A Novel TNM Classification for Colorectal Cancers based on the Metro-ticket Paradigm

Abstract

Background: Several revisions of the TNM classifications for colorectal cancer (CRC) have acknowledged that the oncological outcomes of stage IIB/IIC CRC are worse than those of stage IIIA. We aimed to develop a novel TNM (nTNM) classification based on the metro-ticket paradigm. Methods: We identified eligible CRC patients from the Surveillance, Epidemiology, and End Results database. The nTNM was developed using distance from the origin on a Cartesian plane incorporating the pN (x-axis) and pT (y-axis) stages, and was compared with the AJCC TNM classification. The areas under the curves (AUCs), calibration curves, and Akaike's information criterion (AIC) were used to evaluate the predictive performances of the two classifications. Clinical benefits were further estimated by decision curve analyses. The validation cohort was applied to validate these findings. Results: A total of 58,192 CRC patients (40,736 training cohort, 17,456 validation cohort) were finally included. In the training cohort, 18,476 patients (45.4%) experienced upstaging and 15,907 patients (39.0%) experienced downstaging in the nTNM classification compared with the TNM classification. Taking the prognosis of stage I as the reference, survival decreased with increasing nTNM stage. The nTNM classification showed better discrimination (AUC, 0.678 vs. 0.667, P<0.001), model-fitting (AIC, 236,525 vs. 237,741), and clinical benefits than the TNM classification. Similar results were found in the validation cohort. Conclusions: The nTNM classification for CRC has better predictive performances and superior accuracy for predicting prognosis compared with the TNM classification. The nTNM classification should therefore be considered in future revisions of the TNM classification.

Keywords: TNM classification; colorectal cancer; metro-ticket; novel TNM classification.

Figure 1

Flow chart for patient selection.

Figure 2

A: the novel TNM (nTNM) classification was defined as the distance from the origin on a Cartesian plane that incorporated two variables: the pN stage (x-axis) and pT stage (y-axis); B: the Pythagoras theorem was used to calculate the distance of any given point from the origin of the plane (0, 0), where [(nTNM)2 = (pN)² + (pT)²]; C: AJCC 8^th TNM classification; D: nTNM classification; E: the staging migration between the nTNM and AJCC 8^th TNM staging systems in the training cohort.

Figure 3

Kaplan-Meier survival curve for overall survival according to the AJCC 8^th TNM and novel TNM (nTNM) staging systems. A: the AJCC 8^th TNM staging system in the training cohort; B: the nTNM staging system in the training cohort; C: the AJCC 8^th TNM staging system in the validation cohort; D: the nTNM staging system in the validation cohort.

Figure 4

The areas under the curves (AUCs) and calibration curves for predicting patient survival. A: AUCs of the AJCC 8^th TNM staging system and novel TNM (nTNM) staging system in the training cohort; B: AUCs of the AJCC 8^th TNM staging system and nTNM staging system in the validation cohort; C, At three-year overall survival (OS) in the training cohort; D, At three-year OS in the validation cohort; E, At five-year OS in the training cohort; F, At five-year OS in the validation cohort.

Figure 5

Decision curve analysis (DCA) of three- and five-year overall survival (OS) of novel TNM (nTNM) staging system and AJCC 8^th TNM staging system. A: the three-year OS in the training cohort; B: the five-year OS in the training cohort; C: the three-year OS in the validation cohort; D: the five-year OS in the validation cohort.