Skip to main content
Fig. 6 | Journal of Ovarian Research

Fig. 6

From: Development of machine learning models for diagnostic biomarker identification and immune cell infiltration analysis in PCOS

Fig. 6

Feature explanation of the model based on SHAP. (a) The SHAP summary plot demonstrates the features contributing to the XGBoost prediction model’s prediction of PCOS, ranked from highest to lowest contribution. (b) The position of each feature is arranged in descending order of importance according to the model’s predictions. Each dot represents a patient sample, where purple indicates a lower SHAP value and yellow indicates a higher SHAP value. (c) The SHAP force plot illustrates how various features collectively contribute to the final prediction outcome. By observing the magnitude and direction of the force corresponding to each feature, one can understand the specific impact of each feature on the prediction result

Back to article page