A screening model for advanced colorectal neoplasia based on tumor markers and inflammatory indices: a retrospective study with an online risk calculator - Report - MDSpire
Advertisement
A screening model for advanced colorectal neoplasia based on tumor markers and inflammatory indices: a retrospective study with an online risk calculator
Clinical Report: Noninvasive Screening Model for Advanced Colorectal Neoplasia
Overview
This study developed and validated a noninvasive screening model for advanced colorectal neoplasia (ACN) using blood tumor markers and inflammatory indices. An online risk assessment tool was created, demonstrating an AUC of 0.956.
Background
Colorectal cancer is a significant health concern, often arising from advanced neoplasms. Noninvasive screening methods could enhance accessibility and compliance among patients at risk.
Data Highlights
Parameter
Value
AUC
0.956 (95% CI 0.936–0.976)
Patients with ACN
210
Key Findings
1,290 patients were analyzed, with 210 diagnosed with advanced colorectal neoplasms.
CEA, SII, NLR, ALB, and PLR were identified as independent predictors of ACN.
XGBoost model achieved the highest performance with an AUC of 0.956.
SHAP analysis indicated SII as the most influential predictor.
The online calculator developed can assess individual risk based on blood markers.
Clinical Implications
The study presents a noninvasive approach for screening advanced colorectal neoplasia using blood markers.
Conclusion
The study presents a noninvasive approach for screening advanced colorectal neoplasia, leveraging machine learning and routine blood markers.