Background We have demonstrated that a neural network is able to predict a person’s age from the electrocardiogram (ECG) [artificial intelligence (AI) ECG age]. However, some discrepancies were observed between ECG-derived and chronological ages. We assessed whether the difference between AI ECG and chronological age (Age-Gap) represents biological ageing and predicts long-term outcomes. Methods and results We previously developed a convolutional neural network to predict chronological age from ECGs. In this study, we used the network to analyse standard digital 12-lead ECGs in a cohort of 25 144 subjects ≥30 years who had primary care outpatient visits from 1997 to 2003. Subjects with coronary artery disease, stroke, and atrial fibrillation were excluded. We tested whether Age-Gap was correlated with total and cardiovascular mortality. Of 25 144 subjects tested (54% females, 95% Caucasian) followed for 12.4 ± 5.3 years, the mean chronological age was 53.7 ± 11.6 years and ECG-derived age was 54.6 ± 11 years (R2 = 0.79, P < 0.0001). The mean Age-Gap was small at 0.88 ± 7.4 years. Compared to those whose ECG-derived age was within 1 standard deviation (SD) of their chronological age, patients with Age-Gap ≥1 SD had higher all-cause and cardiovascular disease (CVD) mortality. Conversely, subjects whose Age-Gap was ≤1 SD had lower all-cause and CVD mortality. Results were unchanged after adjusting for CVD risk factors and other survival influencing factors. Conclusion The difference between AI ECG and chronological age is an independent predictor of all-cause and cardiovascular mortality. Discrepancies between these possibly reflect disease independent biological ageing.

Background Although elevated body mass index (BMI) is a risk factor for cardiac disease, patients with elevated BMI have better survival in the context of severe illness, a phenomenon termed the “obesity paradox.” Hypothesis Higher BMI is associated with lower mortality in sudden cardiac arrest (SCA) survivors. Methods Data were collected on 1433 post‐SCA patients, discharged alive from the hospitals of the University of Pittsburgh Medical Center between 2002 and 2012. Of those, 1298 patients with documented BMI during the index hospitalization and follow‐up data constituted the study cohort. Results In the overall cohort, 30 patients were underweight (BMI <18.5 kg/m2), 312 had normal weight (BMI 18.5–24.9 kg/m2), 417 were overweight (BMI 25.0–29.9 kg/m2), and 539 were obese (BMI ≥30 kg/m2). As expected, the prevalence of coronary artery disease, myocardial infarction, diabetes mellitus, and hypertension increased significantly with increasing BMI. Over a median follow‐up of 3.6 years, 602 (46%) patients died. Despite higher prevalence of cardiovascular comorbidities in more obese patients, a higher BMI was associated with lower all‐cause mortality on univariate analysis (hazard ratio: 0.86 per increase by 1 BMI category, 95% confidence interval: 0.78‐0.94, P = 0.002) and multivariate analysis after adjusting for unbalanced baseline comorbidities (hazard ratio: 0.86 per increase by 1 BMI category, 95% confidence interval: 0.77‐0.96, P = 0.009). Conclusions Higher BMI is associated with lower all‐cause mortality in survivors of SCA, suggesting that the obesity paradox applies to the post‐arrest population. Further investigation into its mechanisms may inform the management of post‐SCA patients.

In survivors of SCA because of a reversible and correctable cause, ICD therapy is associated with lower all-cause mortality except if the SCA was because of myocardial infarction. These data deserve further investigation in a prospective multicenter randomized controlled trial, as they may have important and immediate clinical implications.