Towards Sustainable Equine Welfare: Comparative Analysis of Machine Learning Techniques in Predicting Horse Survival

Summary

# Editorial Summary Predicting which horses are likely to survive serious illness or injury remains crucial for veterinary decision-making, yet few systematic comparisons exist between different predictive approaches. Mahmoud (2023) trained and evaluated multiple machine learning algorithms—including decision trees, random forests, support vector machines, and neural networks—on a dataset of horses with documented medical histories and survival outcomes, using standard performance metrics (accuracy, precision, recall, and F1 score) to benchmark each model's reliability. The comparative analysis revealed differential strengths across algorithms, with implications for how practitioners might deploy predictive tools to support prognostic judgement in challenging cases. For equine professionals, this work highlights both the potential value of data-driven decision support and the importance of understanding which computational approaches perform most reliably when predicting survival outcomes from medical records. Such predictive models could eventually improve resource allocation and welfare decisions, though veterinary clinicians should view algorithmic predictions as adjuncts to—rather than replacements for—clinical expertise and horse-owner consultation.

Read the full abstract on the publisher's site

Key Findings

• •Machine learning algorithms (decision trees, random forests, support vector machines, neural networks) can be applied to predict horse survival outcomes from historical medical data
• •Model performance was evaluated using accuracy, precision, recall, and F1 score metrics to assess predictive capability

Conditions Studied