Fig. 8: Machine learning and MEQ-features correlations (n = 20 participants). | Communications Biology

Fig. 8: Machine learning and MEQ-features correlations (n = 20 participants).

From: Neural and molecular changes during a mind-body reconceptualization, meditation, and open label placebo healing intervention

Fig. 8: Machine learning and MEQ-features correlations (n = 20 participants).

A ROC curves and SHAP plots for XGBoost and Random Forest models predicting pre/post classification: AUC = 0.86 (XGBoost) and 0.90 (Random Forest) indicate good classification performance. SHAP plots display the top contributing features ranked by impact on model output. B ROC curves and SHAP plots for XGBoost and Random Forest models predicting novice/advanced classification: AUC = 0.70 (XGBoost) and 0.93 (Random Forest). Abbreviations: R (right), L (left), AN (auditory network), SN (salience network), DMN (default mode network), SMN (somatomotor network), ECN (executive control network), VN (visual network), DAN (dorsal attention network), dlPFC (dorsolateral prefrontal cortex), AI (anterior insula), AG (angular gyrus), GAPDH (glyceraldehyde-3-phosphate dehydrogenase), ATP5PB (ATP synthase peripheral stalk membrane subunit B), FGF (fibroblast growth factor), NTRK2 (neurotrophin receptor tyrosine kinase 2). C Heatmaps of Spearman R correlations between Mystical Experience Questionnaire (MEQ) scores and the top machine learning features per model and time point, with * denoting FDR-adjusted statistical significance (pFDR < 0.05).

Back to article page