首页|Shandong University Reports Findings in Personalized Medicine (Machine Learning-Enabled Fuhrman Grade in Clear-cell Renal Carcinoma Prediction Using Two-dimensi onal Ultrasound Images)
Shandong University Reports Findings in Personalized Medicine (Machine Learning-Enabled Fuhrman Grade in Clear-cell Renal Carcinoma Prediction Using Two-dimensi onal Ultrasound Images)
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
New research on Drugs and Therapies -Personalized Medicine is the subject of a report. According to news reporting fr om Jinan, People's Republic of China, by NewsRx journalists, research stated, "A ccurate assessment of Fuhrman grade is crucial for optimal clinical management a nd personalized treatment strategies in patients with clear cell renal cell carc inoma (CCRCC). In this study, we developed a predictive model using ultrasound ( US) images to accurately predict the Fuhrman grade." The news correspondents obtained a quote from the research from Shandong Univers ity, "Between March 2013 and July 2023, a retrospective analysis was conducted o n the US imaging and clinical data of 235 patients with pathologically confirmed CCRCC, including 67 with Fuhrman grades III and IV. This study included 201 pat ients from Hospital A who were divided into training set (n = 161) and an intern al validation set (n = 40) in an 8:2 ratio. Additionally, 34 patients from Hospi tal B were included for external validation. US images were delineated using ITK software, and radiomics features were extracted using PyRadiomics software. Sub sequently, separate models for clinical factors, radiomics features, and their c ombinations were constructed. The model's performance was assessed by calculatin g the area under the receiver operating characteristic curve (AUC), calibration curve and decision curve analysis (DCA). In total, 235 patients diagnosed with C CRCC, comprising 168 low-grade and 67 high-grade tumors, were included in this s tudy. A comparison of the predictive performances of different models revealed t hat the logistic regression model exhibited relatively good stability and robust ness. The AUC of the combined model for the training, internal validation and ex ternal validation sets were 0.871, 0.785 and 0.826, respectively, which were hig her than those of the clinical and imaging histology models. Furthermore, the ca libration curve demonstrated excellent concordance between the predicted Fuhrman grade probability of CCRCC using the combined model and the observed values in both the training and validation sets. Additionally, within the threshold range of 0-0.93, the combined model demonstrated substantial clinical utility, as evid enced by DCA. The application of US radiomics techniques enabled objective predi ction of Fuhrman grading in patients with CCRCC. Nevertheless, certain clinical indicators remain indispensable, underscoring the pressing need for their integr ated use in clinical practice. Previous studies have predominantly focused on us ing computed tomography or magnetic resonance imaging modalities to predict the Fuhrman grade of CCRCC. Our findings demonstrate that a prediction model based o n US images is more cost-effective, easily accessible and exhibits commendable p erformance."
JinanPeople's Republic of ChinaAsiaCancerCarcinomasCyborgsDrugs and TherapiesEmerging TechnologiesHealth and MedicineHospitalsKidneyMachine LearningNephrologyOncologyPerson alized MedicinePersonalized TherapySoftwareUltrasound
NETL
NSTL
