Associations between echocardiographic traits and artificial intelligence-enabled electrocardiography predictions of heart failure
Elias Stenhede, Eivind Bjørkan Orstad, Torbjørn Omland, Henrik Schirmer, Arian Ranjbar · 2026
Read Associations between echocardiographic traits and artificial intelligence-enabled electrocardiography predictions of heart failure by Elias Stenhede, Eivind Bjørkan Orstad, Torbjørn Omland, Henrik Schirmer, Arian Ranjbar (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13584927.txt.
Description
Elias Stenhede and co-authors ask what heart traits an AI-read ECG score for heart failure truly tracks. The score can flag failure even when pumping fraction looks normal. Data joined 8,147 patients who had both tests within three days at one hospital. Ultrasound measures were set against the AI score one by one.
Global longitudinal strain, a fine squeeze measure, tracked the score most strongly. Chamber motion and ejection fraction followed close behind. Among patients with preserved pumping, strain and filling measures still tracked well. A second center's 36,286 pairs echoed the shared links. Women showed weaker volume links but stronger filling links than men.
Catalog record
| CREATOR | Elias Stenhede, Eivind Bjørkan Orstad, Torbjørn Omland, Henrik Schirmer, Arian Ranjbar |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |