Federated learning of predictive models from federated Electronic Health Records

By Theodora S. Brisimi, Ruidi Chen, Theofanie Mela, Alexander Olshevsky, Ioannis Ch. Paschalidis, Wei Shi. 2018

938 citations recorded by the source corpus.

Background In an era of “big data,” computationally efficient and privacy-aware solutions for large-scale machine learning problems become crucial, especially in the healthcare domain, where large amounts of data are stored in different locations and owned by different entities. Past research has been focused on centralized algorithms, which assume the existence of a central data repository (database) which stores and can process the data from all participants. Such an architecture, however, can be impractical when data are not centrally located, it does not scale well to very large datasets, and introduces single-point of failure risks which could compromise the integrity and privacy of the data. Given scores of data widely spread across hospitals/individuals, a decentralized computationally scalable methodology is very much in need. Objective We aim at solving a binary supervised classification problem to predict hospitalizations for cardiac events using a distributed algorithm. We seek to develop a general decentralized optimization framework enabling multiple data holders to collaborate and converge to a common predictive model, without explicitly exchanging raw data. Methods We focus on the soft-margin l1-regularized sparse Support Vector Machine (sSVM) classifier. We develop an iterative cluster Primal Dual Splitting (cPDS) algorithm for solving the large-scale sSVM problem in a decentralized fashion. Such a distributed learning scheme is relevant for multi-institutional collaborations or peer-to-peer applications, allowing the data holders to collaborate, while keeping every participant’s data private. Results We test cPDS on the problem of predicting hospitalizations due to heart diseases within a calendar year based on information in the patients Electronic Health Records prior to that year. cPDS converges faster than centralized methods at the cost of some communication between agents. It also converges faster and with less communication overhead compared to an alternative distributed algorithm. In both cases, it achieves similar prediction accuracy measured by the Area Under the Receiver Operating Characteristic Curve (AUC) of the classifier. We extract important features discovered by the algorithm that are predictive of future hospitalizations, thus providing a way to interpret the classification results and inform prevention efforts.

Subfields: Artificial Intelligence, Health Information Management, 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 Artificial Intelligence

  1. Qiang Yang
  2. Peter Richtárik
  3. Jakub Konecný
  4. Martin Jaggi
  5. Dacheng Tao
  6. Virginia Smith
  7. Sebastian U. Stich
  8. Yang Liu

In Health Information Management

  1. Arne Küderle
  2. Mike Tse
  3. Muhammad Bilal
  4. Ala Al-Fuqaha
  5. Rodolfo Stoffel Antunes
  6. Aruna Prasad Seneviratne
  7. Cristiano André da Costa
  8. Ming Ding

In Federated & Distributed Learning

  1. Virginia Smith
  2. Jakub Konecný
  3. Qiang Yang
  4. Bingsheng He
  5. Qinbin Li
  6. Tian Li
  7. Zachary B. Charles
  8. Sebastian U. Stich

In Medical & Health AI

  1. Arne Küderle
  2. Mike Tse
  3. Dacheng Tao
  4. Rodolfo Stoffel Antunes
  5. Cristiano André da Costa
  6. Jing Zhang
  7. Qiang Yang
  8. Fei Wang

Citations in the corpus