Confederated learning in healthcare: Training machine learning models using disconnected data separated by individual, data type and identity for Large-Scale health system Intelligence

[Display omitted] •Patients' data are horizontally separated by individual and vertically separated by type.•Confederated machine learning to model data both horizontally and vertically separated.•Real-world medical data from many locations across the country. A patient’s health information is...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of biomedical informatics 2022-10, Vol.134, p.104151-104151, Article 104151
Hauptverfasser: Liu, Dianbo, Fox, Kathe, Weber, Griffin, Miller, Tim
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:[Display omitted] •Patients' data are horizontally separated by individual and vertically separated by type.•Confederated machine learning to model data both horizontally and vertically separated.•Real-world medical data from many locations across the country. A patient’s health information is generally fragmented across silos because it follows how care is delivered: multiple providers in multiple settings. Though it is technically feasible to reunite data for analysis in a manner that underpins a rapid learning healthcare system, privacy concerns and regulatory barriers limit data centralization for this purpose. Machine learning can be conducted in a federated manner on patient datasets with the same set of variables but separated across storage. But federated learning cannot handle the situation where different data types for a given patient are separated vertically across different organizations and when patient ID matching across different institutions is difficult. We call methods that enable machine learning model training on data separated by two or more dimensions “confederated machine learning”, which we aim to develop in this study. We propose and evaluate confederated learning for training machine learning models to stratify the risk of several diseases among silos when data are horizontally separated by individual, vertically separated by data type, and separated by identity without patient ID matching. The confederated learning method can be intuitively understood as a distributed learning method with representation learning, generative model, imputation method and data augmentation elements. Our confederated learning method achieves AUCROC (Area Under The Curve Receiver Operating Characteristics) of 0.787 for diabetes prediction, 0.718 for psychological disorders prediction, and 0.698 for Ischemic heart disease prediction using nationwide health insurance claims. Our proposed confederated learning method successfully trained machine learning models on health insurance data separated by two or more dimensions.
ISSN:1532-0464
1532-0480
DOI:10.1016/j.jbi.2022.104151