Body Weight Prediction from Linear Measurements of Icelandic Foals: A Machine Learning Approach

Simple Summary

Knowing the body weight of a growing horse is important both for horse breeders and veterinarians because this information helps to identify abnormalities of the growing process, determine adequate feeding rations or choose an appropriate drug treatment regimen. It is not always possible to measure accurately a horse’s body weight using special scales, and a visual assessment, which is the easiest method for finding out a horse’s body weight, produces heavily biased results. Simple formulas are being sought to allow making accurate estimates of body weight in horses based on their body measurements. This study relates the estimation of body weight in Icelandic foals with the use of models relying on machine learning methods. Based on their evaluation, two of the models are recommended for use in practical applications.

Abstract

Knowledge of the body weight of horses permits breeders to provide appropriate feeding and care regimen and allows veterinarians to monitor the animals’ health. It is not always possible to perform an accurate measurement of the body weight of horses using horse weighbridges, and therefore, new body weight formulas based on biometric measurements are required. The objective of this study is to develop and validate models for estimating body weight in Icelandic foals using machine learning methods. The study was conducted using 312 data records of body measurements on 24 Icelandic foals (12 colts and 12 fillies) from birth to 404 days of age. The best performing model was the polynomial model that included features such as heart girth, body circumference and cannon bone circumference. The mean percentage error for this model was 4.1% based on cross-validation and 3.8% for a holdout dataset. The body weight of Icelandic foals can also be estimated using a less complex model taking a single trait defined as the square of heart girth multiplied by body circumference. The mean percentage error for this model was up to 5% both for the training and the holdout datasets. The study results suggest that machine learning methods can be considered a useful tool for designing models for the estimation of body weight in horses.

Does Experience Make Hucul Horses More Resistant to Stress? A Pilot Study

The aim of the study was to determine whether experience related to horse age and number of starts in championships influences stress level, measured by salivary cortisol concentration. The study involved 18 clinically healthy Hucul mares who participated in the Polish Championships for Hucul Horses. Evaluation of performance value was carried out in accordance with the guidelines specified in the breeding and genetic resources conservation program for this breed. The championship lasted two days, consisting of conformation evaluation, endurance, and Hucul path. Saliva was collected at baseline (T1), after arena assessment (T2), after endurance (T3), and on the second day after the Hucul path (T4). Cortisol levels increased from an average of 2.73 ± 1.18 ng/mL (T1) to 10.46 ± 8.03 ng/mL after T3. Significantly lower levels of free cortisol were detected in the saliva of the younger mares, up to 9 years old, and mares who participated in only one qualifying path after each element of the championship. The highest levels of cortisol (T3) were found in mares competing repeatedly on the qualifying path. No correlation was found between cortisol levels and the championship results. Participation of mares in the championship was associated with stress, which was reflected in the increase in cortisol levels in saliva.

Evaluation of the Accuracy of Horse Body Weight Estimation Methods

Simple Summary

Horse body weight estimation and monitoring of the weight variations are necessary to determine the amount of feed and feed additives for the proper functioning of the animal. Due to the cost and practical challenge of weighing horses on a large scale, several alternative methods for estimating the body weight of horses have been developed. One of them is to determine a horse’s body weight using a formula. The aim of the study was to evaluate established formulae for estimating horse body weight from data gathered using measurement tape. The investigation was conducted on a group of 299 adult horses of five breeds: ponies, Polish Noble Half Breed, Silesian Breed, Wielkopolski Breed and Thoroughbred. For each horse, body measurements were performed and the actual body weight of the horses was measured with an electronic scales. The horse’s body weight measurements were compared with the result of seven different formulae. It was found that the use of formulae for body weight estimation can be useful in determining feed dosages and additives, medicines, or deworming agents.

Abstract

Methods of estimating horse body weight using mathematical formulae have better accuracy than methods of reading body weight from measuring tape. The aim of the study was to evaluate established formulae for estimating horse body weight from data gathered using measurement tape. The research was conducted in a group of 299 adult horses and ponies of selected breeds: ponies (n = 58), Polish Noble Half Breed (n = 150), Silesian Breed (n = 23), Wielkopolski Breed (n = 52), and Thoroughbred (n = 16). Body measurements were performed on each horse using a measuring stick and tape. The actual body weight of the horses was measured with electronic scale. Statistical analysis was carried out separately for individual breeds of horses. In each of the research groups formulae were selected, the results of which were closest to the actual horse body weight readings. The use of formulae for body weight estimation can be useful in determining feed dosages and additives, medicines or deworming agents. Regular weight measurement is important for maintaining a healthy horse.