Deep Semi-Supervised Embedded Clustering (DSEC) for Stratification of Heart Failure Patients
This work aims to improve in-hospital patient care and drug development for heart failure patients by identifying data-driven subgroups, which could lead to improved treatments.
This paper addresses the challenge of identifying disease phenotypes in high-dimensional electronic health records by extending deep embedded clustering to a semi-supervised approach. They applied this method to stratify 4,487 heart failure and control patients, discovering clinically relevant clusters from heterogeneous data.
Determining phenotypes of diseases can have considerable benefits for in-hospital patient care and to drug development. The structure of high dimensional data sets such as electronic health records are often represented through an embedding of the data, with clustering methods used to group data of similar structure. If subgroups are known to exist within data, supervised methods may be used to influence the clusters discovered. We propose to extend deep embedded clustering to a semi-supervised deep embedded clustering algorithm to stratify subgroups through known labels in the data. In this work we apply deep semi-supervised embedded clustering to determine data-driven patient subgroups of heart failure from the electronic health records of 4,487 heart failure and control patients. We find clinically relevant clusters from an embedded space derived from heterogeneous data. The proposed algorithm can potentially find new undiagnosed subgroups of patients that have different outcomes, and, therefore, lead to improved treatments.