Phenotype clustering of hospitalized high-risk patients with COVID-19 - a machine learning approach within the multicentre, multinational PCHF-COVICAV registry.

IMTRODUCTION: The high-risk population of patients with cardiovascular (CV) disease or risk factors (RF) suffering from COVID-19 is heterogeneous. Several predictors for impaired prognosis have been identified. However, with machine learning (ML) approaches, certain phenotypes may be confined to classify the affected population and to predict outcome. This study aimed to phenotype patients using unsupervised ML technique within the International Postgraduate Course Heart Failure Registry for patients hospitalized with COVID-19 and Cardiovascular disease and/or RF (PCHF-COVICAV). MATERIAL AND METHODS: Patients from the eight centres with follow-up data available from the PCHF-COVICAV registry were included in this ML analysis (K-medoids algorithm). RESULTS: Out of 617 patients included into the prospective part of the registry, 458 [median age: 76 (IQR:65-84) years, 55% male] were analyzed and 46 baseline variables, including demographics, clinical status, comorbidities and biochemical characteristics were incorporated into the ML. Three clusters were extracted by this ML method. Cluster 1 (n = 181) represents mainly women with the least number of overall comorbidities and cardiovascular RF. Cluster 2 (n = 227) is characterized mainly by men with non-CV conditions and less severe symptoms of infection. Cluster 3 (n=50) mainly represents men with the highest prevalence of cardiac comorbidities and RF, more extensive inflammation and organ dysfunction with the highest 6-month all-cause mortality risk. CONCLUSIONS: The ML process has identified three important clinical clusters from hospitalized COVID-19 CV and/or RF patients. The cluster of males with severe CV disease, particularly HF, and multiple RF presenting with increased inflammation had a particularly poor outcome.

Landmark Evolutions in Time and Indication for Cardiac Resynchronization Therapy: Results from a Multicenter Retrospective Registry.

Background: Cardiac resynchronization therapy (CRT) has evolved into an established therapy for patients with chronic heart failure and a wide QRS complex. Data on long-term outcomes over time are scarce and the criteria for implantation remain a subject of investigation. Methods: An international, multicenter, retrospective registry includes 2275 patients who received CRT between 30 November 2000 and 31 December 2019, with a mean follow-up of 3.6 ± 2.7 years. Four time periods were defined, based on landmark trials and guidelines. The combined endpoint was a composite of all-cause mortality, heart transplantation, or left ventricular assist device implantation. Results: The composite endpoint occurred in 656 patients (29.2%). The mean annual implantation rate tripled from 31.5 ± 17.4/year in the first period to 107.4 ± 62.4/year in the last period. In the adjusted Cox regression analysis, the hazard ratio for the composite endpoint was not statistically different between time periods. When compared to sinus rhythm with left bundle branch block (LBBB), a non-LBBB conduction pattern (sinus rhythm: HR 1.51, 95% CI 1.12-2.03; atrial fibrillation: HR 2.08, 95% CI 1.30-3.33) and a QRS duration below 130 ms (HR 1.64, 95% CI 1.29-2.09) were associated with a higher hazard ratio. Conclusions: Despite innovations, an adjusted regression analysis revealed stable overall survival over time, which can at least partially be explained by a shift in patient characteristics.