Search

Abstract Background To provide a preoperative prediction model for lymph node metastasis in pancreatic cancer patients and provide molecular information of key radiomic features. Methods Two cohorts comprising 151 and 54 pancreatic cancer patients were included in the analysis. Radiomic features from the tumor region of interests were extracted by using PyRadiomics software. We used a framework that incorporated 10 machine learning algorithms and generated 77 combinations to construct radiomics-based models for lymph node metastasis prediction. Weighted gene coexpression network analysis (WGCNA) was subsequently performed to determine the relationships between gene expression levels and radiomic features. Molecular pathways enrichment analysis was performed to uncover the underlying molecular features. Results Patients in the in-house cohort (mean age, 61.3 years ± 9.6 [SD]; 91 men [60%]) were separated into training (n = 105, 70%) and validation (n = 46, 30%) cohorts. A total of 1,239 features were extracted and subjected to machine learning algorithms. The 77 radiomic models showed moderate performance for predicting lymph node metastasis, and the combination of the StepGBM and Enet algorithms had the best performance in the training (AUC = 0.84, 95% CI = 0.77–0.91) and validation (AUC = 0.85, 95% CI = 0.73–0.98) cohorts. We determined that 15 features were core variables for lymph node metastasis. Proliferation-related processes may respond to the main molecular alterations underlying these features. Conclusions Machine learning-based radiomics could predict the status of lymph node metastasis in pancreatic cancer, which is associated with proliferation-related alterations.

Introduction This study aims to evaluate the predictive value of color Doppler ultrasound for the diagnosis of aberrant right subclavian artery (ARSA) with a co-occurring non-recurrent right laryngeal nerve (NRLN). Material and methods In the present study, 58 patients with ARSA (ARSA group) and 1,280 patients without ARSA (controls) were diagnosed by ultrasonography. In addition, 32 patients with ARSA (ARSA operation group) and controls underwent thyroidectomy with surgical exploration with or without NRLN. Then, the incidence of NRLN was analyzed. The right common carotid artery (RCCA) and right subclavian artery (RSA) trends were observed by ultrasound, and classified into two types: RCCA and RSA originating from the innominate artery (IA) (type I), and IA could not be detected (type II). Results A total of 32 cases of NRLN were found in the ARSA operation group, but no case was found in controls, and the difference was statistically significant (p = 0.0006). The difference in the constituent ratio of type I and type II was statistically significant between the ARSA group and controls (p = 0.0002). That is, the IA could not be detected in the ARSA group, which was accompanied by the RCCA that originated from the aortic arch, while the IA was detected in most patients in the control group at the level of the sternoclavicular joints. Conclusions Aberrant right subclavian artery can be rapidly detected by ultra­sonography. Aberrant right subclavian artery occurs when the RCCA originates from the aortic arch during detection. Patients with ARSA sometimes have co-occurring NRLN. Hence, vigilance in protecting the NRLN is needed during an operation.

With the development of intelligent and networked sensor technology,wireless sensor networks were widely used in human life and commercial fields,because wireless sensor network nodes usually only carry limited resources,it is prone to failures due to insufficient resources,the accurate and timely fault diagnosis of WSN nodes can ensure the reliability of information,thus improving the maintainability of WSN and prolonging the service life of WSN.A method of using kernel partial least squares has been proposed to predict the fault reasons,the method overcomes the defects of traditional linear regression method and the nonlinear high dimensional space for data analysis.Through many experiments,the method can absorb the characteristics of canonical correlation analysis and principal component analysis method,provide a more thorough and rich content analysi,that the reason of the fault can be predicted effectively.