Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction.

Ricardo R Lopes,Pim A L Tonino,Marije M Vis,Marco Mamprin,Henk A Marquering,Martijn S Van Mourik,Peter H N De With,Bas A J M De Mol,Jo M Zelis,Svitlana Zinger

doi:10.3389/fcvm.2021.787246

Abstract

Background: 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.Objective: 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.Methods: 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.Results: 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).Conclusion: 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.

Highlights

Transcatheter Aortic Valve Implantation (TAVI) is a consolidated procedure for aortic stenosis treatment
Models to predict 1-year modality were created with data from a total of 1,791 patients who underwent TAVI procedures in two distinct centers were included in this study
The stacked models with the highest accuracies achieved a receiver operating characteristic (ROC) area under the curve (AUC) of 0.65. This accuracy was achieved by three models; CATB, XGB and the Neural Networks (NN) with a narrow architecture

Summary

Introduction

Transcatheter Aortic Valve Implantation (TAVI) is a consolidated procedure for aortic stenosis treatment. Mortality estimation models have shown limited prediction accuracy when tested on other center’s populations than the one used to generate the models [5,6,7,8] This can be explained by the different distribution in the populations, given by different patient selection or practice variation among institutions. Mitigating the models’ accuracy drop on different populations is essential to obtain models with higher generalization capability For this purpose, model updating or fine-tuning have been used successfully [9, 10]. Machine learning models have been developed for numerous medical prognostic purposes These models are commonly developed using data from single centers or regional registries. Data sharing between multiple centers is complex, mainly because of regulations and patient privacy issues

Methods

Results

Discussion

Conclusion