An Exploration of Craniofacial Features in Obstructive Sleep Apnea Using the Explainable Deep Learning Approaches
Liuyi Luo, Ruicong Yang, Zitong Pei, Min Yu, Xu Gong, Yi Lei, Qing Wang, Xuemei Gao · 2026
Read An Exploration of Craniofacial Features in Obstructive Sleep Apnea Using the Explainable Deep Learning Approaches by Liuyi Luo, Ruicong Yang, Zitong Pei, Min Yu, Xu Gong, Yi Lei, Qing Wang, Xuemei Gao (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/PMC13287242.txt.
Description
Liuyi Luo and colleagues applied explainable computer vision in 2026 to face and skull images from 130 adults, half with sleep apnoea confirmed by overnight testing and half matched controls. Their goal was to find shape traits linked to the condition without starting from a fixed list of expected features.
The model separated the groups well, with an accuracy measure the authors report as 0.87. Highlight maps pointed to the jaw and chin, as expected, but also to the forehead, brows, and upper eyelids. Direct measures then confirmed narrower brow spacing and greater forehead projection in patients. The authors say larger groups must confirm the upper-face traits.
Catalog record
| CREATOR | Liuyi Luo, Ruicong Yang, Zitong Pei, Min Yu, Xu Gong, Yi Lei, Qing Wang, Xuemei Gao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42691 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |