Big-data analysis: A clinical pathway on endoscopic retrograde cholangiopancreatography for common bile duct stones

BACKGROUND A clinical pathway(CP)is a standardized approach for disease management.However,big data-based evidence is rarely involved in CP for related common bile duct(CBD)stones,let alone outcome comparisons before and after CP implementation.AIM To investigate the value of CP implementation in patients with CBD stones undergoing endoscopic retrograde cholangiopancreatography(ERCP).METHODS This retrospective study was conducted at Nanjing Drum Tower Hospital in patients with CBD stones undergoing ERCP from January 2007 to December 2017.The data and outcomes were compared by using univariate and multivariable regression/linear models between the patients who received conventional care(non-pathway group,n=467)and CP care(pathway group,n=2196).RESULTS At baseline,the main differences observed between the two groups were the percentage of patients with multiple stones(P<0.001)and incidence of cholangitis complication(P<0.05).The percentage of antibiotic use and complications in the CP group were significantly less than those in the nonpathway group[adjusted odds ratio(OR)=0.72,95%confidence interval(CI):0.55-0.93,P=0.012,adjusted OR=0.44,95%CI:0.33-0.59,P<0.001,respectively].Patients spent lower costs on hospitalization,operation,nursing,medication,and medical consumable materials(P<0.001 for all),and even experienced shorter length of hospital stay(LOHS)(P<0.001)after the CP implementation.No significant differences in clinical outcomes,readmission rate,or secondary surgery rate were presented between the patients in the non-pathway and CP groups.CONCLUSION Implementing a CP for patients with CBD stones is a safe mode to reduce the LOHS,hospital costs,antibiotic use,and complication rate.

A deep learning approach for detecting candidates of supernova remnants

Detecting supernova remnant(SNR) candidates in the interstellar medium is a challenging task because SNRs have weak radio signals and irregular shapes. The use of a convolutional neural network is a deep learning method that can help us extract various features from images. To extract SNRs from astronomical images and estimate the positions of SNR candidates, we design the SNR-Net model composed of a training component and a detection component. In addition, transfer learning is used to initialize the network parameters, which improves the speed and accuracy of network training. We apply a T-T plot(of the different brightness temperatures of map pixels at two different frequencies) to calculate the spectral index of SNR candidates. To accelerate the scientific computing process, we take advantage of innovative hardware architecture, such as deep learning optimized graphics processing units, which increases the speed of computation by a factor of 5. A case study suggests that SNR-Net may be applicable to detecting extended sources in the images automatically.