Temporal Convolutional Neural Network Analysis of Magnetocardiography Signals for Detection of Pulmonary Hypertension
Yuankun Qi, Kai Ma, Xiaole Han, Dong Xu, Xu Zhang, Min Xiang · 2026
Read Temporal Convolutional Neural Network Analysis of Magnetocardiography Signals for Detection of Pulmonary Hypertension by Yuankun Qi, Kai Ma, Xiaole Han, Dong Xu, Xu Zhang, Min Xiang (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/PMC13405781.txt.
Description
Yuankun Qi and co-authors pair magnetic heart recordings with a neural network to detect pulmonary hypertension, in a 2026 study. Magnetocardiography senses the heart's magnetic field with high detail, but reading it needs machine help. Patients had the diagnosis confirmed by catheter testing or were low-probability controls.
A temporal convolutional network learned from 64-channel recordings plus age, sex and body mass. Discrimination reached an AUC of 0.939 in internal checks and 0.974 on held-out patients in the reported results, beating standard machine learning models. Decision curve analysis supported clinical usefulness at sensible thresholds. Which signal features drove the verdicts is explored through attribution analysis.
Catalog record
| CREATOR | Yuankun Qi, Kai Ma, Xiaole Han, Dong Xu, Xu Zhang, Min Xiang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38035 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |