Evaluating non-linear thresholds and synergistic interactions in the comorbidity of preoperative insomnia and emergence agitation: a SHAP-based machine learning study
Jianheng Zhao, Xiaoxu Yu, Bangjian Zhang, Mengying Wang, Xiaoyan Yang · 2026
Read Evaluating non-linear thresholds and synergistic interactions in the comorbidity of preoperative insomnia and emergence agitation: a SHAP-based machine learning study by Jianheng Zhao, Xiaoxu Yu, Bangjian Zhang, Mengying Wang, Xiaoyan Yang (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-13616693.txt.
Description
Jianheng Zhao and a team of co-authors use machine learning to study poor sleep before surgery and agitation on waking from anesthesia, in two thousand twenty-six. The two problems often occur together, and straight-line models may miss how they interact. The team studied more than five hundred adult surgical patients at one center.
A boosting model predicted the paired problem far better than a classic regression model. An explanation method ranked two hormone measures as the strongest signals behind the predictions. Plots hinted at threshold levels where risk climbs in a curved way. Severe pain after surgery seemed to amplify the risk tied to poor sleep. The authors call for multi-center checks before clinical use.
Catalog record
| CREATOR | Jianheng Zhao, Xiaoxu Yu, Bangjian Zhang, Mengying Wang, Xiaoyan Yang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |