Phenotyping Cardiogenic Shock

Abstract

Background Cardiogenic shock (CS) is a heterogeneous syndrome with varied presentations and outcomes. We used a machine learning approach to test the hypothesis that patients with CS have distinct phenotypes at presentation, which are associated with unique clinical profiles and in‐hospital mortality. Methods and Results We analyzed data from 1959 patients with CS from 2 international cohorts: CSWG (Cardiogenic Shock Working Group Registry) (myocardial infarction [CSWG‐MI; n=410] and acute‐on‐chronic heart failure [CSWG‐HF; n=480]) and the DRR (Danish Retroshock MI Registry) (n=1069). Clusters of patients with CS were identified in CSWG‐MI using the consensus k means algorithm and subsequently validated in CSWG‐HF and DRR. Patients in each phenotype were further categorized by their Society of Cardiovascular Angiography and Interventions staging. The machine learning algorithms revealed 3 distinct clusters in CS: "non‐congested (I)", "cardiorenal (II)," and "cardiometabolic (III)" shock. Among the 3 cohorts (CSWG‐MI versus DDR versus CSWG‐HF), in‐hospital mortality was 21% versus 28% versus 10%, 45% versus 40% versus 32%, and 55% versus 56% versus 52% for clusters I, II, and III, respectively. The "cardiometabolic shock" cluster had the highest risk of developing stage D or E shock as well as in‐hospital mortality among the phenotypes, regardless of cause. Despite baseline differences, each cluster showed reproducible demographic, metabolic, and hemodynamic profiles across the 3 cohorts. Conclusions 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.

Validation of cardiogenic shock phenotypes in a mixed cardiac intensive care unit population

“…This severely ill “hemometabolic” cluster had twofold higher in‐hospital mortality, even after adjustment for the severity of shock and overall critical illness. This emphasizes the importance of hemometabolic shock, defined by kidney and liver injury with metabolic acidosis, as a high‐risk phenotype of CS 7,14 . It is notable that substantial differences between the phenotypes exist regarding hemodynamics and echocardiographic variables despite clustering using a limited number of laboratory variables.…”

“…Zweck et al 7 recently used an unsupervised machine learning clustering approach to identify three proposed subpopulations in a multicenter CS cohort, which were labeled as phenotypes within the CS population. These three proposed phenotypes—“noncongested” (low‐risk), “cardiorenal” (intermediate‐risk), and “hemometabolic” (high‐risk)—were associated with a mortality gradient independent from shock severity.…”

Heart Failure-Related Cardiogenic Shock: Pathophysiology, Evaluation and Management Considerations

“…2,14À16 More recently, 3 distinct CS phenotypes (noncongested, cardiorenal and cardiometabolic shock) were identified by using a supervised machine learning approach and were validated in both AMI-CS and HF-CS populations by 2 independent multicenter cohorts. 17 These phenotypes differed based on demographic, hemodynamic and metabolic profiles and were correlated with inpatient mortality. The cardiometabolic phenotype was associated with the highest mortality rate and was characterized clinically by venous congestion and low CO, right heart dysfunction and liver injury.…”

The Multicenter Collaborative to Enhance Biologic Understanding, Quality, and Outcomes in Cardiogenic Shock (VANQUISH Shock): Rationale and Design

“…In addition, enrolling patients with CS in mechanistic studies and clinical trials is associated with inherent challenges. Therefore, there is a major unmet need for deep phenotyping within comprehensive multicenter registries to better characterize mutually J o u r n a l P r e -p r o o f exclusive groups of patients in this heterogenous disease state and to advance our biological and clinical knowledge in CS (Table 1) (13,14).…”