Fig. 3: Prognostic performance of the spatial neighborhood GNN predictions in NSCLC survival analysis. | npj Precision Oncology

Fig. 3: Prognostic performance of the spatial neighborhood GNN predictions in NSCLC survival analysis.

From: Graph neural network modeling of spatial tumor-immune interactions identifies prognostic cellular niches in non‑small cell lung cancer

Fig. 3: Prognostic performance of the spatial neighborhood GNN predictions in NSCLC survival analysis.The alternative text for this image may have been generated using AI.

a Kaplan–Meier curves illustrating survival differences between test set patients (N = 129) classified as high- vs. low-risk by the spatial neighborhood GNN (log-rank p < 0.005). b Multivariable Cox regression confirming that both GNN predictions and tumor stage are independent predictors of survival, while IO status is not significant when included in the model (test set, N = 129).

Back to article page