Accurate prediction of hypoglycemia and hyperglycemia using machine learning in critically ill patients
Yu Ikeda, Satoru Sugimoto, Tetsuo Ishikawa, Tatsuro Yokoyama, Takehiko Oami, Keisuke Tomita, Eiryo Kawakami, Taka-aki Nakada · 2025
Read Accurate prediction of hypoglycemia and hyperglycemia using machine learning in critically ill patients by Yu Ikeda, Satoru Sugimoto, Tetsuo Ishikawa, Tatsuro Yokoyama, Takehiko Oami, Keisuke Tomita, Eiryo Kawakami, Taka-aki Nakada (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-12770608.txt.
Description
Yu Ikeda and seven co-authors trained in 2025 a model that warns six hours ahead when a critical patient's blood sugar will crash or soar. Both extremes are common in intensive care and dangerous, yet many forces move sugar at once. Records of nearly nine thousand patients at one Japanese hospital fed four learning methods.
The strongest, a gradient-boosted tree model, read routine chart data: body measures, lab values, and treatments. A six-hour warning gives nurses time to adjust insulin or food before harm lands. Prediction turns sugar control from reaction into prevention.
Catalog record
| CREATOR | Yu Ikeda, Satoru Sugimoto, Tetsuo Ishikawa, Tatsuro Yokoyama, Takehiko Oami, Keisuke Tomita, Eiryo Kawakami, Taka-aki Nakada |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 28 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |