AI-Driven SaO2 prediction from pulse oximetry and electronic health records
JiWon Woo, Orian Stapleton, Jay Luo, Chao Cheng Chuang, Yolanda Su, Sreenidhi Sankararaman, Esanika Mukherjee, Nikita Sivakumar, Katherine Calligy, Summer Duffy, Rebecca Mosier, Joseph Greenstein, Casey Overby Taylor, Danielle Gottlieb Sen · 2025
Read AI-Driven SaO2 prediction from pulse oximetry and electronic health records by JiWon Woo, Orian Stapleton, Jay Luo, Chao Cheng Chuang, Yolanda Su, Sreenidhi Sankararaman, Esanika Mukherjee, Nikita Sivakumar, Katherine Calligy, Summer Duffy, Rebecca Mosier, Joseph Greenstein, Casey Overby Taylor, Danielle Gottlieb Sen (2025) 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-12752230.txt.
Description
JiWon Woo and co-authors use machine learning to improve blood oxygen checks in work from 2025. Finger sensors estimate oxygen fast, but they can read too high in people with dark skin. High readings can hide low oxygen and delay care.
The team trained models on near 49 thousand hospital records from three large databases. Each record held 64 clinical measures plus lab-based oxygen values. Models learned to predict the lab value and to flag hidden low oxygen. Three model types were compared against sensor readings and lab tests. Better prediction could help staff catch low oxygen sooner and treat all patients more fairly.
Catalog record
| CREATOR | JiWon Woo, Orian Stapleton, Jay Luo, Chao Cheng Chuang, Yolanda Su, Sreenidhi Sankararaman, Esanika Mukherjee, Nikita Sivakumar, Katherine Calligy, Summer Duffy, Rebecca Mosier, Joseph Greenstein, Casey Overby Taylor, Danielle Gottlieb Sen |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |