Soussi, Sabri

Abstract Aims Hospitalized patients with heart failure (HF) are a heterogeneous population, with multiple phenotypes proposed. Prior studies have not examined the biological phenotypes of critically ill patients with HF admitted to the contemporary cardiac intensive care unit (CICU). We aimed to leverage unsupervised machine learning to identify previously unknown HF phenotypes in a large and diverse cohort of patients with HF admitted to the CICU. Methods We screened 6008 Mayo Clinic CICU patients with an admission diagnosis of HF from 2007 to 2018 and included those without missing values for common laboratory tests. Consensus k-means clustering was performed based on 10 common admission laboratory values (potassium, chloride, anion gap, blood urea nitrogen, haemoglobin, red blood cell distribution width, mean corpuscular volume, platelet count, white blood cell count and neutrophil-to-lymphocyte ratio). In-hospital mortality was evaluated using logistic regression, and 1 year mortality was evaluated using Cox proportional hazard models after multivariable adjustment. Results Among 4877 CICU patients with HF who had complete admission laboratory data (mean age 69.4 years, 38.4% females), we identified five clusters with divergent demographics, comorbidities, laboratory values, admission diagnoses and use of critical care therapies. We labelled these clusters based on the characteristic laboratory profile of each group: uncomplicated (25.7%), iron-deficient (14.5%), cardiorenal (18.4%), inflamed (22.3%) and hypoperfused (19.2%). In-hospital mortality occurred in 10.7% and differed between the phenotypes: uncomplicated, 2.7% (reference); iron-deficient, 8.1% [adjusted odds ratio (OR) 2.18 (1.38–3.48), P < 0.001]; cardiorenal, 10.3% [adjusted OR 2.11 (1.37–3.32), P < 0.001]; inflamed, 12.5% [adjusted OR 1.79 (1.18–2.76), P = 0.007]; and hypoperfused, 21.9% [adjusted OR 4.32 (2.89–6.62), P < 0.001]. These differences in mortality between phenotypes were consistent when patients were stratified based on demographics, aetiology, admission diagnoses, mortality risk scores, shock severity and systolic function. One-year mortality occurred in 31.5% and differed between the phenotypes: uncomplicated, 11.9% (reference); inflamed, 26.8% [adjusted hazard ratio (HR) 1.56 (1.27–1.92), P < 0.001]; iron-deficient, 33.8% [adjusted HR 2.47 (2.00–3.04), P < 0.001]; cardiorenal, 41.2% [adjusted HR 2.41 (1.97–2.95), P < 0.001]; and hypoperfused, 52.3% [adjusted HR 3.43 (2.82–4.18), P < 0.001]. Similar findings were observed for post-discharge 1 year mortality. Conclusions Unsupervised machine learning clustering can identify multiple distinct clinical HF phenotypes within the CICU population that display differing mortality profiles both in-hospital and at 1 year. Mortality was lowest for the uncomplicated HF phenotype and highest for the hypoperfused phenotype. The inflamed phenotype had comparatively higher in-hospital mortality yet lower post-discharge mortality, suggesting divergent short-term and long-term prognosis.

Abstract Aims An elevated risk of adverse events persists for years in cardiogenic shock (CS) survivors with high mortality rate and physical/mental disability. This study aims to link clinical CS-survivor phenotypes with distinct late host-response patterns at intensive care unit (ICU) discharge and long-term outcomes using model-based clustering. Methods and results In the original prospective, observational, international French and European Outcome Registry in Intensive Care Units (FROG-ICU) study, ICU patients with CS on admission were identified (N = 228). Among them, 173 were discharged alive from the ICU and included in the current study. Latent class analysis was applied to identify distinct CS-survivor phenotypes at ICU discharge using 15 readily available clinical and laboratory variables. The primary endpoint was 1 year of mortality after ICU discharge. Secondary endpoints were readmission and physical/mental disability [short form-36 questionnaire (SF-36) score] within 1 year after ICU discharge. Two distinct phenotypes at ICU discharge were identified (A and B). Patients in Phenotype B (38%) were more anaemic and had higher circulating levels of lactate, sustained kidney injury, and persistent elevation in plasma markers of inflammation, myocardial fibrosis, and endothelial dysfunction compared with Phenotype A. They had also a higher rate of non-ischaemic origin of CS and right ventricular dysfunction on admission. CS survivors in Phenotype B had higher 1 year of mortality compared with Phenotype A (P = 0.045, Kaplan–Meier analysis). When adjusted for traditional risk factors (i.e. age, severity of illness, and duration of ICU stay), Phenotype B was independently associated with 1 year of mortality [adjusted hazard ratio = 2.83 (95% confidence interval 1.21–6.60); P = 0.016]. There was a significantly lower physical quality of life in Phenotype B patients at 3 months (i.e. SF-36 physical component score). Conclusions A phenotype with sustained inflammation, myocardial fibrosis, and endothelial dysfunction at ICU discharge was identified from readily available data and was independently associated with poor long-term outcomes in CS survivors.

Purpose of review Cardiogenic shock (CS) results in persistently high short-term mortality and a lack of evidence-based therapies. Several trials of novel interventions have failed to show an improvement in clinical outcomes despite promising preclinical and physiologic principles. In this review, we highlight the challenges of CS trials and provide suggestions for the optimization and harmonization of their design. Recent findings CS clinical trials have been plagued by slow or incomplete enrolment, heterogeneous or nonrepresentative patient cohorts, and neutral results. To achieve meaningful, practice-changing results in CS clinical trials, an accurate CS definition, a pragmatic staging of its severity for appropriate patient selection, an improvement in informed consent process, and the use of patient-centered outcomes are required. Future optimizations include the use of predictive enrichment using host response biomarkers to unravel the biological heterogeneity of the CS syndrome and identify subphenotypes most likely to benefit from individualized treatment to allow a personalized medicine approach. Summary Accurate characterization of CS severity and its pathophysiology are crucial to unravel heterogeneity and identify the patients most likely to benefit from a tested treatment. Implementation of biomarker-stratified adaptive clinical trial designs (i.e., biomarker or subphenotype-based therapy) might provide important insights into treatment effects.

AbstractBackgroundProposed phenotypes have recently been identified in cardiogenic shock (CS) populations using unsupervised machine learning clustering methods. We sought to validate these phenotypes in a mixed cardiac intensive care unit (CICU) population of patients with CS.MethodsWe included Mayo Clinic CICU patients admitted from 2007 to 2018 with CS. Agnostic K means clustering was used to assign patients to three clusters based on admission values of estimated glomerular filtration rate, bicarbonate, alanine aminotransferase, lactate, platelets, and white blood cell count. In‐hospital mortality and 1‐year mortality were analyzed using logistic regression and Cox proportional‐hazards models, respectively.ResultsWe included 1498 CS patients with a mean age of 67.8 ± 13.9 years, and 37.1% were females. The acute coronary syndrome was present in 57.3%, and cardiac arrest was present in 34.0%. Patients were assigned to clusters as follows: Cluster 1 (noncongested), 603 (40.2%); Cluster 2 (cardiorenal), 452 (30.2%); and Cluster 3 (hemometabolic), 443 (29.6%). Clinical, laboratory, and echocardiographic characteristics differed across clusters, with the greatest illness severity in Cluster 3. Cluster assignment was associated with in‐hospital mortality across subgroups. In‐hospital mortality was higher in Cluster 3 (adjusted odds ratio [OR]: 2.6 vs. Cluster 1 and adjusted OR: 2.0 vs. Cluster 2, both p < 0.001). Adjusted 1‐year mortality was incrementally higher in Cluster 3 versus Cluster 2 versus Cluster 1 (all p < 0.01).ConclusionsWe observed similar phenotypes in CICU patients with CS as previously reported, identifying a gradient in both in‐hospital and 1‐year mortality by cluster. Identifying these clinical phenotypes can improve mortality risk stratification for CS patients beyond standard measures.