Siraj Mahamed Ali

PURPOSE: This study investigated whether the benefit of patients with recurrent and/or metastatic nasopharyngeal carcinoma (R/M NPC) from immune checkpoint inhibitor (ICI)–containing regimens was correlated with the presence of tumor microenvironment (TME) cell subpopulations that correlate with clinical outcomes. PATIENTS AND METHODS: A total of 73 patients with R/M NPC from four prospective trials in three centers using nivolumab monotherapy, nivolumab + gemcitabine, nivolumab + ipilimumab, or avelumab + axitinib were included. Lunit SCOPE IO, an artificial intelligence–powered spatial TME analyzer, analyzed tumor-infiltrating lymphocytes (TILs), macrophages (MPs), fibroblasts (FBs), and endothelial cells in the intratumoral area and adjacent stroma. RESULTS: The median progression-free survival (PFS) was 7.3 months, and the median overall survival (OS) was 30.0 months for the entire cohort. Higher intratumoral immune infiltrates showed association with improved treatment response, with both intratumoral TILs (hazard ratio [HR], 0.44 [95% CI, 0.24 to 0.83]; P = .0081) and intratumoral MPs (HR, 0.5 [95% CI, 0.27 to 0.91]; P = .0209) showing associations with improved PFS in the combined cohort. In contrast, stromal immune populations did not show clear correlations (stromal TILs: HR 1.14, P = .6681; stromal MPs: HR 0.9, P = .7278). Higher stromal FB density was also associated with poor outcomes, showing a trend toward shorter PFS and a significant reduction in OS (HR, 2.44 [95% CI, 1.16 to 5.11]; P < .05). CONCLUSION: The results from this multinational cohort suggest that high intratumoral infiltrations of TILs and MPs, along with low stromal FB densities, may be associated with better response to ICI-containing treatment in NPC. Further studies in larger, expanded cohorts are warranted, and prospective validation is needed.

Baseline characteristics of the test sets (test set A, B, and C).

Figure S6. Prediction scores for EGFR mutation prediction between two magnifications in test set C (n = 2,261).

Performance of the ensemble model to predict EGFR mutation status across test set A (n = 1,461) and test set B (n = 599). ROC curves for test set A (A–D) and test set B (E–I) are shown. For each test set, the following subgroup analyses were performed: entire dataset (A and E), specimen type (surgical resection and biopsy; B and F), EGFR mutation subtypes (E19del, L858R point mutations, E20ins, T790M, and other mutations; C and G) and scanner type (D and H). For test set B, data source subgroups are additionally presented (I). The sample size (“n”) for each subgroup reflects the number of cases and controls. For EGFR subtypes, each ROC curve was generated using cases positive for the specific EGFR subtype (with or without co-mutations) as EGFR mutant and all EGFR wild-type cases as EGFR wild type. The data represent the AUC together with corresponding 95% CIs.

Baseline characteristics of the training set and tuning set.

Figure S3. Prediction scores of the ensemble model for EGFR mutation prediction across EGFR mutation subtypes in test set A.

Figure S5. Prediction scores for EGFR mutation prediction across scanner types in test set C (n = 2,261).

Generalized performance across different whole-slide scanners and magnifications in test set C (n = 2,261). A and B, Binary classification performance for EGFR mutation prediction across six scanner types (A) and two magnifications (B). The x-axis represents the slides sorted by average value of prediction scores from six scanners. The predicted EGFR classification determined by the model is denoted by color (blue, EGFR mutant; black, EGFR wild type). C and D, Concordance rates of binary classification performance across scanner types (C) and magnifications (D). E, Pearson correlation coefficients (r) for the continuous prediction scores across scanner types and magnifications.

Figure S1. Distribution of prediction scores from the ensemble model in Test Set A (n = 1,461) and Test Set B (n = 599).

Supplementary Materials and Methods