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 explore the association between sleep quality and dry eye symptoms in adolescents,so as to provide the evidence for reducing the prevalence of dry eye symptoms. Methods: The study population was adolescents aged 12-24 years from the Psychology and Behavior Investigation of Chinese Residents (PBICR) survey, which was conducted from 20 June to 31 August 2022. A stratified random sampling and quota sampling method was used to select 6 456 adolescents within mainland China. The Ocular Surface Disease Index (OSDI) and Brief version of the Pittsburgh Sleep Quality Index (B-PSQI) were used to assess dry eye symptoms and sleep quality. Multiple Logistic regression model was used to explore the relationship between sleep quality and dry eye symptoms in adolescents. The influence of gender on the association was explored by using interaction terms. Results: A total of 2 815 adolescents reported having dry eye symptoms, with a prevalence of 43.6%. Logistic regression analysis results showed an increased risk of exacerbation of dry eye symptoms in adolescents with poor sleep quality. The OR (95% CI ) for mild, moderate, and severe dry eye symptoms groups were 1.39(1.16-1.67), 1.52(1.28-1.81), and 2.35(2.02-2.72), respectively, compared with the ocularly normal group ( P <0.05). There was a significant interaction between sleep quality and gender on dry eye symptoms in adolescents ( P <0.01). Conclusions Sleep quality is associated with dry eye symptoms in adolescents, and those with poor sleep quality have a higher risk of dry eye symptoms. The effect of sleep quality on dry eye symptoms is greater in boys.

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.

This paper reviews the published articles of recent years on the application of deep learning methods in automatic localization of acupoint, and summarizes it from 3 key links, i.e. the dataset construction, the neural network model design, and the accuracy evaluation of acupoint localization. The significant progress has been obtained in the field of deep learning for acupoint localization, but the scale of acupoint detection needs to be expanded and the precision, the generalization ability, and the real-time performance of the model be advanced. The future research should focus on the support of standardized datasets, and the integration of 3D modeling and multimodal data fusion, so as to increase the accuracy and strengthen the personalization of acupoint localization.
Deep Learning ; Acupuncture Points ; Humans ; Neural Networks, Computer

BACKGROUND: Arsenic trioxide (ATO) is indicated as a broad-spectrum medicine for a variety of diseases, including cancer and cardiac disease. While the role of ATO in hepatic ischemia/reperfusion injury (HIRI) has not been reported. Thus, the purpose of this study was to identify the effects of ATO on HIRI. METHODS: In the present study, we established a 70% hepatic warm I/R injury and partial hepatectomy (30% resection) animal models in vivo and hepatocytes anoxia/reoxygenation (A/R) models in vitro with ATO pretreatment and further assessed liver function by histopathologic changes, enzyme-linked immunosorbent assay, cell counting kit-8, and terminal deoxynucleotidyl transferase-mediated dUTP nick-end labeling (TUNEL) assay. Small interfering RNA (siRNA) for extracellular signal-regulated kinase (ERK) 1/2 was transfected to evaluate the role of ERK1/2 pathway during HIRI, followed by ATO pretreatment. The dynamic process of autophagic flux and numbers of autophagosomes were detected by green fluorescent protein-monomeric red fluorescent protein-LC3 (GFP-mRFP-LC3) staining and transmission electron microscopy. RESULTS: A low dose of ATO (0.75 μmol/L in vitro and 1 mg/kg in vivo ) significantly reduced tissue necrosis, inflammatory infiltration, and hepatocyte apoptosis during the process of hepatic I/R. Meanwhile, ATO obviously promoted the ability of cell proliferation and liver regeneration. Mechanistically, in vitro  studies have shown that nontoxic concentrations of ATO can activate both ERK and phosphoinositide 3-kinase-serine/threonine kinase (PI3K-AKT) pathways and further induce autophagy. The hepatoprotective mechanism of ATO, at least in part, relies on the effects of ATO on the activation of autophagy, which is ERK-dependent. CONCLUSION Low, non-toxic doses of ATO can activate ERK/PI3K-AKT pathways and induce ERK-dependent autophagy in hepatocytes, protecting liver against I/R injury and accelerating hepatocyte regeneration after partial hepatectomy.
Animals ; Arsenic Trioxide ; Autophagy/physiology* ; Reperfusion Injury/prevention & control* ; Mice ; Male ; Proto-Oncogene Proteins c-akt/physiology* ; Arsenicals/therapeutic use* ; Oxides/therapeutic use* ; Liver/metabolism* ; Extracellular Signal-Regulated MAP Kinases/metabolism* ; Mice, Inbred C57BL

