With the widespread adoption of low-dose CT screening and the extensive application of high-resolution CT, the detection rate of sub-centimeter lung nodules has significantly increased. How to scientifically manage these nodules while avoiding overtreatment and diagnostic delays has become an important clinical issue. Among them, lung nodules with a consolidation tumor ratio less than 0.25, dominated by ground-glass shadows, are particularly worthy of attention. The therapeutic challenge for this group is how to achieve precise and complete resection of nodules during surgery while maximizing the preservation of the patient's lung function. The "watershed topography map" is a new technology based on big data and artificial intelligence algorithms. This method uses Dicom data from conventional dose CT scans, combined with microscopic (22-24 levels) capillary network anatomical watershed features, to generate high-precision simulated natural segmentation planes of lung sub-segments through specific textures and forms. This technology forms fluorescent watershed boundaries on the lung surface, which highly fit the actual lung anatomical structure. By analyzing the adjacent relationship between the nodule and the watershed boundary, real-time, visually accurate positioning of the nodule can be achieved. This innovative technology provides a new solution for the intraoperative positioning and resection of lung nodules. This consensus was led by four major domestic societies, jointly with expert teams in related fields, oriented to clinical practical needs, referring to domestic and foreign guidelines and consensus, and finally formed after multiple rounds of consultation, discussion, and voting. The main content covers the theoretical basis of the "watershed topography map" technology, indications, operation procedures, surgical planning details, and postoperative evaluation standards, aiming to provide scientific guidance and exploration directions for clinical peers who are currently or plan to carry out lung nodule resection using the fluorescent microscope watershed analysis method.

Objective To investigate the value of artificial intelligence-assisted compressed sensing (ACS) technology for intravenous gadolinium contrast-enhanced magnetic resonance imaging of the inner ear using three-dimensional fluid-attenuated inversion recovery (3D-FLAIR) sequence. Methods The patients received gadolinium contrast-enhanced magnetic resonance imaging using ACS and united compressed sensing (uCS) 3D-FLAIR at Zhongshan Hospital, Fudan University from January to November 2024 were prospectively enrolled. The repetition time was 16 000 ms, and acquisition time was 6 min 40 s and 10 min 24 s in ACS 3D-FLAIR and uCS 3D-FLAIR, respectively. The images on the two sequences were evaluated independently by two radiologists. The image quality of the two sequences was subjectively evaluated and compared. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were compared between the two sequences. The grading consistencies using two sequences and between the two doctors were analyzed. Results There was no statistically difference in subjective score of image quality between the two sequences. SNR and CNR of the ACS 3D-FLAIR sequence were significantly higher than those of the uCS 3D-FLAIR sequence (P＜0.001). The kappa values of grades of cochlear and vestibular endolymphatic hydrops were 0.942 and 0.888 using two sequences (P＜0.001). The kappa values of grades of cochlear and vestibular endolymphatic hydrops using the ACS 3D-FLAIR sequence between the two doctors were 0.784 and 0.831, respectively (P＜0.001); the kappa values of grades of cochlear and vestibular endolymphatic hydrops using uCS 3D-FLAIR sequence between the two doctors were 0.725 and 0.756, respectively (P＜0.001). Conclusions ACS 3D-FLAIR could provide higher SNR and CNR than uCS 3D-FLAIR, and is more suitable for intravenous gadolinium contrast-enhanced magnetic resonance imaging of the inner ear; the endolymphatic hydrops grades using ACS 3D-FLAIR is similar to use uCS 3D-FLAIR.

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.

ObjectiveTo understand the seropositivity of neutralizing antibodies (NAb) and low-level NAb against SARS-CoV-2 infection in the community residents, and to explore the impact of COVID-19 vaccination and SARS-CoV-2 infection on the levels of NAb in human serum. MethodsOn the ground of surveillance cohort for acute infectious diseases in community populations in Shanghai, a proportional stratified sampling method was used to enroll the subjects at a 20% proportion for each age group (0‒14, 15‒24, 25‒59, and ≥60 years old). Blood samples collection and serum SARS-CoV-2 NAb concentration testing were conducted from March to April 2023. Low-level NAb were defined as below the 25^th percentile of NAb. ResultsA total of 2 230 participants were included, the positive rate of NAb was 97.58%, and the proportion of low-level NAb was 25.02% (558/2 230). Multivariate logistic regression analysis indicated that age, infection history and vaccination status were correlated with low-level NAb (all P<0.05). Individuals aged 60 years and above had the highest risk of low-level NAb. There was a statistically significant interaction between booster vaccination and one single infection (aOR=0.38, 95%CI: 0.19‒0.77). Compared to individuals without vaccination, among individuals infected with SARS-CoV-2 once, both primary immunization (aOR=0.23, 95%CI: 0.16‒0.35) and booster immunization (aOR=0.12, 95%CI: 0.08‒0.17) significantly reduced the risk of low-level NAb; among individuals without infections, only booster immunization (aOR=0.28, 95%CI: 0.14‒0.52) showed a negative correlation with the risk of low-level NAb. ConclusionsThe population aged 60 and above had the highest risk of low-level NAb. Regardless of infection history, a booster immunization could reduce the risk of low-level NAb. It is recommended that eligible individuals , especially the elderly, should get vaccinated in a timely manner to exert the protective role of NAb.

ObjectiveTo analyze the epidemiological and clinical characteristics of surveillance cases in a sentinel hospital for pertussis in Jiangxi Province in 2019, and to provide corresponding references for the prevention and control of pertussis. MethodsCase investigation of pertussis was conducted among sentinel hospital surveillance cases, collecting their basic information, epidemiological characteristics, clinical characteristics, and other information. ResultsA total of 125 pertussis surveillance cases were investigated in 2019, including 73 clinically diagnosed cases (58.40%) and 52 confirmed cases (41.60%). The age of onset was mainly concentrated in children under 5 years old (108 cases, 86.40%), with the largest number of cases in infants aged less than 1-year-old (48 cases, 38.40%). Most cases had a history of receiving pertussis vaccine before onset (110 cases, 88.00%), and the intervals between the onset date and the date of last dose of pertussis vaccine in the 1‒2 doses group were significantly shorter than that in the 3‒4 doses group (U=-5.990, P<0.001). Probable household transmission of pertussis was found in 3 cases. All cases had cough symptoms, mainly manifested as whooping cough (77 cases, 61.60%), in addition to other main clinical manifestations, such as fever (76 cases, 60.80%), vomiting (30 cases, 24.00%), conjunctival congestion (27 cases, 21.60%), and inspiratory whoop (16 cases, 12.80%). A total of 73 cases (58.40%) experienced complications, including 1 death case. All the cases had multiple medical visit experiences before this visit, with an interval of 2 (0,3) days between the onset date and the first visit date. The misdiagnosis rate at the first medical visit was 88.00% (110/125), and the misdiagnosis rate of the first visit in secondary and primary hospitals was significantly higher than that in tertiary hospitals, exhibiting a statistically significant difference (χ²=21.582, P<0.001). ConclusionThe clinical symptoms of pertussis cases are often atypical, and the first diagnosis is prone to misdiagnosis, so it’s necessary to further strengthen the early diagnosis capabilities for pertussis cases in healthcare institutions, especially in the primary healthcare institutions.

Animals ; Macaca mulatta ; Optic Disk ; Glaucoma ; Craniocerebral Trauma ; Intraocular Pressure ; Low Tension Glaucoma