Non-specific myocardial fibrosis in young competitive athletes: clinical significance and risk prediction by a powerful machine learning-based model.

Background: Non-specific myocardial fibrosis (NSMF) is a heterogeneous entity. We aimed to evaluate young athletes with and without NSMF to establish potentially clinically significance.

Methods: We analysed data from 328 young athletes. We identified 61 with NSMF and compared them with 75 matched controls. Athletes with NSMF were divided into Group 1 (n = 28) with 'minor' fibrosis and Group 2 (n = 33) with non-insertion point fibrosis, defined as 'major'. Athletes were followed-up for adverse events. Finally, we tested various machine learning (ML) algorithms to create a prediction model for 'major' fibrosis. We created 4 different classifiers.

Results: Athletes of black ethnicity were more likely to have a subepicardial pattern (OR: 5.0, p = 0.004). Athletes with 'major' fibrosis demonstrated a higher prevalence of lateral T-wave inversion (TWI) ( < 0.001) and ventricular arrhythmias (VEs > 500/24 h, p = 0.046; non-sustained VT, p = 0.043). Athletes with 'minor' fibrosis demonstrated higher right ventricular volumes (p = 0.013), maximum Watts (p = 0.022) and maximum VO₂ (p = 0.005). Lateral TWI (p = 0.026) and VO₂ < 44 mL/min/Kg (p = 0.040) remained the only significant predictors for 'major' fibrosis. During follow up, athletes with 'major' fibrosis were 9.1 times more likely to exhibit adverse events (OR 13.4, p = 0.041). All ML models outperformed the benchmark method in predicting significant MF, best accuracy achieved by the random forest classifier (90%).

Conclusions: Lateral TWI and reduced exercise performance are associated with higher burden of fibrosis. Fibrosis was associated with increased ventricular arrhythmia and adverse events. A comprehensive assessment can help develop a ML-based model for significant fibrosis, which could also guide clinical practice and appropriate CMR referrals.