BACKGROUND: Chronic kidney disease (CKD)-associated anemia (CKD-anemia) is associated with poor survival, and hemoglobin targets are often not achieved with current therapies. Phase 3 trials have demonstrated the treatment efficacy of roxadustat for CKD-anemia. This phase 4 study aims to evaluate the long-term (52-week) safety and effectiveness of roxadustat in a broad real-world patient population with CKD-anemia with and without dialysis in China. METHODS: This Phase 4 multicenter, open-label, prospective study, conducted from 24 November 2020 to 11 November 2022, evaluated the long-term safety and effectiveness of roxadustat for CKD-anemia in China. Patients aged ≥18 years with CKD-anemia with or without dialysis were included. The initial oral dose was 70-120 mg (weight-based followed by dose adjustment) over 52 weeks. The primary endpoint was safety based on adverse events (AEs). The secondary endpoints were hemoglobin changes from baseline and the proportion of patients who achieved mean hemoglobin ≥100 g/L. Effectiveness evaluable populations 1 (EE1) and EE2 included roxadustat-naïve and previously roxadustat-treated patients, respectively. The safety analysis set (SAF) included all patients who received ≥1 occasion. RESULTS: The EE1, EE2, and SAF populations included 1804, 193, and 2021 patients, respectively. In the SAF, the mean age was 50 ± 14 years, and 1087 patients (53.8%) were male. Mean baseline hemoglobin was 96.9 ± 14.0 g/L in EE1 and 100.3 ± 12.9 g/L in EE2. In EE1, the mean (95% confidence interval) hemoglobin changes from baseline over weeks 24-36 and 36-52 were 14.2 (13.5-14.9) g/L and 14.3 (13.5-15.0) g/L, respectively. Over weeks 24-36 and 36-52, 83.3% and 86.1% of patients in EE1 and 82.7% and 84.7% in EE2 achieved mean hemoglobin ≥100 g/L, respectively. In the SAF, 1643 (81.3%) patients experienced treatment-emergent AEs (TEAEs). Overall, 219 (10.8%) patients experienced drug-related TEAEs. Thirty-eight (1.9%) patients died of TEAEs (unrelated to the study drug). Vascular access thrombosis was uncommon. CONCLUSIONS: Roxadustat (52 weeks) increased hemoglobin and maintained the treatment target in Chinese patients with CKD-anemia with acceptable safety, supporting its use in real-world settings. REGISTRATION Chinese Clinical Trial Registry ( www.chictr.org.cn ) ChiCTR2100046322; CDE ( www.chinadrugtrials.org.cn ) CTR20201568.
Humans ; Male ; Female ; Anemia/etiology* ; Middle Aged ; Renal Insufficiency, Chronic/complications* ; Glycine/adverse effects* ; Isoquinolines/adverse effects* ; Aged ; Prospective Studies ; Adult ; Hemoglobins/metabolism* ; Treatment Outcome ; China ; Registries ; East Asian People

Recent advances in large models demonstrate significant prospects for transforming the field of medical imaging. These models, including large language models, large visual models, and multimodal large models, offer unprecedented capabilities in processing and interpreting complex medical data across various imaging modalities. By leveraging self-supervised pretraining on vast unlabeled datasets, cross-modal representation learning, and domain-specific medical knowledge adaptation through fine-tuning, large models can achieve higher diagnostic accuracy and more efficient workflows for key clinical tasks. This review summarizes the concepts, methods, and progress of large models in medical imaging, highlighting their potential in precision medicine. The article first outlines the integration of multimodal data under large model technologies, approaches for training large models with medical datasets, and the need for robust evaluation metrics. It then explores how large models can revolutionize applications in critical tasks such as image segmentation, disease diagnosis, personalized treatment strategies, and real-time interactive systems, thus pushing the boundaries of traditional imaging analysis. Despite their potential, the practical implementation of large models in medical imaging faces notable challenges, including the scarcity of high-quality medical data, the need for optimized perception of imaging phenotypes, safety considerations, and seamless integration with existing clinical workflows and equipment. As research progresses, the development of more efficient, interpretable, and generalizable models will be critical to ensuring their reliable deployment across diverse clinical environments. This review aims to provide insights into the current state of the field and provide directions for future research to facilitate the broader adoption of large models in clinical practice.
Humans ; Diagnostic Imaging/methods* ; Precision Medicine/methods* ; Image Processing, Computer-Assisted/methods*