A machine learning approach to predict treatment response in myofascial pain patients receiving masseter trigger point injections.
Machine learning model predicted masseter trigger point injection success on external validation
A machine learning approach to predict treatment response in myofascial pain patients receiving masseter trigger point injections.
Trigger point injection (trigger point injection) therapy is widely used for masseter myofascial pain syndrome (myofascial pain syndrome), yet outcomes vary substantially.
To develop, externally validate, and generalize ensemble machine learning models for predicting composite treatment success following masseter trigger point injection, and to deploy a web-based clinical decision support system (clinical decision support system).
This multicenter study included 1,181 patients with DC/TMD‑diagnosed masseter myofascial pain syndrome treated with one of six injectable modalities.
Overall composite success rate was 43.1%.
External PR‑AUC values were 0.759 (Random Forest) and 0.761 (XGBoost).
Both models showed good calibration and positive net benefit on decision curve analysis across clinically relevant thresholds.
SHAP analysis identified baseline maximum mouth opening, OHIP-14, age, pain intensity, and injectable modality as the most influential predictors, with consistent rankings across models and cohorts.
Machine learning models demonstrated good ability to predict multidimensional treatment success following masseter trigger point injection.
Baseline maximum mouth opening, OHIP-14, age, pain intensity, and injectable modality were the strongest outcome determinants.
External validation, SHAP interpretability, and decision curve analysis support model robustness and potential clinical utility for personalized treatment planning in myofascial pain syndrome.