# Classification of Clinical Outcomes in Hospitalized Asian Elephants Using Machine Learning and Survival Analysis: A Retrospective Study (2019–2024)

## TL;DR

This study uses machine learning to predict clinical outcomes in hospitalized Asian elephants, showing that data-driven tools can improve veterinary decision-making.

## Contribution

The novel use of machine learning to classify clinical outcomes in Asian elephants using routinely collected clinical data.

## Key findings

- A Random Forest model achieved 86.3% accuracy in classifying treatment outcomes using age, sex, disease group, and length of hospital stay.
- Acute diseases like herpesvirus-hemorrhagic disease showed rapid deterioration, while dental and renal conditions required longer treatment.
- The study demonstrates the feasibility of using clinical data science to improve prognosis and treatment planning in wildlife medicine.

## Abstract

This study analyzed five years of clinical records from 467 Asian elephants admitted to Thailand’s largest referral hospital. Using four routinely collected variables: age, sex, disease group, and length of hospital stay, we developed a machine learning model to classify treatment outcomes. A Random Forest algorithm delivered the best performance, suggesting potential for distinguishing clinical outcomes. Elephants with acute illnesses such as herpesvirus-hemorrhagic disease or toxin exposure typically deteriorated quickly, while those with dental or renal conditions required longer treatment. Such classification models may be useful for in-hospital monitoring and decision support, helping veterinarians anticipate clinical trajectories, communicate prognosis more clearly, and guide care decisions.

Captive Asian elephants (Elephas maximus) frequently present to hospitals with complex, multisystemic diseases, yet veterinarians lack objective tools to predict and classify clinical outcomes. Decision-making often relies on experience or anecdote, and few studies have applied data-driven approaches in wildlife medicine. This study developed a machine learning–based classification model using routinely collected clinical data. A total of 467 medical records from hospitalized elephants at Thailand’s National Elephant Institute (2019–2024) were retrospectively analyzed. Four variables (age, sex, disease group, and length of stay [LOS]) were used to train four classification algorithms: Random Forest, eXtreme Gradient Boosting, Naïve Bayes, and multinomial logistic regression. The Random Forest model achieved the highest classification performance (accuracy = 86.3%; log-loss = 0.374), with disease group, LOS, and age as key predictors. Survival analysis revealed distinct hospitalization trajectories across disease groups: acute conditions like elephant endotheliotropic herpesvirus-hemorrhagic disease and toxicosis showed rapid early declines, whereas dental and renal cases followed more prolonged courses. Our findings demonstrate the preliminary feasibility of outcome classification in elephant care and highlight the potential of clinical data science to improve in-hospital prognostication, monitoring, and treatment planning in zoological and wildlife medicine.