Search

Background: Accurate diagnosis of Parkinson's disease (PD) is challenging due to its diverse manifestations. Machine learning (ML) algorithms can improve diagnostic precision, but their generalizability across medical centers in China is underexplored. Objective: To assess the accuracy of an ML algorithm for PD diagnosis, trained and tested on data from different medical centers in China. Methods: A total of 1656 participants were included, with 1028 from Beijing (training set) and 628 from Fuzhou (external validation set). Models were trained using the least absolute shrinkage and selection operator–logistic regression (LASSO-LR), decision tree (DT), random forest (RF), eXtreme gradient boosting (XGboost), support vector machine (SVM), and k-nearest neighbor (KNN) techniques. Hyperparameters were optimized using five-fold cross-validation and grid search techniques. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, accuracy, sensitivity (recall), specificity, precision, and F1 score. Variable importance was assessed for all models. Results: SVM demonstrated the best differentiation between healthy controls (HCs) and PD patients (AUC: 0.928, 95% CI: 0.908–0.947; accuracy: 0.844, 95% CI: 0.814–0.871; sensitivity: 0.826, 95% CI: 0.786–0.866; specificity: 0.861, 95% CI: 0.820–0.898; precision: 0.849, 95% CI: 0.807–0.891; F1 score: 0.837, 95% CI: 0.803–0.868) in the validation set. Constipation, olfactory decline, and daytime somnolence significantly influenced predictability. Conclusion: We identified multiple pivotal variables and SVM as a precise and clinician-friendly ML algorithm for prediction of PD in Chinese patients. [ABSTRACT FROM AUTHOR]

Background: Hypertrophic scar (HS) is characterized by the hyperproliferation of fibroblasts and the excessive deposition of extracellular matrix (ECM). Thrombospondin 1 (THBS1) is a component of the ECM, which has been implicated in HS formation. Objectives: This study aimed to explore whether miR-375/miR-5691 could modulate HS formation by targeting THBS1. Methods: The expression levels of miR-375/miR-5691/THBS1 in HS and normal skin tissues were measured by quantitative reverse transcription-polymerase chain reaction. 3-(4,5)-dimethylthiahiazo (-z-y1)-2,5-di-phenytetrazoliumromide and Western blot assays were performed on fibroblasts isolated from HS tissues (HSFBs) to determine cell proliferation and the expression levels of proliferating cell nuclear antigen (PCNA), apoptosis-related proteins (caspase3/9, cleaved caspase3/9, Bax, and Bcl-2), and ECM-related proteins. The binding sites between THBS1 and miR-375/miR-5691 were predicted by the TargetScan. Dual-luciferase reporter and anti-Ago2 immunoprecipitation assays were applied to confirm the interactions between THBS1 and miR-375/miR-5691. Results: The expression levels of both miR-375 and miR-5691 were downregulated in HS tissues and HSFBs, which were negatively correlated with THBS1 expression levels. The overexpression of miR-375/miR-5691 inhibited cell proliferation and ECM production, and promoted apoptosis of HSFBs, while silencing of miR-375/miR-5691 led to an opposite result. In the mechanism analysis, THBS1 was confirmed as the direct target gene of miR-375/miR-5691. Furthermore, rescue experiments showed that the suppressed growth of HSFBs and ECM production induced by silencing of THBS1 was reversed by miR-375/miR-5691 inhibitors. Conclusion: MiR-375/miR-5691 was downregulated in HS tissues, and it could suppress the hyperproliferation and ECM production of HSFBs by targeting THBS1. [ABSTRACT FROM AUTHOR]