Artificial Intelligence Assessment of Biological Age from Transthoracic Echocardiography: Discrepancies to Chronologic Age Predict Significant Excess Mortality

Abstract

Age and sex can be estimated by artificial intelligence based on various sources. We aimed to test whether convolutional neural networks could be trained to estimate the age and predict the sex using standard transthoracic echocardiography (TTE), and to evaluate its prognostic implications. The algorithm was trained on 76,342 patients, validated in 22,825 patients, and tested in 20,960 patients. It was then externally validated using data from a different hospital (N=556). Finally, a prospective cohort of handheld point-of-care ultrasound (POCUS) devices (N=319; ClinicalTrials.Gov NCT05455541) was used to confirm the findings. Multivariate Cox regression model was used to investigate the association between age-estimation and chronological age with overall survival. The mean average error in age estimation was 4.9 years, with a Pearson correlation coefficient of 0.922. The probabilistic value of sex had an overall accuracy of 96.1% and an area under the curve (AUC) of 0.993. External validation and prospective study cohorts yielded consistent results. Finally, survival analysis demonstrated that age prediction ≥ 5 years of chronological age was associated with an independent 34% increased risk of death during follow-up (p<0.001). Applying artificial intelligence to the standard TTE allows prediction of sex and estimation of age. Machine-based estimation is an independent predictor of overall survival and, with further evaluation, can be used for risk stratification and estimation of biological age.