Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

PURPOSE: The fixation method commonly employed worldwide for treating unstable fractures of the posterior pelvic ring is the percutaneous iliosacral screw technique. However, prolonged operation time and frequent fluoroscopies result in surgical risks. This study aimed to investigate whether a new triangulation method could reduce operative and fluoroscopy times and increase the accuracy of screw placement. METHODS: This study is a real-world retrospective cohort analysis that examined a patient cohort who underwent percutaneous iliosacral screw fixation between January 1, 2019 and December 31, 2022. Inclusion criteria were patients (1) diagnosed with posterior pelvic ring instability who underwent pelvic fracture closed reduction and percutaneous S1 transverse-penetrating iliosacral screw placement and (2) aged >18 years. Exclusion criteria were: (1) combined proximal femoral fractures, (2) severe soft tissue injury in the surgical area, (3) incomplete imaging data, and (4) declining to provide written informed consent by the patient. The patients were divided into 2 groups according to the screw insertion method: conventional and triangulation methods. Screw placement and fluoroscopy times recorded by the C-arm were compared between the 2 methods. The accuracy of screw placement was evaluated by Smith grading on postoperative CT. Normality tests were conducted to assess the distribution of the quantitative variables and the Chi-square test was used to compare the qualitative variables. RESULTS: The study included a total of 94 patients diagnosed with posterior pelvic ring instability, who underwent percutaneous iliosacral screw placement. The patients were divided into 2 groups: 46 patients treated with the conventional surgical method and 48 patients received the triangulation method. The operation time (61.13±9.69 vs. 35.77±6.27) min and fluoroscopy frequency times (52.15±9.29 vs. 24.40±4.04) of the triangulation method were significantly reduced (p<0.001). CONCLUSIONS The use of a triangular positioning technique for the surface positioning of percutaneous iliosacral screws could reduce the operative time and fluoroscopy frequency. And the screw placement accuracy using this new method was comparable to that using other conventional methods.
Humans ; Retrospective Studies ; Bone Screws ; Pelvic Bones/surgery* ; Male ; Female ; Fracture Fixation, Internal/methods* ; Fractures, Bone/surgery* ; Adult ; Middle Aged ; Fluoroscopy ; Aged ; Sacrum/surgery* ; Operative Time

OBJECTIVE: To evaluate the efficacy and safety of Shexiang Tongxin Dropping Pill (STDP) in treating stable angina patients with phlegm-heat and blood-stasis syndrome by exercise duration and metabolic equivalents. METHODS: This multicenter, randomized, double-blind, placebo-controlled clinical trial enrolled stable angina patients with phlegm-heat and blood-stasis syndrome from 22 hospitals. They were randomized 1:1 to STDP (35 mg/pill, 6 pills per day) or placebo for 56 days. The primary outcome was the exercise duration and metabolic equivalents (METs) assessed by the standard Bruce exercise treadmill test after 56 days of treatment. The secondary outcomes included the total angina symptom score, Chinese medicine (CM) symptom scores, Seattle Angina Questionnaire (SAQ) scores, changes in ST-T on electrocardiogram and adverse events (AEs). RESULTS: This trial enrolled 309 patients, including 155 and 154 in the STDP and placebo groups, respectively. STDP significantly prolonged exercise duration with an increase of 51.0 s, compared to a decrease of 12.0 s with placebo (change rate: -11.1% vs. 3.2%, P<0.01). The increase in METs was significantly greater in the STDP group than in the placebo group (change: -0.4 vs. 0.0, change rate: -5.0% vs. 0.0%, P<0.01). The improvement of total angina symptom scores (25.0% vs. 0.0%), CM symptom scores (38.7% vs. 11.8%), reduction of nitroglycerin consumption (100.0% vs. 11.3%), and all domains of SAQ, were significantly greater with STDP than placebo (all P<0.01). The changes in Q-T intervals at 28 and 56 days from baseline were similar between the two groups (both P>0.05). Twenty-five participants (16.3%) with STDP and 16 (10.5%) with placebo experienced AEs (P=0.131), with no serious AEs observed. CONCLUSION STDP could improve exercise tolerance in patients with stable angina and phlegm-heat and blood stasis syndrome, with a favorable safety profile. (Registration No. ChiCTR-IPR-15006020).
Humans ; Double-Blind Method ; Drugs, Chinese Herbal/adverse effects* ; Male ; Female ; Middle Aged ; Angina, Stable/physiopathology* ; Aged ; Syndrome ; Treatment Outcome ; Placebos ; Tablets

