Association Between Social Isolation With Age-Gap Determined by Artificial Intelligence-Enabled Electrocardiography

Background Loneliness and social isolation are associated with poor health outcomes such as an increased risk of cardiovascular diseases. Objectives The authors aimed to explore the association between social isolation with biological aging which was determined by artificial intelligence-enabled electrocardiography (AI-ECG) as well as the risk of all-cause mortality. Methods The study included adults aged ≥18 years seen at Mayo Clinic from 2019 to 2022 who respond to a survey for social isolation assessment and had a 12-lead ECG within 1 year of completing the questionnaire. Biological age was determined from ECGs using a previously developed and validated convolutional neural network (AI-ECG age). Age-Gap was defined as AI-ECG age minus chronological age, where positive values reflect an older-than-expected age. The status of social isolation was measured by the previously validated multiple-choice questions based on Social Network Index (SNI) with score ranges between 0 (most isolated) and 4 (least isolated). Results A total of 280,324 subjects were included (chronological age 59.8 ± 16.4 years, 50.9% female). The mean Age-Gap was −0.2 ± 9.16 years. A higher SNI was associated with a lower Age-Gap (β of SNI = 4 was −0.11; 95% CI: −0.22 to −0.01; P < 0.001, adjusted to covariates). Cox proportional hazard analysis revealed the association between social connection and all-cause mortality (HR for SNI = 4, 0.47; 95% CI: 0.43-0.5; P < 0.001). Conclusions Social isolation is associated with accelerating biological aging and all-cause mortality independent of conventional cardiovascular risk factors. This observation underscores the need to address social connection as a health care determinant.