Patient Clustering Improves Efficiency of Federated Machine Learning to predict mortality and hospital stay time using distributed Electronic Medical Records

By Li Huang, Dianbo Liu. 2019

424 citations recorded by the source corpus.

Electronic medical records (EMRs) support the development of machine learning algorithms for predicting disease incidence, patient response to treatment, and other healthcare events. But so far most algorithms have been centralized, taking little account of the decentralized, non-identically independently distributed (non-IID), and privacy-sensitive characteristics of EMRs that can complicate data collection, sharing and learning. To address this challenge, we introduced a community-based federated machine learning (CBFL) algorithm and evaluated it on non-IID ICU EMRs. Our algorithm clustered the distributed data into clinically meaningful communities that captured similar diagnoses and geographical locations, and learnt one model for each community. Throughout the learning process, the data was kept local at hospitals, while locally-computed results were aggregated on a server. Evaluation results show that CBFL outperformed the baseline federated machine learning (FL) algorithm in terms of Area Under the Receiver Operating Characteristic Curve (ROC AUC), Area Under the Precision-Recall Curve (PR AUC), and communication cost between hospitals and the server. Furthermore, communities' performance difference could be explained by how dissimilar one community was to others.

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

In Health Information Management

In Federated & Distributed Learning

In Medical & Health AI

Citations in the corpus

LoAdaBoost: Loss-based AdaBoost federated machine learning with reduced computational complexity on IID and non-IID intensive care data (2018, methodology): “used a federated transfer learning strategy to balance global and local learning [13–16,20].”
End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things (2020, background): “However, data can often be highly private or sensitive; for example, data collected from medical sensors [4] and microphones [5] would be such cases.”
A Superquantile Approach to Federated Learning with Heterogeneous Devices (2021, background): “Federated learning has found myriad applications such as smartphone apps [3, 4] and healthcare [5].”
A review of applications in federated learning (2020, methodology): “For data pre-processing, Huang et al., (2019) introduced clustering thought with FL and constructed a community-based FL method.”
A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond (2021, background): “The devices of the users/clients in current studies are varying between smartphones [4], [5], IoT devices [6]–[9], healthcare devices [10], [11], robots [12], vehicles [13], [14], and many more.”
Privacy Preserving Machine Learning with Homomorphic Encryption and Federated Learning (2021, background): “In the medical ﬁeld, patients’ medical data are sensitive, thus federated learning is very useful [40,41].”
Federated Multi-view Learning for Private Medical Data Integration and Analysis (2021, methodology): “For example, FL can be used to process EHR data distributed in multiple hospitals by sharing the local model instead of the patients’ data to prevent the raw data leakage [6, 7, 27, 37].”
Towards Personalized Federated Learning (2021, background): “Huang et al. [69] proposed community-based FL (CBFL) to predict patient hospitalization time and mortality.”
Federated Learning for Healthcare Informatics (2019, methodology): “[45] sought to tackle the challenge of non-IID ICU patient data by clustering patients into clinically meaningful communities that”
A Survey on federated learning* (2020, methodology): “For data pre-processing, Huang & Liu introduced clustering thought and constructed a community-based FL method [28].”
Two-stage Federated Phenotyping and Patient Representation Learning (2019, background): “Federated machine learning is a concept that machine learning models are trained in a distributed and collaborative manner without centralised data (Liu et al., 2018a; McMahan et al., 2016; Bonawitz et al., 2019; Konečnỳ et al., 2016; Huang et al., 2018; Huang and Liu, 2019).”