Retrospective study of 10,513 colorectal cancer patients operated at a Shanghai centre, 2008-2020, with 6,739 external validation patients. Five tree-based machine-learning models predicted metastasis; CatBoost gave the highest AUROC for lymph node metastasis, 0.800. SHAP analysis ranked lymphovascular invasion, pT stage and perineural invasion highest; smaller diameter raised predicted metastatic risk. Standardised metastasis rate was 59.9% for tumours 5 cm or less versus 53.6% for larger tumours. Spline Cox analysis found mortality rising below 3 cm; younger men with T4 disease fared worse (P<0.001). Design is retrospective; tumour diameter came from pathology reports and models use postoperative variables.
Why it is interesting: Tumour size is not part of colorectal TNM staging, and this reverses the usual assumption that larger means worse. The effect is concentrated in young men with locally advanced disease.
Abstract — the authors' own words, CC BY
Background
In colorectal cancer, the AJCC T category is defined by the depth of bowel wall invasion rather than by the absolute size of the primary tumor. The clinical value of tumor size in assessing tumor aggressiveness, metastatic risk, and prognosis remains insufficiently investigated.
Aim
To evaluate the clinical value of tumor size in assessing potential metastatic risk and prognostic stratification in colorectal cancer.
Methods
We retrospectively included 10,513 patients with colorectal cancer who underwent surgical treatment at FUSCC between 2008 and 2020. We integrated tumor size with clinicopathological characteristics to assess metastatic risk using machine-learning models and SHAP-based interpretation. By modeling tumor size as both a categorical and continuous variable, we further investigated its prognostic relevance using Kaplan–Meier survival analysis and Cox proportional hazards regression incorporating restricted cubic splines. Additionally, an independent cohort of 6,739 patients from Changhai Hospital was used for external validation.
Results
Machine-learning identified lymph node metastasis as the primary predictive endpoint, with the CatBoost model achieving the highest AUROC of 0.800. SHAP analysis showed that smaller tumor diameter contributed positively to predicted metastatic risk. Multivariable restricted cubic spline analysis further demonstrated a significant nonlinear association between tumor diameter and OS, with mortality risk increasing as tumor diameter decreased within the approximately 0–3 cm range. Among younger male patients with locally advanced disease, tumors ≤3 cm were associated with significantly worse OS and DFS than tumors >5 cm (both
P
< 0.001). External validation yielded similar findings.
Conclusion
Smaller tumor size may paradoxically indicate higher lymph node metastatic risk and poorer prognosis in a subset of patients with colorectal cancer, particularly younger male patients with locally advanced disease. Tumor size may therefore serve as a complementary factor for postoperative risk stratification beyond conventional TNM staging.
Cite this item
BibTeX
Free sign-up. A digest of the new papers twice a week, grouped by domain.
Other drivers in Health today
-
Cancer
Where is cancer incidence rising and falling, what screening and new tests find earlier, and what treatment has done to survival.
7 this week -
Obesity, diabetes and GLP-1
Are obesity and diabetes still rising, what behavioural change and public policy do, and what difference do GLP-1s and other similar drugs make.
7 this week -
Heart and stroke
Whether deaths from heart disease and stroke have stopped falling, what is found earlier, what treatment and prevention do now, and what the deaths say.
4 this week -
Mental health
Deaths by suicide, the life expectancy gap in severe mental illness, and the physical disease that follows it: what mental illness costs in lives.
1 this week -
Dementia
Whether dementia is becoming more or less common, what is now found, what treatment and prevention do, and what the deaths say.
4 this week -
Frailty and multimorbidity
Whether the years added after 85 are healthy ones, how frailty and multiple conditions are measured, and where the data run out.
1 this week
