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

Area of Science:

• Veterinary Medicine
• Machine Learning Applications
• Animal Physiology

Background:

• Rectal temperature (RT) is a key indicator of core body temperature in pets, crucial for diagnosing and treating diseases.
• Current methods for measuring core temperature can be invasive and stressful for animals.

Purpose of the Study:

• To develop and evaluate a machine learning-based alternative for determining core body temperatures in cats and dogs.
• To utilize easily obtainable surface body temperatures for predicting core temperatures.

Main Methods:

• Collected core and surface body temperature data from 200 cats and 200 dogs.
• Trained multiple machine learning models using cross-validation.
• Evaluated model performance on retrospective and prospective testing sets.

Main Results:

• Machine learning models demonstrated strong performance in predicting core temperatures for both species.
• Achieved low root mean square errors (RMSE): 0.25 (cats) and 0.15 (dogs) retrospectively; 0.15 (cats) and 0.14 (dogs) prospectively.

Conclusions:

• A machine learning model can accurately predict companion animal core temperatures from surface measurements.
• This non-invasive method offers a practical advancement in veterinary diagnostics.