发用于众多医学预后目的。这些模型通常使用来自单一中心或区域登记处的数据来开发。纳入多个中心的数据可提高预后模型的稳健性和准确性。然而，多个中心之间的数据共享很复杂，主要是因为法规和患者隐私问题。我们旨在通过使用分布式机器学习和局部学习然后进行模型整合来克服数据共享障碍。我们应用这些技术，利用来自两个中心的数据开发1年经导管主动脉瓣置换术（TAVI）死亡率估计模型，而无需共享任何数据。一种分布式机器学习技术和局部学习然后进行模型整合被用于开发预测TAVI术后1年死亡率的模型。我们纳入了两组人群，分别有1160名患者（中心A）和631名患者（中心B）。实施了五种传统机器学习算法。将结果与在每个中心单独创建的模型进行比较。联合学习技术优于单中心模型。对于中心A，联合局部极端梯度提升（XGBoost）模型的曲线下面积（AUC）为0.67（单中心AUC为0.65），对于中心B，分布式神经网络模型的AUC为0.68（单中心AUC为0.64）。这项研究表明，分布式机器学习和联合局部模型技术可以克服数据共享限制，并产生更准确的TAVI死亡率估计模型。我们已证明两个中心的预后准确性均有所提高，并且在创建预后模型时也可作为克服数据量有限问题的一种替代方法。
