Artificial Intelligence Assessment of Biological Age From Transthoracic Echocardiography: Discrepancies with Chronologic Age Predict Significant Excess Mortality.

Kobi Faierstein¹, Michael Fiman², Ranel Loutati³, Noa Rubin², Uri Manor⁴, Adiel Am-Shalom², Michal Cohen-Shelly², Nimrod Blank⁵, Dor Lotan⁶, Qiong Zhao⁷, Ehud Schwammenthal⁸, Robert Klempfner⁸, Eyal Zimlichman⁹, Ehud Raanani⁸, Elad Maor⁸

¹Leviev Cardiovascular Institute, Sheba Medical Center, Ramat Gan, Israel; Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel. Electronic address: kobi.faierstein@sheba.health.gov.il.

²Aisap.ai, Ramat Gan, Israel.

³Leviev Cardiovascular Institute, Sheba Medical Center, Ramat Gan, Israel.

⁴Leviev Cardiovascular Institute, Sheba Medical Center, Ramat Gan, Israel; Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel.

⁵Echocardiography Unit, Division of Cardiovascular Medicine, Baruch-Padeh Medical Center, Poria, Israel.

⁶Division of Cardiology, Department of Medicine, NewYork-Presbyterian Hospital, Columbia University Irving Medical Center, New York, New York.

⁷Inova Heart and Vascular Institute, Inova Fairfax Hospital, Falls Church, Virginia.

⁸Leviev Cardiovascular Institute, Sheba Medical Center, Ramat Gan, Israel; Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel; Aisap.ai, Ramat Gan, Israel.

⁹Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel.

PubMed DOI

Abstract

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 patien…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.