AI-Powered Resting 12-Lead Electrocardiogram Algorithm for Predicting Low Peak Oxygen Consumption: Development and Validation Study
Shu-Chun Huang, Tieh-Cheng Fu, Michelle Liou, Yu-Chieh Huang, Sing-Ya Chang, Guan-Yi Huang, Hong-Ren Su · 2026
Read AI-Powered Resting 12-Lead Electrocardiogram Algorithm for Predicting Low Peak Oxygen Consumption: Development and Validation Study by Shu-Chun Huang, Tieh-Cheng Fu, Michelle Liou, Yu-Chieh Huang, Sing-Ya Chang, Guan-Yi Huang, Hong-Ren Su (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/PMC13260999.txt.
Description
Shu-Chun Huang leads a 2026 study developing an AI algorithm that predicts low peak oxygen consumption from a resting heart tracing. Peak oxygen consumption measures cardiorespiratory fitness and predicts mortality risk, but direct testing is impractical for screening. The model was trained on data from 965 people at one hospital branch, over half with heart or lung disorders, and validated in an independent group of 242 people at another branch. Low fitness was defined below a standard threshold.
Low peak oxygen consumption affected twenty-seven percent of the training group and thirty-eight percent of the validation group. A model using the ECG alone beat one using personal characteristics alone, and combining both performed best. The combined model scored 0.89 in cross-validation and 0.87 in external validation on the AUC measure. Signal wavelet analysis improved accuracy. The authors propose ECG screening to flag low fitness early.
Catalog record
| CREATOR | Shu-Chun Huang, Tieh-Cheng Fu, Michelle Liou, Yu-Chieh Huang, Sing-Ya Chang, Guan-Yi Huang, Hong-Ren Su |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35281 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |