Development and validation of artificial intelligence models for preoperative prediction of inferior mesenteric artery lymph nodes metastasis in left colon and rectal cancer

BackgroundDissection of lymph nodes at the roots of the inferior mesenteric artery (IMAN) should be offered only to selected patients at a major risk of developing IMAN involvement. The aim of this study is to present the first artificial intelligence (AI) models to predict IMAN metastasis risk in the left colon and rectal cancer patients.MethodsA total of 2891 patients with descending colon including splenic flexure, sigmoid colon and rectal cancer undergoing major primary surgery and IMAN dissection were included as a study cohort, which was then split into a training set (67%) and a testing set (33%). Feature selection was conducted using the least absolute shrinkage and selection operator (LASSO) regression model. Seven AI algorithms, namely Support Vector Machine (SVM), Logistic Regression (LR), Extreme Gradient Boosting (XGB), Light Gradient Boosting (LGB), Decision Tree Classifier (DTC), Random Forest (RF) classifier, and Multilayer Perceptron (MLP), as well as traditional multivariate LR model were employed to construct predictive models. The optimal hyperparameters were determined with 5 fold cross-validation. The predictive performance of models and the expert surgeon was assessed and compared in the testing set independently.ResultsThe IMAN involvement incidence was 4.6%. The optimal set of features selected by LASSO included 10 characteristics: neoadjuvant treatment, age, synchronous liver metastasis, synchronous lung metastasis, signet ring adenocarcinoma, neural invasion, lymphovascular invasion, CA199, endoscopic obstruction, T stage evaluated by MRI. The most accurate model derived from MLP showed excellent prediction power with area under the receiver operating characteristic curve (AUROC) of 0.873 and produced 81.0% recognition sensitivity and 82.5% specificity in the testing set independently. In contrast, the judgment of IMAN metastasis by expert surgeon yield rather imprecise and unreliable results with a significantly lower AUROC of 0.509. Additionally, the proposed MLP had the highest net benefits and the largest reduction of unnecessary IMAN dissection without the cost of additional involved IMAN missed.ConclusionMLP model was able to maintain its prediction accuracy in the testing set better than other models and expert surgeons. Our MLP model could be used to help identify IMA nodal metastasis and to select candidates for individual IMAN dissection.     

Lipids,Lipid-Lowering Therapy,and Neuropathy: A Narrative Review

Statins, or 3-hydroxy-3-methylglutaryl coenzyme A reductase inhibitors, are the mainstay of treatment for hypercholesterolemia as they effectively reduce LDL-C levels and risk of atherosclerotic cardiovascular disease. Apart from hyperglycemia, dyslipidemia and HDL dysfunction are known risk factors for neuropathy in people with obesity and diabetes. Although there are case reports of statin-induced neuropathy, ad hoc analyses of clinical trials and observational studies have shown that statins may improve peripheral neuropathy. However, large randomized controlled trials and meta-analyses of cardiovascular outcome trials with statins and other lipid-lowering drugs have not reported on neuropathy outcomes. Because neuropathy was not a prespecified outcome in major cardiovascular trials, one cannot conclude whether statins or other lipid-lowering therapies increase or decrease the risk of neuropathy. The aim of this review was to assess if statins have beneficial or detrimental effects on neuropathy and whether there is a need for large well-powered interventional studies using objective neuropathy end points.     

Genetically predicted childhood obesity and adult atrial fibrillation: A mendelian randomization study

Background and aimsIt is unclear whether the association of childhood obesity with adult atrial fibrillation observed in observational studies reflects causal effects. The aim of this study was to evaluate the association of childhood obesity with adult atrial fibrillation using genetic instruments.Methods and resultsWe used a two-sample Mendelian randomization (MR) design to evaluate the association between childhood obesity and adult atrial fibrillation. Two sets of genetic variants (15 single nucleotide polymorphisms [SNPs] for childhood body mass index [BMI] and 12 SNPs for dichotomous childhood obesity) were selected as instruments. Summary data on SNP-childhood obesity and SNP-atrial fibrillation associations were obtained from recently published genome-wide association studies. Effect estimates were evaluated using inverse-variance weighted (IVW) methods. Other MR analyses, including MR-Egger, simple and weighted median, weighted MBE and MR-PRESSO methods were performed in sensitivity analyses.The IVW models showed that both a genetically predicted one-standard deviation increase in childhood BMI (kg/m²) and higher log-odds of childhood obesity were associated with a substantial increase in the risk of atrial fibrillation (OR = 1.22, 95% CI: 1.11–1.34, P < 0.001; OR = 1.09, 95% CI: 1.04–1.14, P < 0.001). MR-Egger regression showed no evidence of genetic pleiotropy for childhood BMI (intercept = 0.000, 95% CI: ?0.024 to 0.023), but for childhood obesity (intercept = ?0.036, 95% CI: ?0.057 to ?0.015). Similar results were observed using leave-one-out and other MR methods in sensitivity analyses.ConclusionsThis MR analysis found a consistent association between genetically predicted childhood obesity and an increased risk of adult atrial fibrillation. Further research is warranted to validate our findings.