# Development of an Explainable Machine Learning Computational Model for the Prediction of Severe Complications After Orchiectomy in Stallions

## TL;DR

This study developed a machine learning model to predict severe complications after castration in stallions, using data from 612 cases.

## Contribution

The novel contribution is an explainable machine learning model to predict post-castration complications in stallions.

## Key findings

- Logistic Regression provided the best performance with high accuracy and recall for predicting complications.
- Age of the horse and surgical technique were the most influential factors in predicting complications.
- Machine learning models can serve as decision-support tools in equine peri-operative management.

## Abstract

The present work describes the development of a model, through the use of Machine Learning methodologies, for making predictions regarding the possible development of complications after an orchiectomy (castration) in stallions. The study has been based on a large dataset of 612 cases of surgery in stallions, operated in conditions of general veterinary practice by one of three experienced veterinary surgeons. Supervised Machine Learning methodologies were applied and, in total, 84 models were evaluated. The recall rate of the selected models was over 90%. The findings of this study have indicated that computational models could be used as adjunct tools to support clinical decisions in the peri-operative management of horses.

The objective of the present study was to apply supervised Machine Learning to predict severe complications after equine orchiectomy. A dataset of 612 cases of orchiectomies in stallions was used for the development of a computational model, among which in 8.5% of cases severe complications (colic, continued stallion-like behaviour, evisceration, funiculitis, haemorrhage, and scrotal infection) were diagnosed post-orchiectomy. Three supervised Machine Learning tools were employed: Logistic Regression (12 different models evaluated), Random Forest (64 models), and Gradient Boosting (8 models). For the prediction of the development of severe complications post-orchiectomy, Logistic Regression was the tool that produced the best discrimination measures, where accuracy, precision and recall were 0.9134, 0.8391, and 0.9133, respectively. The results of the analysis for SHapley Additive exPlanations values for the impact of the independent variables in the prediction of the development of complications indicated that (a) the age of the horse and (b) the surgical technique employed were the two variables that mostly influenced the prediction outcome, findings that were unambiguous in the models developed by any Machine Learning tool. The findings of this study indicate that computational models could be used as adjunct tools to support clinical decisions in the peri-operative management of horses.