Using Artificial Intelligence to Predict Survivability Likelihood and Need for Surgery in Horses Presented With Acute Abdomen (Colic)

Abstract

Artificial intelligence and machine learning have promising applications in several medical fields of diagnosis, imaging, and laboratory testing procedures. However, the use of this technology in the veterinary medicine field is lagging behind, and there are many areas where it could be used with potentially successful outcomes and results. In this study, two critical predictions were explored in horses presented with acute abdomen (colic) using this technology. Those were the need for surgical intervention and survivability likelihood of affected horses based on clinical data (history, clinical examination findings, and diagnostic procedures). The two prediction parameters were explored using the application of Decision Trees, Multilayer Perceptron, Bayes Network, and Naïve Bayes. The machine learning algorithms were able to predict the need for surgery and survivability likelihood of horses presented with acute abdomen (colic) with 76% and 85% accuracy, respectively. The application of this technology in the different clinical fields of veterinary medicine appears to be of a value and warrants further investigation and testing.