A multi-algorithm prognostic model combining inflammatory indices and surgical features in distal cholangiocarcinoma

Area of Science:

• Oncology
• Biomarkers
• Surgical Outcomes

Background:

• The derived neutrophil-to-lymphocyte ratio (dNLR) is an emerging blood-based inflammatory biomarker.
• Previous studies indicate dNLR has prognostic value in various malignancies.
• The prognostic significance of dNLR in distal cholangiocarcinoma (dCCA) post-curative resection requires investigation.

Purpose of the Study:

• To investigate the prognostic significance of dNLR in patients with distal cholangiocarcinoma (dCCA) after curative resection.
• To evaluate the predictive value of dNLR for postoperative survival in dCCA patients.
• To develop and validate a predictive model for dCCA outcomes incorporating dNLR.

Main Methods:

• Retrospective analysis of clinicopathological data from 177 dCCA patients.
• Receiver operating characteristic (ROC) curve analysis to determine optimal dNLR cutoff (1.60).
• Kaplan-Meier analysis, machine learning models (random forest, RFE, LASSO), and Cox regression for prognostic factor identification and model development.

Main Results:

• An optimal dNLR cutoff of 1.60 was identified, with an AUC of 0.707 for predicting postoperative survival.
• Patients with high dNLR (> 1.60) had significantly worse recurrence-free and overall survival.
• Preoperative dNLR > 1.60 was identified as an independent adverse prognostic factor, improving a predictive model with other clinical variables.

Conclusions:

• Preoperative dNLR > 1.60 is an independent risk factor for poor prognosis in dCCA patients.
• A machine learning-based clinical prediction model incorporating dNLR effectively predicts postoperative outcomes in dCCA.