Artificial Intelligence Assessment of Biological Age From Transthoracic Echocardiography: Discrepancies with Chronologic Age Predict Significant Excess Mortality - 01/08/24
, Michael Fiman, BSc c, Ranel Loutati, MD a, Noa Rubin, BSc c, Uri Manor, MD a, b, Adiel Am-Shalom, BSc c, Michal Cohen-Shelly, BSc c, Nimrod Blank, MD d, Dor Lotan, MD e, Qiong Zhao, MD, PhD f, Ehud Schwammenthal, MD, PhD a, b, c, Robert Klempfner, MD a, b, c, Eyal Zimlichman, MD, MSc b, Ehud Raanani, MD a, b, c, Elad Maor, MD, PhD a, b, cAbstract |
Background |
Age and sex can be estimated using artificial intelligence on the basis of various sources. The aims of this study were to test whether convolutional neural networks could be trained to estimate age and predict sex using standard transthoracic echocardiography and to evaluate the prognostic implications.
Methods |
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 devices (n = 319; ClinicalTrials.Gov identifier NCT05455541) was used to confirm the findings. A multivariate Cox regression model was used to investigate the association between age estimation and chronologic age with overall survival.
Results |
The mean absolute 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 of 0.993. External validation and prospective study cohorts yielded consistent results. Finally, survival analysis demonstrated that age prediction ≥5 years vs chronologic age was associated with an independent 34% increased risk for death during follow-up (P < .001).
Conclusions |
Applying artificial intelligence to standard transthoracic echocardiography allows the prediction of sex and the 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.
Le texte complet de cet article est disponible en PDF.Graphical abstract |
We aimed to investigate whether deep learning models are able to accurately estimate patients’ age and be used as a risk stratification tool. Applying artificial intelligence to standard transthoracic echocardiography (TTE) allows the prediction of sex and the estimation of age. Discrepancies between chronologic age and machine-estimated age correlate with mortality. Applying the same model to handheld devices demonstrated consistent results, emphasizing the importance of this tool in risk stratification and clinical evaluation.
Central IllustrationWe aimed to investigate whether deep learning models are able to accurately estimate patients’ age and be used as a risk stratification tool. Applying artificial intelligence to standard transthoracic echocardiography (TTE) allows the prediction of sex and the estimation of age. Discrepancies between chronologic age and machine-estimated age correlate with mortality. Applying the same model to handheld devices demonstrated consistent results, emphasizing the importance of this tool in risk stratification and clinical evaluation.Le texte complet de cet article est disponible en PDF.
Highlights |
• | Deep learning can accurately estimate age and sex on transthoracic echocardiography. |
• | Machine-based age and sex estimation is associated with increased risk for mortality. |
• | Machine learning algorithms may be used for risk stratification purposes. |
• | Machine learning algorithms may enhance point-of-care ultrasound devices. |
Keywords : Echocardiography, Point-of-care ultrasound, Artificial intelligence, Longevity
Abbreviations : ADG, AI, AUC, CNN, HR, IQR, LVEF, MAE, RMSE, POCUS
Plan
Vol 37 - N° 8
P. 725-735 - août 2024 Retour au numéro
Article précédent
- Information for Readers
- Beyond Years: Is Artificial Intelligence Ready to Predict Biological Age and Cardiovascular Risk Using Echocardiography?
- Bjørnar Grenne, Andreas Østvik
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?