Machine Learning–Based Multidimensional Oximetry for Obstructive Sleep Apnea Screening: Development and External Validation
Xuanyu Qian, Haitong Luo, Rong Ding, Tianming Gao, Haoan Wang, Pengliang Wu, Ning Li, Arriel Benis, F A Etindele Sosso, Bo Xiang · 2026
Read Machine Learning–Based Multidimensional Oximetry for Obstructive Sleep Apnea Screening: Development and External Validation by Xuanyu Qian, Haitong Luo, Rong Ding, Tianming Gao, Haoan Wang, Pengliang Wu, Ning Li, Arriel Benis, F A Etindele Sosso, Bo 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/pmc-13197743.txt.
Description
Breathing that stalls in sleep strains the heart and brain, yet the full night lab test that proves it is slow and scarce. Qian and co-authors build a sieve from a fingertip oxygen clip in 2026. Eight reads off the oxygen trace — dip counts, burden sums, time spent low — feed six learning models.
The build pool held 2,195 lab-tested sleepers, drawn from 4,156 screened. A second pool of 446 home-tested sleepers checks the sieve cold. Scores are read by hit rate first and curve strength second, and split by sex and age to hunt bias. The aim is a cheap first pass that sends the right people to the lab. Which reads drive each call is part of the report.
Catalog record
| CREATOR | Xuanyu Qian, Haitong Luo, Rong Ding, Tianming Gao, Haoan Wang, Pengliang Wu, Ning Li, Arriel Benis, F A Etindele Sosso, Bo Xiang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |