Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction
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 shari...
Guardado en:
Autores principales: | , , , , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/da14c3b27e7547969392b4a11ffd1ef0 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:da14c3b27e7547969392b4a11ffd1ef0 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:da14c3b27e7547969392b4a11ffd1ef02021-11-12T04:59:19ZLocal and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction2297-055X10.3389/fcvm.2021.787246https://doaj.org/article/da14c3b27e7547969392b4a11ffd1ef02021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fcvm.2021.787246/fullhttps://doaj.org/toc/2297-055XBackground: 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.Ricardo R. LopesRicardo R. LopesMarco MamprinJo M. ZelisPim A. L. ToninoMartijn S. van MourikMarije M. VisSvitlana ZingerBas A. J. M. de MolPeter H. N. de WithHenk A. MarqueringHenk A. MarqueringFrontiers Media S.A.articletranscatheter aortic valve implantation (TAVI)outcome predictionprognosismortality predictioninter-center cross-validationmachine learningDiseases of the circulatory (Cardiovascular) systemRC666-701ENFrontiers in Cardiovascular Medicine, Vol 8 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
transcatheter aortic valve implantation (TAVI) outcome prediction prognosis mortality prediction inter-center cross-validation machine learning Diseases of the circulatory (Cardiovascular) system RC666-701 |
spellingShingle |
transcatheter aortic valve implantation (TAVI) outcome prediction prognosis mortality prediction inter-center cross-validation machine learning Diseases of the circulatory (Cardiovascular) system RC666-701 Ricardo R. Lopes Ricardo R. Lopes Marco Mamprin Jo M. Zelis Pim A. L. Tonino Martijn S. van Mourik Marije M. Vis Svitlana Zinger Bas A. J. M. de Mol Peter H. N. de With Henk A. Marquering Henk A. Marquering Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction |
description |
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. |
format |
article |
author |
Ricardo R. Lopes Ricardo R. Lopes Marco Mamprin Jo M. Zelis Pim A. L. Tonino Martijn S. van Mourik Marije M. Vis Svitlana Zinger Bas A. J. M. de Mol Peter H. N. de With Henk A. Marquering Henk A. Marquering |
author_facet |
Ricardo R. Lopes Ricardo R. Lopes Marco Mamprin Jo M. Zelis Pim A. L. Tonino Martijn S. van Mourik Marije M. Vis Svitlana Zinger Bas A. J. M. de Mol Peter H. N. de With Henk A. Marquering Henk A. Marquering |
author_sort |
Ricardo R. Lopes |
title |
Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction |
title_short |
Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction |
title_full |
Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction |
title_fullStr |
Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction |
title_full_unstemmed |
Local and Distributed Machine Learning for Inter-hospital Data Utilization: An Application for TAVI Outcome Prediction |
title_sort |
local and distributed machine learning for inter-hospital data utilization: an application for tavi outcome prediction |
publisher |
Frontiers Media S.A. |
publishDate |
2021 |
url |
https://doaj.org/article/da14c3b27e7547969392b4a11ffd1ef0 |
work_keys_str_mv |
AT ricardorlopes localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction AT ricardorlopes localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction AT marcomamprin localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction AT jomzelis localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction AT pimaltonino localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction AT martijnsvanmourik localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction AT marijemvis localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction AT svitlanazinger localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction AT basajmdemol localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction AT peterhndewith localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction AT henkamarquering localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction AT henkamarquering localanddistributedmachinelearningforinterhospitaldatautilizationanapplicationfortavioutcomeprediction |
_version_ |
1718431199578292224 |