Federated Tensor Factorization for Computational Phenotyping

By Yejin Kim, Jimeng Sun, Hwanjo Yu, Xiaoqian Jiang. 2017

129 citations recorded by the source corpus.

Tensor factorization models offer an effective approach to convert massive electronic health records into meaningful clinical concepts (phenotypes) for data analysis. These models need a large amount of diverse samples to avoid population bias. An open challenge is how to derive phenotypes jointly across multiple hospitals, in which direct patient-level data sharing is not possible (e.g., due to institutional policies). In this paper, we developed a novel solution to enable federated tensor factorization for computational phenotyping without sharing patient-level data. We developed secure data harmonization and federated computation procedures based on alternating direction method of multipliers (ADMM). Using this method, the multiple hospitals iteratively update tensors and transfer secure summarized information to a central server, and the server aggregates the information to generate phenotypes. We demonstrated with real medical datasets that our method resembles the centralized training model (based on combined datasets) in terms of accuracy and phenotypes discovery while respecting privacy.

Subfields: Computational Mathematics, Federated & Distributed Learning, Medical & Health AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mathematics

In Federated & Distributed Learning

In Medical & Health AI

Citations in the corpus

Advances and Open Problems in Federated Learning (2019, methodology): “Among the existing works, [236] used an alternating direction method of multipliers (ADMM) based approach and [280] improved the efficiency with the elastic averaging SGD (EASGD) algorithm and further ensures differential privacy for the intermediate factors.”
Privacy-Preserving Tensor Factorization for Collaborative Health Data Analysis (2019, methodology): “Recent studies have suggested that the integration of health records can provide more benefits [12], which motivated the application of federated tensor learning framework [20].”
Federated Multi-view Learning for Private Medical Data Integration and Analysis (2021, background): “proposed a federated tensor factorization framework for horizontally partitioned data [34].”
Federating Recommendations Using Differentially Private Prototypes (2020, background): “Kim et al. (2017) consider federated tensor factorization for computational phenotyping.”
FedHome: Cloud-Edge Based Personalized Federated Learning for In-Home Health Monitoring (2020, background): “Kim et al. convert massive electronic health records into meaningful phenotypes for data analysis by iteratively transferring secure summarized information of hospitals to a central server in federated settings [13].”
L G ] 1 1 A pr 2 01 7 Federated Tensor Factorization for Computational Phenotyping (2018, background): “Due to limited space, medication factors in phenotypes are omied and can be found in our project website [17].”
Federated Learning for Healthcare Informatics (2019, methodology): “[55] used tensor factorization models to convert massive electronic health records into meaningful phenotypes for data analysis in federated learning setting.”
COPA: Constrained PARAFAC2 for Sparse & Large Datasets (2018, unknown): “1 INTRODUCTION Tensor factorization encompasses a set of powerful analytic methods that been successfully applied in many application domains: social network analysis, urban planning, text mining, and health analytics [2, 13, 14, 17, 18, 25].”
Federated Learning for Healthcare: Systematic Review and Architecture Proposal (2022, methodology): “Kim et al. [23] propose a federated tensor factorization method that iteratively trains and aggregates a learning model to extract phenotypes from EHR datasets.”