ACCENT-based web calculators to predict recurrence and overall survival in stage III colon cancer

Abstract

Background: Current prognostic tools in colon cancer use relatively few patient characteristics. We constructed and validated clinical calculators for overall survival (OS) and time to recurrence (TTR) for stage III colon cancer and compared their performance against an existing tool (Numeracy) and American Joint Committee on Cancer (AJCC) version 7 staging.

Methods: Data from 15936 stage III patients accrued to phase III clinical trials since 1989 were used to construct Cox models for TTR and OS. Variables included age, sex, race, body mass index, performance status, tumor grade, tumor stage, ratio of positive lymph nodes to nodes examined, number and location of primary tumors, and adjuvant treatment (fluoropyrimidine single agent or in combination). Missing data were imputed, and final models internally validated for optimism-corrected calibration and discrimination and compared with AJCC. External validation and comparisons against Numeracy were performed using stage III patients from NSABP trial C-08. All statistical tests were two-sided.

Results: All variables were statistically and clinically significant for OS prediction, while age and race did not predict TTR. No meaningful interactions existed. Models for OS and TTR were well calibrated and associated with C-indices of 0.66 and 0.65, respectively, compared with C-indices of 0.58 and 0.59 for AJCC. These tools, available online, better predicted patient outcomes than Numeracy, both overall and within patient subgroups, in external validation.

Conclusions: The proposed ACCENT calculators are internally and externally valid, better discriminate patient risk than AJCC version 7 staging, and better predict patient outcomes than Numeracy. These tools have replaced Numeracy for online clinical use and will aid prognostication and patient/physician communication.

Figure 1.

Risk of death (on the log hazard ratio scale, y-axis), as a function of (A) age, (C) body mass index (BMI), and (E) lymph node ratio. Risk of recurrence as a function of (B) age, (D) BMI, and (F) lymph node ratio. Solid line = risk function. Dashed lines = 95% confidence bands for the risk function.

Figure 2.

Nomogram for overall survival (OS). Using Figure 2, an example patient’s predictions may be obtained from a single nomogram as follows. First, risk points associated with each variable are obtained via vertical translation of the patient’s variable value (eg, “Male”) to the scale labeled “Points” in the nomogram (ie, being male contributes 12 points to OS risk). Next, the points associated with each variable value for the patient are totaled across the variables. This total is then located on the scale “Total Points” (eg, 119 for OS) and then vertically mapped to obtain the prediction of interest (ie, five-year OS probability of 78%). In the web implementation, 95% confidence intervals for each prediction are also provided. BMI = body mass index; PS = performance status; OS = overall survival.

Figure 3.

Nomogram for TTR. BMI = body mass index; PS = performance status; TTR = time to recurrence.

Figure 4.

Calibration plots for (A) overall survival at five years and (B) time to recurrence at three years. Error bars are 95% confidence intervals. OS = overall survival; TTR = time to recurrence.