Fig 2.

Random forest modeling was used to explore multivariable contributions of all QST measures to each binary COPC case classification, with study site, age, gender, and race included as covariates. Contributions of individual variables in the random forest models were quantified using variable importance scores, which estimate the relative contribution of each predictor to the model’s classification of true positives and true negatives. Other QST measures were included in the models but are not plotted because their variable importance factors did not exceed 0.0004. Filled symbols = COPC cases; open symbols = controls. PPT = pressure pain threshold; MCP(T) = mechanical cutaneous pain (threshold); TS = temporal summation; HP = heat pain.