Summary

A systematic review of machine learning methods in predicting tendinopathy in elite and non-elite athletes

Abstract

Background

Tendinopathy, a degenerative condition of tendon collagen protein, is a common sports injury among elite athletes. Despite its prevalence, the manifestation and progression of tendinopathy remain unclear, and the efficiency of diagnosis and treatment modalities is uncertain. The use of artificial intelligence (AI) and machine learning (ML) has shown positive results in disease diagnosis and treatment evaluation. This systematic review examined the plethora of ML methods and their diagnostic yield in predicting tendinopathy.

Methods

A comprehensive search of electronic databases, including Ovid Medline, EMBASE, and the Web of Science, was conducted. The quality of the studies was assessed using the Newcastle-Ottawa scale (NOS). The statistical analysis was perf
ormed using mada package on R software.

Results

Four studies were considered eligible for this meta-analysis, constituting outcomes from 12,611 patients. The ML methods used in the selected studies included Random Forest (RF), convolutional neural networks (CNN), and linear support vector machines (SVM). The results showed that all selected studies demonstrated the relevance of ML in accurately predicting tendinopathy. The pooled diagnostic yield of the ML algorithms estimated an overall sensitivity of 0.74 (95% CI: 0.64 to 0.82) and an overall specificity of 0.69 (95% CI: 0.49 to 0.85). The diagnostic odds ratio (dOR) was 6.01 (95% CI: 1.8 to 20.13), with substantial heterogeneity (I2 = 97.6%).

Conclusion

ML methods can predict tendinopathy accurately in elite and non-elite athletes. However, further research is needed to establish the specific clinical features associated with tendinopathy prevalence.