Nuclear factor kappa B (NF-κB), a key nuclear transcription factor, is associated with prognosis in a variety of human cancers. However, the clinical value of NF-κB in non-small cell lung cancer (NSCLC) is still controversial. Therefore, the aim of this meta-analysis
was to obtain an accurate evaluation of the relationship between NF-κB expression and survival prognosis of NSCLC patients based on published articles. PubMed, EMBASE and Web of Science databases were systematically searched for potential articles. A total of 1159 patients from
7 eligible studies comparing prognostic significance of NF-κB expression levels in NSCLC were included in our meta-analysis. I2 statistic and P value were performed to evaluate heterogeneity using Review Manager version 5.3. The results of analysis were
presented as hazard ratio (HR) or odds ratios with 95% confidence interval (95% CI). Subgroup analysis based on ethnicity of NSCLC patients was conducted to illustrate the potential discrepancy. Significant heterogeneity was considered at I2 > 50% and P < 0.05,
and random-effects model was used. The combined results indicated that higher NF-κB expression was associated with shorter overall survival of NSCLC patients (HR = 2.78, 95% CI = 1.51–5.12, P = 0.001). Moreover, NF-κB expression was closely associated
with tumor stage (HR = 0.32, 95% CI = 0.18–0.57, P < 0.0001) and lymph node metastasis (HR = 0.56, 95% CI = 0.38–0.83, P = 0.004). We conclude that NF-κB expression may be a potential unfavorable prognostic marker for NSCLC patients.
Abstract 3048: Deep learning to predict survival prognosis for patients with non-small cell lung cancer using images and clinical data
