Daily Cardiology Research Analysis

BACKGROUND: Females are typically underserved in cardiovascular medicine. The use of sex as a dichotomous variable for risk stratification fails to capture the heterogeneity of risk within each sex. We aimed to develop an artificial intelligence-enhanced electrocardiography (AI-ECG) model to investigate sex-specific cardiovascular risk. METHODS: In this retrospective cohort study, we trained a convolutional neural network to classify sex using the 12-lead electrocardiogram (ECG). The Beth Israel Deaconess Medical Center (BIDMC) secondary care dataset, comprising data from individuals who had clinically indicated ECGs performed in a hospital setting in Boston, MA, USA collected between May, 2000, and March, 2023, was the derivation cohort (1 163 401 ECGs). 50% of this dataset was used for model training, 10% for validation, and 40% for testing. External validation was performed using the UK Biobank cohort, comprising data from volunteers aged 40-69 years at the time of enrolment in 2006-10 (42 386 ECGs). We examined the difference between AI-ECG-predicted sex (continuous) and biological sex (dichotomous), termed sex discordance score. FINDINGS: AI-ECG accurately identified sex (area under the receiver operating characteristic 0·943 [95% CI 0·942-0·943] for BIDMC and 0·971 [0·969-0·972] for the UK Biobank). In BIDMC outpatients with normal ECGs, an increased sex discordance score was associated with covariate-adjusted increased risk of cardiovascular death in females (hazard ratio [HR] 1·78 [95% CI 1·18-2·70], p=0·006) but not males (1·00 [0·63-1·58], p=0·996). In the UK Biobank cohort, the same pattern was seen (HR 1·33 [95% CI 1·06-1·68] for females, p=0·015; 0·98 [0·80-1·20] for males, p=0·854). Females with a higher sex discordance score were more likely to have future heart failure or myocardial infarction in the BIDMC cohort and had more male cardiac (increased left ventricular mass and chamber volumes) and non-cardiac phenotypes (increased muscle mass and reduced body fat percentage) in both cohorts. INTERPRETATION: Sex discordance score is a novel AI-ECG biomarker capable of identifying females with disproportionately elevated cardiovascular risk. AI-ECG has the potential to identify female patients who could benefit from enhanced risk factor modification or surveillance. FUNDING: British Heart Foundation.

BACKGROUND: Approval of transcatheter aortic valve replacement (TAVR) for all risk profiles has extended TAVR use in patients not otherwise examined in clinical trials. We sought to evaluate contemporary real-world outcomes of surgical aortic valve replacement (SAVR) vs TAVR in Medicare beneficiaries by risk strata. METHODS: Using the US Centers for Medicare Services database, all patients aged 65-85 years undergoing isolated first-time SAVR (n = 34,215) or TAVR (n = 124,897) were evaluated (2018-2022). Predicted patient risk accounting for comorbidities simulating The Society of Thoracic Surgeons predicted risk of surgical mortality, but including frailty, were stratified by low (<4%, n = 36,297 TAVR; n = 14,693 SAVR), intermediate (4%-8%, n = 44,026 TAVR; n = 9693 SAVR), or high (>8%, n = 44,574 TAVR; n = 9841 SAVR) risk. Doubly robust risk adjustment with inverse probability weighting and multilevel regression with competing-risk time-to-event analyses compared outcomes. RESULTS: SAVR was associated with higher risk-adjusted in-hospital mortality, acute kidney injury, and bleeding but lower pacemaker rate compared with TAVR across all risk strata (all P < .05). Longitudinal 5-year analysis highlighted that, compared with TAVR, SAVR was associated with superior freedom from composite death, stroke, or valve reintervention in low- and intermediate-risk patients (hazard ratio [HR] 0.85, P = .044, and HR 0.86, P = .039, respectively) as well as lower overall readmission for stroke in low- (HR 0.72, P = .038) and intermediate- (HR 0.78, P = .042) risk patients. CONCLUSIONS: In low- and intermediate-risk Medicare beneficiaries, SAVR was associated with higher in-hospital mortality but superior 5-year longitudinal freedom from death, stroke, or valve reintervention compared to TAVR. These data may further enhance heart team decision-making and patient counseling.

BACKGROUND: Cardiopulmonary resuscitation (CPR) for out-of-hospital cardiac arrest (OHCA) is associated with higher survival. The association between time to bystander CPR at different time thresholds, compared with those with no bystander CPR, is less clear. METHODS: Within the Cardiac Arrest Registry to Enhance Survival, we identified 194,807 witnessed OHCAs during 2013-2023. Multivariable hierarchical logistic regression was used to evaluate the association between each time interval for initiation of bystander CPR (0-1, 2-3, 4-5, 6-7, 8-9, 10 + minutes), compared with no bystander CPR, for survival to discharge and favorable neurological survival (i.e. without severe neurological deficits). RESULTS: The mean age was 64.4 ± 15.9 years, and 33.8% were female. Bystander CPR was provided in 48.4% of cases, with a median initiation time of 2 min (IQR: 1-5). Overall, 15.3% survived to discharge, and 12.9% had favorable neurological survival. Compared with no bystander CPR, survival to discharge was higher for patients with bystander CPR initiated at 0-1 min (OR 1.78 [95% CI: 1.73-1.84]), 2-3 min (OR 1.57 [1.51-1.64]), 4-5 min (OR 1.23 [1.17-1.30]), 6-7 min (OR 1.25 [1.15-1.35]), and 8-9 min (OR 1.13 [1.03-1.25]), but no survival association was seen at ≥ 10 min (OR 0.80 [0.74-0.86]). A similar pattern was observed for neurological survival. CONCLUSIONS: Compared with no bystander CPR, bystander CPR was associated with improved survival even when started at 8 to 9 min. Given that there is a graded, inverse relationship between time to bystander CPR and survival, these findings underscore the urgency of immediate bystander CPR initiation to optimize OHCA survival.