Machine learning algorithms for the early detection of bloodstream infection in children with osteoarticular infections
Yuwen Liu, Yuhan Wu, Tao Zhang, Jie Chen, Wei Hu, Guixin Sun, Pengfei Zheng · 2024
Read Machine learning algorithms for the early detection of bloodstream infection in children with osteoarticular infections by Yuwen Liu, Yuhan Wu, Tao Zhang, Jie Chen, Wei Hu, Guixin Sun, Pengfei Zheng (2024) 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-11668579.txt.
Description
Yuwen Liu and co-authors train machine learning to spot bloodstream infection early in children with bone and joint infections. Such infections can seed the blood, a life-threatening turn that blood cultures confirm only slowly. Working from three Chinese hospitals, the team gathered 601 children treated between 2012 and 2023, of whom 181 had bloodstream infection. Sixteen measurements available early were fed to eight learning algorithms.
A random forest model won, reaching an area under the curve of 0.947 and about 90 percent accuracy. Four signals did most of the work: procalcitonin levels, neutrophil counts, white cell counts, and days of fever. The authors argue the model could help doctors act before culture results return, cutting the danger from delayed or misleading tests. They frame it as decision support, not a replacement for clinical judgement.
Catalog record
| CREATOR | Yuwen Liu, Yuhan Wu, Tao Zhang, Jie Chen, Wei Hu, Guixin Sun, Pengfei Zheng |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 24 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |