Fig. 4: Yale Combined Modality Model (YMMM) predicts response to immunotherapy in patients with advanced melanoma. | npj Precision Oncology

Fig. 4: Yale Combined Modality Model (YMMM) predicts response to immunotherapy in patients with advanced melanoma.

From: Models that combine transcriptomic with spatial protein information exceed the predictive value for either single modality

Fig. 4

a, b Predictive value of YMMM for best overall response (BOR). Box and whisker plot (a) and receiver operator characteristic (ROC) curve (b) for the prediction of BOR (AUC, 0.88; 95% CI, 0.78 to 0.95; sensitivity, 0.85; specificity, 0.83; PPV, 0.79; NPV, 0.88); on each boxplot, the central line indicates the median and edges indicate the interquartile range. The upper whisker extends from the 75th percentile to the largest value at most the 1.5x interquartile and the lower whisker extends from the 25th percentile to the smallest value at most the ×1.5 interquartile. c Predictive value of YMMM for progression-free survival (PFS). Kaplan–Meier curve showing that patients with high YMMM score have significantly prolonged PFS in comparison with patients with low YMMM score (HR, 0.20; 95% CI, 0.10-0.41; p < 0.0001). d Predictive value of YMMM for overall survival (OS). Kaplan–Meier curve showing that patients with high YMMM score have significantly prolonged OS in comparison with patients with low YMMM score (HR, 0.16; 95% CI, 0.06-0.43; p < 0.0001). Cutoff point for high and low-risk subgroup stratification was calculated based on Youden’s index.

Back to article page