首页|Nanchang University Reports Findings in Thyroid Cancer (Prediction of TNFRSF9 ex pression and molecular pathological features in thyroid cancer using machine lea rning to construct Pathomics models)
Nanchang University Reports Findings in Thyroid Cancer (Prediction of TNFRSF9 ex pression and molecular pathological features in thyroid cancer using machine lea rning to construct Pathomics models)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Oncology-Thyroid Can cer is the subject of a report. According to news reporting originating from Nan chang, People's Republic of China, by NewsRx correspondents, research stated, "T he TNFRSF9 molecule is pivotal in thyroid carcinoma (THCA) development. This stu dy utilizes Pathomics techniques to predict TNFRSF9 expression in THCA tissue an d explore its molecular mechanisms." Our news editors obtained a quote from the research from Nanchang University, "T ranscriptome data, pathology images, and clinical information from the cancer ge nome atlas (TCGA) were analyzed. Image segmentation and feature extraction were performed using the OTSU's algorithm and pyradiomics package. The dataset was sp lit for training and validation. Features were selected using maximum relevance minimum redundancy recursive feature elimination (mRMR_RFE) and mod eling conducted with the gradient boosting machine (GBM) algorithm. Model evalua tion included receiver operating characteristic curve (ROC) analysis. The Pathom ics model output a probabilistic pathomics score (PS) for gene expression predic tion, with its prognostic value assessed in TNFRSF9 expression groups. Subsequen t analysis involved gene set variation analysis (GSVA), immune gene expression, cell abundance, immunotherapy susceptibility, and gene mutation analysis. High T NFRSF9 expression correlated with worsened progression-free interval (PFI) and a cted as an independent risk factor [hazard ratio (HR) = 2.178 , 95% confidence interval (CI) 1.045-4.538, P = 0.038] . Nine pathohistological features were identified. The GBM Pathomics model demon strated good prediction efficacy [area under the curve (AUC) 0.819 and 0.769] and clinical benefits. High PS was a PFI ris k factor (HR = 2.156, 95% CI 1.047-4.440, P = 0.037). Patients wit h high PS potentially exhibited enriched pathways, increased TIGIT gene expressi on, Tregs infiltration (P <0.0001), and higher rates of ge ne mutations (BRAF, TTN, TG)."
NanchangPeople's Republic of ChinaAs iaCancerCyborgsEmerging TechnologiesGeneticsHealth and MedicineMachi ne LearningOncologyRisk and PreventionThyroid CancerThyroid Neoplasms
NETL
NSTL
