Figure 3 | Scientific Reports

Figure 3

From: Machine learning models for identifying predictors of clinical outcomes with first-line immune checkpoint inhibitor therapy in advanced non-small cell lung cancer

Figure 3

Summary plots for SHAP values. (A) Overall survival. (B) Progression-free survival. For each predictor, one point corresponds to a single patient, and the x-axis represents the impact of the feature on the model’s output for the specific patient. A positive SHAP value contributes to death or disease progression, while a negative value contributes to OS or PFS. Predictors are arranged along the y-axis based on their ranking: the higher the feature is positioned in the plot, the more significant it is in the model. ECOG, Eastern Cooperative Oncology Group; ICI, immune checkpoint inhibitor; PD-L1, programmed cell death-ligand 1; SHAP, SHapley Additive exPlanation.

Back to article page