Fig. 4From: Application and interpretation of machine learning models in predicting the risk of severe obstructive sleep apnea in adultsSHAP summary plot to illustrate the model predicting severe OSA at the feature levelThe features were ranked according to the sum of the SHAP values for all patients, and the SHAP values are used to show the distribution of the effect of each feature on the GBM model outputs. Each dot represents a case in the dataset. The color of a dot indicates the value of the feature, with blue indicating low values and red indicating high values. Only the top 10 important predictors are shown in the plot. SHAP, SHapley Additive exPlanations; ESS, Epworth Sleepiness Scale; BQ, Berlin questionnaire; BMI, body mass index; and SBQ, STOP-BANG questionnaireBack to article page