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.

Liquiritigenin(LG)is a flavone of pharmacological importance,however,its application potential is severely limited due to its poor water solubility.LG could be disassociated slightly in water to form phenolate anion,therefore,better solubilization effect is expected by inclusion with cationic cyclodextrins(CCDs).In this work,four kinds of CCDs modified with amino groups at the primary face were synthesized,and their solid inclusion complexes with LG were successfully prepared by preparing their saturated solutions.The formation of the solid inclusion complexes was confirmed by scanning electron microscopy(SEM)and powder X-ray diffraction(PXRD),and their supramolecular binding behavior in solution was studied using multiple techniques.A 1∶1 inclusion stoichiometry of inclusion complexation was defined using Job plot by ultraviolet-visible(UV-vis)spectroscopy,and their binding stability constants(Ks)were determined as 2862.77,3494.70,6521.85 and 9599.48 L/mol using UV-vis spectroscopic titration,far more superior to that of nativeβ-CD(Ks=236.79 L/mol).This indicated that the amino side chains on CCDs could actively participate in the inclusion complexation through anion-cation interactions,significantly strengthening the host-guest binding between CCDs and LG.The inclusion modes were further elucidated based on proton and two-dimensional rotating-frame overhauser enhancement spectroscopy(2D-ROESY)nuclear magnetic resonance(NMR)experiments and molecular docking.Water solubility of LG was dramatically promoted up to 4.9 mg/mL,which was 70-fold higher than that of native LG.This study could draw inspiration for the binding and solubilization of phenols such as flavones by design of cationic macrocyclic molecules.

Objective To explore the potential clinical value of the ratio of glycated albumin to albumin(GA/ALB)in the occurrence of heart failure(HF)among patients with coronary atherosclerotic heart disease(CHD).Methods A total of 337 CHD patients admitted to the Department of Cardiology in Shanxi Provincial People's Hospital from July 2023 to June 2024 were selected in this study.CHD patients were divided into HF group and non-HF group based on whether they progressed to HF.The clinical data and laboratory parame-ters of the two groups were compared.Restricted cubic spline curve was used to analyze the relationship be-tween GA/ALB levels and the risk of HF in CHD patients.Receiver operating characteristic curve was applied to evaluate the diagnostic efficacy of GA/ALB,GA,platelet to lymphocyte ratio(PLR),and monocyte to lym-phocyte ratio(MLR)in CHD patients with the occurrence of HF.Logistic regression was used to explore the relationship between serum GA/ALB levels and the risk of CHD patients occurrence of HF,and to analyze the degree of influence and stability of subgroup variables on results.Results There were statistically significant differences in GA/ALB,GA,PLR,MLR,and other indicators between the HF group and the non-HF group in CHD patients(P＜0.05).A non-linear relationship was observed between GA/ALB levels and the risk of HF in CHD patients.When the value of GA/ALB multiplied by 10 was less than 5.751,the risk of HF in CHD pa-tients increased with the increase of GA/ALB levels(P＜0.001).GA/ALB was an effective predictor for HF occurrence in CHD patients.Multivariable Logistic regression model showed that GA/ALB was an independ-ent risk factor for CHD patients with occurrence of HF.Subgroup analysis also confirmed the stability of GA/ALB in predicting the occurrence of HF in CHD patients.Conclusion GA/ALB is an independent risk factor for the occurrence of HF in CHD patients,and monitoring GA/ALB levels provides predictive value for the oc-currence of HF in these patients.

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: 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

The rapid development of artificial intelligence (AI), especially generative AI (GenAI), has already brought, and will continue to bring, revolutionary changes to our daily production and life, as well as create new opportunities and challenges for diagnostic and therapeutic practices in the medical field. Haihe Hospital of Tianjin University collaborates with the National Supercomputer Center in Tianjin, Tianjin University, and other institutions to carry out research in areas such as smart healthcare, smart services, and smart management. We have conducted research and development of a full-process disease diagnosis and treatment assistance system based on GenAI in the field of smart healthcare. The development of this project is of great significance. The first goal is to upgrade and transform the hospital's information center, organically integrate it with existing information systems, and provide the necessary computing power storage support for intelligent services within the hospital. We have implemented the localized deployment of three models: Tianhe "Tianyuan", WiNGPT, and DeepSeek. The second is to create a digital avatar of the chief physician/chief physician's voice and image by integrating multimodal intelligent interaction technology. With generative intelligence as the core, this solution provides patients with a visual medical interaction solution. The third is to achieve deep adaptation between generative intelligence and the entire process of patient medical treatment. In this project, we have developed assistant tools such as intelligent inquiry, intelligent diagnosis and recognition, intelligent treatment plan generation, and intelligent assisted medical record generation to improve the safety, quality, and efficiency of the diagnosis and treatment process. This study introduces the content of a full-process disease diagnosis and treatment assistance system, aiming to provide references and insights for the digital transformation of the healthcare industry.
Artificial Intelligence ; Humans ; Delivery of Health Care ; Generative Artificial Intelligence

OBJECTIVE: This study reports the first imported case of Lassa fever (LF) in China. Laboratory detection and molecular epidemiological analysis of the Lassa virus (LASV) from this case offer valuable insights for the prevention and control of LF. METHODS: Samples of cerebrospinal fluid (CSF), blood, urine, saliva, and environmental materials were collected from the patient and their close contacts for LASV nucleotide detection. Whole-genome sequencing was performed on positive samples to analyze the genetic characteristics of the virus. RESULTS: LASV was detected in the patient's CSF, blood, and urine, while all samples from close contacts and the environment tested negative. The virus belongs to the lineage IV strain and shares the highest homology with strains from Sierra Leone. The variability in the glycoprotein complex (GPC) among different strains ranged from 3.9% to 15.1%, higher than previously reported for the seven known lineages. Amino acid mutation analysis revealed multiple mutations within the GPC immunogenic epitopes, increasing strain diversity and potentially impacting immune response. CONCLUSION The case was confirmed through nucleotide detection, with no evidence of secondary transmission or viral spread. The LASV strain identified belongs to lineage IV, with broader GPC variability than previously reported. Mutations in the immune-related sites of GPC may affect immune responses, necessitating heightened vigilance regarding the virus.
Humans ; China/epidemiology* ; Genome, Viral ; Lassa Fever/virology* ; Lassa virus/classification* ; Molecular Epidemiology ; Phylogeny