Song Li, MD

Using machine learning, we identified and validated 3 distinct CS phenotypes, with specific and reproducible associations with mortality. These phenotypes may allow for targeted patient enrollment in clinical trials and foster development of tailored treatment strategies in subsets of patients with CS.

We report a novel approach to define SCAI stages and identify a significant association between baseline and maximum stage and mortality. This approach may improve clinical application of the staging system and provides new insight into the trajectory of hospitalized CS patients.

In a large contemporary HF-CS cohort, we identified a greater incidence of in-hospital death and cardiac arrest as well as a more rapid escalation to maximum SCAI stage severity among DNHF-CS. AMCS use in HF-CS was common, with significant heterogeneity among device types.