Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia.

ABSTRACT: The objective of this study was to characterize patients with hyponatremia at hospital admission into clusters using an unsupervised machine learning approach, and to evaluate the short- and long-term mortality risk among these distinct clusters. We performed consensus cluster analysis based on demographic information, principal diagnoses, comorbidities, and laboratory data among 11,099 hospitalized adult hyponatremia patients with an admission serum sodium below 135 mEq/L. The standardized mean difference was utilized to identify each cluster's key features. We assessed the association of each hyponatremia cluster with hospital and one-year mortality using logistic and Cox proportional hazard analysis, respectively. There were three distinct clusters of hyponatremia patients: 2033 (18%) i

SUBMITTER: Thongprayoon C 

PROVIDER: S-EPMC8395840 | biostudies-literature | 2021 Aug

REPOSITORIES: biostudies-literature