# Prediction of differentiation levels in lung adenocarcinoma using peripheral blood inflammatory cytokines and tumor markers

## TL;DR

This study shows that combining blood markers can help predict the aggressiveness of lung adenocarcinoma, improving treatment planning.

## Contribution

A novel model combining inflammatory and tumor markers to predict lung adenocarcinoma differentiation levels.

## Key findings

- AISI, CEA, ferritin, and ProGRP were identified as risk factors for low differentiation LUAD.
- The model achieved an AUC of 0.795 for distinguishing low from high differentiation LUAD.
- Decision curve analysis confirmed the model's clinical utility for personalized treatment planning.

## Abstract

Lung Adenocarcinoma (LUAD) has highly aggressive and lethal, and its degree of differentiation significantly influences prognosis and treatment strategies, yet accurate prediction remains challenging. To assess the predictive value of combining peripheral blood inflammatory markers, such as the aggregate index of systemic inflammation (AISI), with tumor markers, including Carcinoembryonic Antigen (CEA) and Cytokeratin 19 fragment antigen 21−1(CYFRA21−1), etc, for determining LUAD differentiation levels.

This retrospective study included 203 LUAD patients treated at Chongqing Medical University’s Second Affiliated Hospital, categorized by low and high differentiation. Demographic, clinical, and laboratory data including peripheral blood inflammatory and tumor markers were analyzed. A multivariate logistic regression model evaluated these markers’ predictive accuracy.

AISI (OR = 1.64, 95% CI = 1.08–2.58, p = 0.024), CEA (OR = 1.02, 95% CI = 1.00–1.04, p = 0.0497), ferritin (OR = 1.01, 95% CI = 1.00–1.01, p = 0.010), and Progastrin Releasing Peptide (ProGRP) (OR = 1.03, 95% CI = 1.00–1.07, p = 0.047) were risk factors of low differentiation LUAD. The model achieved an Area Under Curve(AUC) of 0.795 (95%CI: 0.726–0.864) for distinguishing low from high differentiation, with decision curve analysis confirming clinical utility.

This model, combining inflammatory and tumor markers, effectively predicts LUAD differentiation, aiding personalized treatment planning, enhancing therapeutic outcomes, and supporting early LUAD detection.