A non-invasive method to determine core temperature for cats and dogs using surface temperatures based on machine learning.

Zhao Z, Li X, Zhuang Y, Li F, Wang W, Wang Q, Su S, Huang J, Tang Y. A non-invasive method to determine core temperature for cats and dogs using surface temperatures based on machine learning. BMC Vet Res. 2024;20:199. https://bmcvetres.biomedcentral.com/articles/10.1186/s12917-024-04063-2

This study aimed to develop and evaluate a machine learning-based method to predict core temperatures of cats and dogs using surface temperatures as a non-invasive alternative to rectal temperature measurement. A total of 200 cats and 200 dogs were included, with temperature data collected and machine learning models trained via cross-validation. The models demonstrated high accuracy, with root mean square errors (RMSE) of 0.25 and 0.15 for cats and dogs, respectively, in the retrospective set, and 0.15 and 0.14 in the prospective set. The results indicate that surface temperature measurements combined with machine learning can accurately predict core temperatures in cats and dogs.