Development and Validation of a Predictive Nomogram for Diagnosing Colorectal Cancer Based on Immune-Nutritional Score.

BACKGROUND

Early diagnosis of colorectal cancer (CRC) can significantly improve prognosis, but currently there is a lack of simple and effective screening methods in clinical practice.

METHODS

This single-center retrospective study included patients with CRC and benign colorectal polyps (BCP) diagnosed at our hospital between December 2020 and December 2023, as well as healthy controls (HCs). Eligible participants were randomly assigned to a training cohort and an internal validation cohort in a 7:3 ratio. Univariable and multivariable logistic regression analyses were performed in the training cohort to identify independent diagnostic predictors of CRC. A diagnostic nomogram was then constructed based on these predictors and internally validated.

RESULTS

Six hundred forty seven CRC, 365 BCP, and 400 HC were ultimately included in the study. Univariate and multivariate analysis showed that sex, HB, CEA, CA19-9, CONUT score, and HALP score were independent diagnostic predictors associated with CRC. The internal validation results indicated that the predictive ability of the nomogram (AUCnomogram = 0.896) is significantly stronger than that of each individual indicator (AUCHB = 0.78, AUCCEA = 0.73, AUCCA19-9 = 0.72, AUCCONUT = 0.64, AUCHALP = 0.72) (p < 0.05). The calibration curves confirmed the high consistency between the predicted probability and observed probability of the nomogram, and the decision curve analysis demonstrated its good clinical utility.

CONCLUSION

This study integrated multiple independent diagnostic predictors of CRC and developed an internally validated diagnostic nomogram with good discrimination and calibration in this single-center retrospective cohort.