Osteoarthritis (OA) of the temporomandibular joint (TMJ) occurs spontaneously in humans and various animal species, including horses. In humans, obtaining tissue samples is challenging and clinical symptoms appear late in the disease progression. Therefore, genetically modified, induced, and naturally occurring animal models play a crucial role in understanding the pathogenesis and evaluating potential therapeutic interventions for TMJ OA. Among the naturally occurring models, the equine TMJ OA model is characterized by slow, age-related progression, a wide range of clinical examinations, and imaging modalities that can be performed on horses, as well as easy tissue and synovial fluid collection. The morphological and functional similarities of TMJ structures in both species make the equine model of TMJ OA an excellent opportunity to track disease progression and response to treatment. However, much work remains to be carried out to determine the utility of human TMJ OA biomarkers in horses. Among the main TMJ OA biomarkers, IL-1, IL-6, TGF-β, TNF-α, and PGE₂ have been recently investigated in the equine model. However, the majority of biomarkers for cartilage degradation, chondrocyte hypertrophy, angiogenesis, and TMJ overload—as well as any of the main signaling pathways—have not been studied so far. Therefore, it would be advisable to focus further research on equine specimens, considering both mediators and signaling.

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.

Computed tomography (CT) is used to support the diagnosis of equine temporomandibular joint (TMJ) disease; however, its diagnostic accuracy remains unclear. This study aimed to evaluate the relationship between CT findings and histopathological manifestations of osteoarthritis (OA) in equine TMJs. A total of 82 TMJs were CT-imaged, sampled, grouped into age-related and OA-related groups, and analyzed for frequency distributions, correlations, and CT-based TMJ OA diagnosis. CT findings were observed in 79% of joints, including ‘CT anatomical variations’ considering to reflect age-related remodeling. Only 50% of joints showed co-occurrence of CT findings and histopathological manifestations of OA, confirming that not all CT findings are indicative of disease. Including all CT findings in the CT-based diagnosis of TMJ OA yielded a specificity of 0.41 (95% CI: 0.26–0.58), suggesting a high rate of false-positive diagnoses. Excluding all ‘CT anatomical variations’ resulted in a sensitivity of 0.56 (95% CI: 0.40–0.72), indicating a substantial number of false-negative diagnoses. However, inclusion of specific ‘CT anatomical variation’—subchondral bone cysts—into the studied CT-based diagnosis increased sensitivity to 0.79 (95% CI: 0.62 to 0.89) while maintaining high specificity of 0.92 (95% CI: 0.80–0.98). Including this subset of CT findings in the diagnosis of equine TMJ OA may improve the accuracy of disease detection; however, the clinical relevance of the present cadaver investigation needs to be confirmed in in vivo studies.