Numerous studies on the formation and consolidation of memory have shown that memory processes are characterized by phase-dependent and dynamic regulation. Memory retrieval, as the only representation of memory content and an active form of memory processing that induces memory reconsolidation, has attracted increasing attention in recent years. Although the molecular mechanisms specific to memory retrieval-induced reconsolidation have been gradually revealed, an understanding of the time-dependent regulatory mechanisms of this process is still lacking. In this study, we applied a transcriptome analysis of memory retrieval at different time points in the recent memory stage. Differential expression analysis and Short Time-series Expression Miner (STEM) depicting temporal gene expression patterns indicated that most differential gene expression occurred at 48 h, and the STEM cluster showing the greatest transcriptional upregulation at 48 h demonstrated the most significant difference. We then screened the differentially-expressed genes associated with that met the expression patterns of those cluster-identified genes that have been reported to be involved in learning and memory processes in addition to dipeptidyl peptidase 9 (DPP9). Further quantitative polymerase chain reaction verification and pharmacological intervention suggested that DPP9 is involved in 48-h fear memory retrieval and viral vector-mediated overexpression of DPP9 countered the 48-h retrieval-induced attenuation of fear memory. Taken together, our findings suggest that temporal gene expression patterns are induced by recent memory retrieval and provide hitherto undocumented evidence of the role of DPP9 in the retrieval-induced reconsolidation of fear memory.
Animals ; Fear/physiology* ; Male ; Dipeptidyl-Peptidases and Tripeptidyl-Peptidases/genetics* ; Memory Consolidation/physiology* ; Time Factors ; Mental Recall/drug effects* ; Mice ; Gene Expression Profiling

With the continuous rise in the incidence of colorectal cancer and the trend towards younger patient population,the existing treatment options,while able to prolong survival,are difficult to avoid significant side effects.It is imperative to develop new treatment strategies.Luteolin(LUT),as a natural herbal active ingredient,has been proved to have broad-spectrum anti-tumor effects in studies of multiple cancer types.However,the mechanism of LUT action in colorectal cancer has not been systematically elucidated.In this study,for the first time,the molecular mechanism of LUT on colorectal cancer SW620 cells from the perspective of proteomics-glycoproteomics co-regulation was revealed.Proteomic analysis identified 472 differentially expressed proteins.Functional enrichment analysis showed that down-regulated proteins were mainly involved in oxidative stress response,mRNA processing,RNA splicing,and actin filament organization among key biological processes,involving oxidative phosphorylation and peroxisome pathways.Up-regulated proteins were mainly involved in DNA replication,protein folding,and rRNA metabolism,closely related to DNA replication and protein processing pathways in the endoplasmic reticulum.At the level of glycoproteomics,231 differentially expressed intact N-glycopeptides were identified.Functional enrichment analysis of corresponding glycoproteins indicateed that LUT might exert biological effects by regulating biological processes such as nuclear organization,nuclear membrane organization,and Fc receptor-mediated signaling pathways,as well as endoplasmic reticulum protein processing and N-glycan biosynthesis pathways.Analysis of key interaction networks revealed 5 core target proteins namely RPS15A,WDR43,FBL,UTP18,and UTP11.The loss of these proteins had been confirmed to inhibit the proliferation and migration of various tumor cells.Notably,altered glycosylation modifications of the lysosome-associated membrane proteins LAMP1 and LAMP2 suggested that LUT might affect tumor metastatic potential by regulating organelle dynamics.It was found that LUT could inhibit the malignant phenotype of colon cancer cells through a dual mechanism of specifically regulating protein expression networks and glycosylation modification patterns,providing new molecular targets and theoretical basis for precise treatment of colorectal cancer based on natural products.

Accurate identification of endogenous and exogenous substances in food,particularly in competition supplies,is crucial for ensuring food safety and fair competition,as well as for protecting the legitimate rights and professional reputations of athletes.Testosterone(T)and dehydroepiandrosterone(DHEA)are important steroid hormones that can stimulate protein synthesis,increase the number and volume of muscle cells,and promote muscle growth and recovery.Both are often illegally used in the animal husbandry industry to promote animal growth and improve meat quality.However,current research in this area remains limited,and identification technologies require further investigation.This study focused on the techniques for identifying endogenous and exogenous hormones including T and DHEA in beef.A Soxhlet extraction method was established,reducing the pretreatment cycle to 110 min while achieving high extraction efficiency,with recovery rates of 102.5%for T and 91.9%for DHEA,respectively.Based on this,a gas chromatography-combustion-isotope ratio mass spectrometry(GC-C-IRMS)method was developed for analyzing carbon isotopes in T and DHEA,eliminating the need for derivatization.By adding reference materials to the extract,simultaneous measurement of reference materials and target analytes was achieved.The measurement of caffeine reference material,T and DHEA was completed within 40 min,with a measurement repeatability of 0.02‰.Theδ13C values of T and DHEA in standard substances,which may serve as exogenous additives,were determined using elemental analysis-isotope ratio mass spectrometry(EA-IRMS).The results indicated an average δ13C value of-29.44‰±0.81‰(k=1)for 10 T standards and-30.86‰±0.87‰(k=1)for 14 kinds of DHEA standards.This approach effectively distinguished between endogenous sources and exogenous addition of these two hormones in beef,thereby providing vital technical support for the assurance and supervision of food safety.