a-g SHapley Additive exPlanation (SHAP) values for model features by class (MIS-C/Non-MIS-C PASC).

The plots show the most significant features as determined by the sum of SHAP value magnitudes over all samples. For each feature, SHAP values for each patient are plotted, with color representing the feature value (e.g. red if feature was present and blue if absent in case of a binary variable). The SHAP values pictured are for the 3 class classification task and the x axis is interpreted as change in log odds for the corresponding outcome (e.g. MIS-C) as opposed to change in probability (in particular, SHAP values are not confined to be between –1 and 1). (ZIP)