Dataset Information

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.

SUBMITTER: Zweck E

PROVIDER: S-EPMC8483502 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundExpert opinion and professional society statements have called for multi-tier care systems for the management of cardiogenic shock (CS). However, little is known about how to pragmatically define centers with different levels of care (LOC) for CS.MethodsEleven of 23 hospitals within our healthcare system sharing a common electronic health record were classified as different LOC according to their highest mechanical circulatory support (MCS) capabilities: Level 1 (L-1)-durable left ventricular assist device, Level 1A (L-1A)-extracorporeal membrane oxygenation, Level 2 (L-2)-intra-aortic balloon pump and percutaneous ventricular assist device; and Level 3 (L-3)-no MCS. All adult patients treated for CS (International Classification of Diseases, ICD-10 code R57.0) between 2016 and 2022 were included. Etiologies of CS were identified using associated diagnostic codes. Management strategies and outcomes across LOC were compared.ResultsHigher LOC centers had higher volumes: L-1 (n = 1): 2,831 patients, L-1A (n = 4): 3,452, L-2 (n = 1): 340, and L-3 (n = 5): 780. Emergency room admissions were more common in lower LOC (96% at L-3 vs. 46% L-1; p < 0.001), while hospital transfers were predominant at higher LOC (40% at L-1 vs. 2.7% at L-3; p < 0.001). Men comprised 61% of the cohort. Patients were younger in the higher LOC [69 (60-78) years at L-1 vs. 77 (67-85) years at L-3; p < 0.001]. Patients with acute myocardial infarction (AMI)-CS and acute heart failure (AHF)-CS were concentrated in higher LOC centers while other etiologies of CS were more common in L-2 and L-3 (p < 0.001). Cardiac arrest on admission was more prevalent in lower LOC centers (L-1: 2.8% vs. L-3: 12.1%; p < 0.001). Patients with AMI-CS received more percutaneous coronary intervention in lower LOC (51% L-2 vs. 29% L-1; p < 0.01) but more coronary arterial bypass graft surgery at higher LOC (L-1: 42% vs. L-1A: 23%; p < 0.001). MCS use was consistent across levels for AMI-CS but was more frequent in higher LOC for AHF-CS patients (L-1: 28% vs. L-2: 10%; p < 0.001). Despite increasing in-hospital mortality with decreasing LOC, no significant difference was seen after multivariable adjustment.ConclusionThis is the first report describing a pragmatic classification of LOC for CS which, based on MCS capabilities, can discriminate between centers with distinct demographics, practice patterns, and outcomes. This classification may serve as the basis for future research and the creation of CS systems of care.

Dataset Information

Phenotyping Cardiogenic Shock.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets