Figure 3.

(A) Integrated clinical and radiomic nomogram (N^Rad+Clin) for small cell lung cancer (SCLC) patients treated with systemic chemotherapy estimating the probability of surviving for 4 years. Instructions for reading the nomogram: locate the risk score on the risk score axis. Draw a line straight up to the Points axis to determine how many points toward the predicted probability of a 4-year overall survival (OS) that the patient receives for radiomic risk score level. Repeat this process for the other predictors, each time drawing a line straight up to the Points axis. Sum the points achieved for each predictor and locate this sum on the Total Points axis. Draw a line straight down to the 4-year Survival axis to determine the patient’s probability of surviving for 4 years. Variables with the greatest discriminatory value are those with the widest point range in the nomogram. Sample data from one patient is shown (tan arrows and ovals). (B) Calibration curve for 4-year survival. The x-axis shows the nomogram predicted probability, while the y-axis gives the actual 4-year survival as estimated by the Kaplan–Meier method. The dotted line represents an ideal agreement between actual and predicted probabilities of 4-year survival. The solid line represents N^Rad+Clin nomogram, and the vertical bars represent 95% CIs. Dots correspond to apparent predictive accuracy.