ABSTRACT
Background: Artificial intelligence (AI) discrimination models using single radioactive variables in recognition algorithms of lung nodules cannot predict lung cancer accurately. Hence, we developed a clinical model that combines AI with blood test variables to predict lung cancer. Methods: Between 2018 and 2021, 584 individuals (358 patients with lung cancer and 226 individuals with lung nodules other than cancer as control) were enrolled prospectively. Machine learning algorithms including lasso regression and random forest (RF) were used to select variables from blood test data, Logistic regression analysis was used to reconfirm the features to build the nomogram model. The predictive performance was assessed by performing the receiver operating characteristic (ROC) curve analysis as well as calibration, clinical decision and impact curves. A cohort of 48 patients was used to independently validate the model. The subgroup application was analyzed by pathological diagnosis. Findings: A total of 584 patients were enrolled (358 lung cancers, 61.30%,226 patients for the control group) to establish the model. The integrated model identified eight potential factors including carcinoembryonic antigen (CEA), AI score, Pro-Gastrin Releasing Peptide (ProGRP), cytokeratin 19 fragment antigen21-1(CYFRA211), squamous cell carcinoma antigen(SCC), indirect bilirubin(IBIL), activated partial thromboplastin time(APTT) and age. The area under the curve (AUC) of the nomogram was 0.907 (95% CI, 0.881-0.929). The decision and clinical impact curves showed good predictive accuracy of the model. An AUC of 0.844 (95% CI, 0.710 - 0.932) was obtained for the external validation group. Conclusion: The nomogram model integrating AI and clinical data can accurately predict lung cancer, especially for the squamous cell carcinoma subtype.
ABSTRACT
Background: Endoscopic retrograde cholangiopancreatography (ERCP) is an established treatment for common bile duct (CBD) stones. Post- ERCP cholecystitis (PEC) is a known complication of such procedure and there are no effective models and clinical applicable tools for PEC prediction. Methods: A random forest (RF) machine learning model was developed to predict PEC. Eligible patients at The First Hospital of Lanzhou University in China with common bile duct (CBD) stones and gallbladders in-situ were enrolled from 2010 to 2019. Logistic regression analysis was used to compare the predictive discrimination and accuracy values based on receiver operation characteristics (ROC) curve and decision and clinical impact curve. The RF model was further validated by another 117 patients. This study was registered with ClinicalTrials.gov, NCT04234126. Findings: A total of 1117 patients were enrolled (90 PEC, 8.06%) to build the predictive model for PEC. The RF method identified white blood cell (WBC) count, endoscopic papillary balloon dilatation (EPBD), increase in WBC, residual CBD stones after ERCP, serum amylase levels, and mechanical lithotripsy as the top six predictive factors and has a sensitivity of 0.822, specificity of 0.853 and accuracy of 0.855, with the area under curve (AUC) value of 0.890. A separate logistic regression prediction model was built with sensitivity, specificity, and AUC of 0.811, 0.791, and 0.864, respectively. An additional 117 patients (11 PEC, 9.40%) were used to validate the RF model, with an AUC of 0.889 compared to an AUC of 0.884 with the logistic regression model. Interpretation: The results suggest that the proposed RF model based on the top six PEC risk factors could be a promising tool to predict the occurrence of PEC.
ABSTRACT
BACKGROUND: Gallbladder drainage plays a key role in the management of acute cholecystitis (AC) patients. Percutaneous transhepatic gallbladder drainage (PTGBD) is commonly used while endoscopic naso-gallbladder drainage (ENGBD) serves as an alternative. METHODS: A single center, prospective randomized controlled trial was performed. Eligible AC patients were randomly assigned to ENGBD or PTGBD group. Randomization was a computer-generated list with 1:1 allocation. All patients received cholecystectomy 2-3 months after drainage. The primary endpoint was abdominal pain score, and the intention-to-treat population was analyzed. (ClinicalTrials.gov: NCT03701464). FINDINGS: Between Oct 1, 2018 and Feb 29, 2020, 22 out of 61 consecutive AC patients were enrolled in the final analysis. The mean abdominal pain scores before drainage, and at 24, 48, and 72 h after drainage in ENGBD were 6.9 ± 1.1, 4.3 ± 1.2, 2.2 ± 0.8 and 1.5 ± 0.5, respectively, while those of PTGBD were 7.4 ± 1.2, 6.2 ± 1.2, 5.3 ± 1.0 and 3.7 ± 0.9; and the mean gallbladder area tenderness scores were 8.4 ± 1.2, 5.7 ± 0.9, 3.5 ± 0.7, 2.5 ± 0.5 for ENGBD and 8.6 ± 0.9, 7.3 ± 1.0, 7.4 ± 0.5, 4.8 ± 0.9 for PTGBD. The mean abdominal pain and gallbladder area tenderness scores of the ENGBD significantly decreased than the PTGBD (group × time interaction P<0.001, respectively). ENGBD group presented lower post-operative hemorrhage and abdominal drainage tube placement rates (median (IQR) 15[5-20] vs 40[20-70]ml, 3vs9, P = 0.03), and pathological grade and lymphocyte count were observed (P = 0.004) between groups. No adverse events were observed in 3 months follow-up. INTERPRETATION: Compared to PTGBD, ENGBD group presented less pain, better gallbladder pathological grades and less surgical difficulties during cholecystectomy procedures. FUNDING: National Natural Science Foundation of China (82060551).
ABSTRACT
BACKGROUND: Cholangiocarcinoma (CCA) is an invasive malignancy arising from biliary epithelial cells; it is the most common primary tumour of the bile tract and has a poor prognosis. The aim of this study was to screen prognostic biomarkers for CCA by integrated multiomics analysis. METHODS: The GSE32225 dataset was derived from the Gene Expression Omnibus (GEO) database and comprehensively analysed by using R software and The Cancer Genome Atlas (TCGA) database to obtain the differentially expressed RNAs (DERNAs) associated with CCA prognosis. Quantitative isobaric tags for relative and absolute quantification (iTRAQ) proteomics was used to screen differentially expressed proteins (DEPs) between CCA and nontumour tissues. Through integrated analysis of DERNA and DEP data, we obtained candidate proteins APOF, ITGAV and CASK, and immunohistochemistry was used to detect the expression of these proteins in CCA. The relationship between CASK expression and CCA prognosis was further analysed. RESULTS: Through bioinformatics analysis, 875 DERNAs were identified, of which 10 were associated with the prognosis of the CCA patients. A total of 487 DEPs were obtained by using the iTRAQ technique. Comprehensive analysis of multiomics data showed that CASK, ITGAV and APOF expression at both the mRNA and protein levels were different in CCA compared with nontumour tissues. CASK was found to be expressed in the cytoplasm and nucleus of CCA cells in 38 (45%) of 84 patients with CCA. Our results suggested that patients with positive CASK expression had significantly better overall survival (OS) and recurrence-free survival (RFS) than those with negative CASK expression. Univariate and multivariate analyses demonstrated that negative expression of CASK was a significantly independent risk factor for OS and RFS in CCA patients. CONCLUSIONS: CASK may be a tumour suppressor; its low expression is an independent risk factor for a poor prognosis in CCA patients, and so it could be used as a clinically valuable prognostic marker.