RESUMO
BACKGROUND: Prostate cancer patients with pelvic lymph node metastasis (PLNM) have poor prognosis. Based on EAU guidelines, patients with >5% risk of PLNM by nomograms often receive pelvic lymph node dissection (PLND) during prostatectomy. However, nomograms have limited accuracy, so large numbers of false positive patients receive unnecessary surgery with potentially serious side effects. It is important to accurately identify PLNM, yet current tests, including imaging tools are inaccurate. Therefore, we intended to develop a gene expression-based algorithm for detecting PLNM. METHODS: An advanced random forest machine learning algorithm screening was conducted to develop a classifier for identifying PLNM using urine samples collected from a multi-center retrospective cohort (n = 413) as training set and validated in an independent multi-center prospective cohort (n = 243). Univariate and multivariate discriminant analyses were performed to measure the ability of the algorithm classifier to detect PLNM and compare it with the Memorial Sloan Kettering Cancer Center (MSKCC) nomogram score. RESULTS: An algorithm named 25 G PLNM-Score was developed and found to accurately distinguish PLNM and non-PLNM with AUC of 0.93 (95% CI: 0.85-1.01) and 0.93 (95% CI: 0.87-0.99) in the retrospective and prospective urine cohorts respectively. Kaplan-Meier plots showed large and significant difference in biochemical recurrence-free survival and distant metastasis-free survival in the patients stratified by the 25 G PLNM-Score (log rank P < 0.001 and P < 0.0001, respectively). It spared 96% and 80% of unnecessary PLND with only 0.51% and 1% of PLNM missing in the retrospective and prospective cohorts respectively. In contrast, the MSKCC score only spared 15% of PLND with 0% of PLNM missing. CONCLUSIONS: The novel 25 G PLNM-Score is the first highly accurate and non-invasive machine learning algorithm-based urine test to identify PLNM before PLND, with potential clinical benefits of avoiding unnecessary PLND and improving treatment decision-making.
RESUMO
Prostate cancer (PRAD) is one of the common malignant tumors of the urinary system. In order to predict the treatment results for PRAD patients, this study proposes to develop a risk profile based on endoplasmic reticulum stress (ERS). Based on the Memorial Sloan-Kettering Cancer Center (MSKCC) cohort and the Gene Expression Omnibus database (GSE70769), we verified the predictive signature. Using a random survival forest analysis, prognostically significant ERS-related genes were found. An ERS-related risk score (ERscore) was created using multivariable Cox analysis. In addition, the biological functions, genetic mutations and immune landscape related to ERscore are also studied to reveal the underlying mechanisms related to ERS in PRAD. We further explored the ERscore-related mechanisms by profiling a single-cell RNA sequencing (scRNA-seq) dataset (GSE137829) and explored the oncogenic role of ASNS in PRAD through in vitro experiments. The risk signature composed of eight ERS-related genes constructed in this study is an independent prognostic factor and validated in the MSKCC and GSE70769 data sets. The scRNA-seq data additionally revealed that several carcinogenic pathways were noticeably overactivated in the group with high ERS scores. As one of the prognostic genes, ASNS will significantly inhibit the proliferation, migration and invasion abilities of PRAD cells after its expression is interfered with. In conclusion, this study developed a novel risk-specific ERS-based clinical treatment strategy for patients with PRAD.