# Computer-Aided Diagnosis of Equine Temporomandibular Joint Osteoarthritis Using Machine Learning Integrating Computed Tomography Findings and Synovial Fluid Biomarkers

## TL;DR

This study uses machine learning to improve the diagnosis of TMJ osteoarthritis in horses by combining CT scans and synovial fluid biomarkers.

## Contribution

A novel machine learning model outperforms traditional methods by integrating CT and biomarker data for equine TMJ OA diagnosis.

## Key findings

- The best-performing model achieved 0.82 accuracy and 0.85 AUC in distinguishing healthy TMJs from OA-affected ones.
- Age was the only significant factor in OA assignment in the mixed-effects logistic regression model.
- Machine learning models outperformed conventional CT-based diagnosis for equine TMJ OA.

## Abstract

Osteoarthritis (OA) is a painful, degenerative joint disease that affects temporomandibular joints (TMJs). In horses, however, clinically linking pain in the head region to TMJ dysfunction is often challenging. This diagnosis may be supported by computer-aided tools incorporating biomarker data. The study aims to introduce a machine learning-based approach to support the distinction between healthy TMJs and those affected by OA. To achieve this aim, a dataset was created by combining nine computed tomography (CT) findings with twelve synovial fluid biomarkers collected from 82 TMJs. Each TMJ was annotated as healthy or as having TMJ OA based on histological changes co-occurring with CT findings. Using a biomarker dataset, correlations among biomarkers were calculated and supported with a mixed-effects logistic regression model. Using a combined dataset, twelve machine learning models were evaluated, incorporating two feature selection methods and six classification algorithms. Specific biomarker levels showed predominately positive correlations with TMJ OA, age, and with each other; however, only age had a significant effect on OA assignment in the mixed model. The best-performing model achieved an accuracy of 0.82 and an area under the curve of 0.85 for distinguishing between healthy TMJs and TMJ OA. This classification model achieved better performance than conventional TMJ OA diagnosis based only on CT findings.

Horses presenting with temporomandibular joint (TMJ) dysfunctions are often clinically evaluated for TMJ osteoarthritis (OA). Due to the unique characteristic of TMJ-related pain, the clinical diagnosis of equine TMJ OA is challenging; however, it may be supported by computer-aided tools incorporating biomarker data. This study aims to evaluate a machine learning-based approach to address a binary classification distinguishing healthy TMJs from TMJ OA. Among 50 equine cadaver heads, 82 TMJs were included and annotated as healthy or OA based on histological and computed tomography (CT) findings. For each TMJ, nine CT findings were assessed, and synovial fluid was collected for the evaluation of twelve biomarkers. Using a biomarker dataset, correlations among biomarkers were calculated and supported with a mixed-effects logistic regression model. Using a combined dataset, twelve machine learning models, incorporating two feature selection methods and six classification algorithms, were evaluated. Specific biomarker levels showed predominately positive correlations with TMJ OA, age, and with each other; however, only age had a significant effect on OA assignment in the mixed model. The best-performing machine learning model achieved an accuracy of 0.82 and an area under the curve (AUC) of 0.85 for binary TMJ classification. The proposed classification model outperforms conventional diagnostic methods and may therefore be considered beneficial in aiding the diagnosis of equine TMJ OA.