Machine Learning-Based Gene Expression Analysis to Identify Prognostic Biomarkers in Upper Tract Urothelial Carcinoma

Upper tract urothelial carcinoma (UTUC) is a rare and aggressive malignancy with limited prognostic tools to predict disease progression. Due to its low incidence, the molecular pathogenesis of UTUC remains poorly understood, and few studies have explored transcriptomic profiling in this setting. Identifying gene expression biomarkers associated with progression may help improve risk stratification and guide postoperative management.

In this study, we applied a machine learning approach to gene expression data from radical nephroureterectomy (RNU) specimens of 17 consecutive patients with pT2 or pT3 UTUC treated at our institution. RNA was extracted from formalin-fixed paraffin-embedded tissues and sequenced using the Ion AmpliSeq™ Transcriptome Human Gene Expression Kit on an Illumina HiSeq 2500 platform. Differential gene expression was assessed using DESeq2, and results were visualized with volcano plots. Predictive power was evaluated through logistic regression and receiver operating characteristic (ROC) analysis. Gene Ontology enrichment analysis was used to explore biological pathways.

A total of 76 genes were differentially expressed between progressive and non-progressive patients. A random forest classifier identified ten key genes with prognostic potential. Validation with logistic regression yielded an area under the ROC curve (AUC) of 0.88, indicating high discriminative ability. These genes were associated with immune regulation, cell cycle control, and tumor progression.

This pilot study demonstrates the potential of integrating machine learning with transcriptomic analysis to identify prognostic biomarkers in UTUC. Further validation in larger, independent cohorts is needed to confirm these findings and support their clinical application.