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.

Objective    To analyze a new classification of the left apicoposterior segmental bronchus and summarize its clinical significance. Methods     We accessed the computed tomography imaging data of the inpatients treated in the Department of Thoracic Surgery, Henan Provincial People's Hospital between January and November 2021. We observed and classified the branching pattern of the left apicoposterior segmental bronchus (B1+2) using three-dimensional computed tomography bronchography and angiography (3D-CTBA) technique. And we filtered out the patients who underwent thoracoscopic left apicoposterior segmentectomy and analyzed their clinical data retrospectively to summarize the instructing significance of different bronchial classification in the accurate and safe operation of left apicoposterior segmentectomy. Results     Finally 240 patients were collected, including 131 males and 109 females with a median age of 51.0 (19.0-77.0) years. The anatomical pattern of the left apicoposterior segmental bronchus was divided into four main types based on the branching pattern of the outer subsegmental bronchi (B1+2c): type Ⅰ 10% (24 patients), type Ⅱ 54% (130 patients) , type Ⅲ 17% (40 patients) , type Ⅳ 18% (43 patients) and other variations 1% (3 patients). Thirty-two patients smoothly underwent thoracoscopic left apicoposterior segmentectomy, including 23 patients of type Ⅰ and type Ⅱ receiving LS1+2 resection, the other 9 patients of type Ⅲ and type Ⅳ receiving LS1+2 resection (3 patients), LS1+2c resection (4 patients) and LS1+2(a+b) resection (2 patients). Conclusion     This new classification systematically and concisely elucidates the branching characteristics of the left apicoposterior bronchus. Different branching types are instructive to the left apicoposterior segmentectomy.

Superior vena cava syndrome(SVCS)is a group of clinical syndromes caused by obstruction of the superior vena cava and its major branches from various causes.Pulmonary artery stenosis(PS)is a complication of lung cancer or mediastinal tumours.SVCS combined with PS due to pulmonary metastases from bladder cancer is extremely rare and has not been reported in the literature.Here we reported an old male patient with pulmonary metastases from bladder cancer presenting with swelling of the head,neck and both upper limbs.SVCS combined with PS was clarified by pulmonary artery computed tomography angiography(CTA)and digital subtraction angiography(DSA).Endovascular stenting was used to treat SVCS.Angiography also showed that PS had not caused pulmonary hypertension and did not need to be treated.The swelling of the patient's head,neck and upper limbs was gradually reduced after the procedure.

Objective:To compare the efficacy of the horizontal plate plus raft screws above the acetabulum and fixation with screws only for acetabular fractures combined with dome impaction in the aged patients.Methods:A retrospective cohort study was conducted to analyze the clinical data of 20 aged patients with acetabular fractures combined with dome impaction, who were admitted to Tianjin hospital between May 2013 and January 2023, including 5 males and 15 females, aged 61-84 years [(72.2±7.3)years]. According to Letournel and Judet classification, 13 patients had anterior column fracture, 5 anterior column fracture combined with posterior transverse fracture and 2 two-column fracture. All the patients underwent open reduction and internal fixation through an anterior approach. Of them, 11 patients were treated with the fixation with the horizonal plate plus raft screws above the acetabulum (plate plus raft screw group) and 9 with the screws only (screw only group). The operative time, intraoperative blood loss, and intraoperative fluoroscopy times were compared between the two groups. The quality of fracture reduction was evaluated with the Matta′s radiographic criteria at 3 days after surgery and the function of the hip joint was assessed with Merle D′Aubigné and Postel scoring system at 3 months after surgery and at the last follow-up as well as the excellent and good rate at te last follow-up. The occurrence of postoperative complications was observed.Results:All the patients were followed up for 6-18 months [(13.1±3.1)months]. There were no significant differences in the operative time, intraoperative blood loss or intraoperative fluoroscopy times between the two groups ( P>0.05). According to the Matta′s radiographic criteria at 3 days after surgery, patients with anatomical reduction and satisfactory reduction accounted 6 and 5 in the plate plus raft screw group, compared to 5 and 4 respectively in the screw only group ( P>0.05). The values of Merle D′Aubigné and Postel score at 3 months after surgery and at the last follow-up were (14.0±2.4)points and (15.8±2.2)points in the plate plus raft screw group, which were higher than those in the screw only group [(11.0±2.6)points and (13.0±3.1)points] ( P<0.01). The values of Merle D′Aubigné and Postel score at the last follow-up of both groups were further enhanced from those at 3 months after surgery ( P<0.01). At the last follow-up, 3 patients were rated excellent, 6 good, 1 fair and 1 poor in the plate plus raft screw group, with an excellent and good rate of 81.8%, while in the screw only group, 3 were rated good, 2 fair and 4 poor, with an excellent and good rate of 33.3% ( P<0.05). One patient in the plate plus raft screw group and 5 in the screw only group had displacement of the dome impaction fragment combined with traumatic arthritis after surgery ( P<0.05). Conclusion:For acetabular fractures combined with dome impaction in the aged patients, the horizontal plate plus raft screw above the acetabulum can effectively improve the function restoration of the hip joint and reduce the occurrence of the displacement of the dome impaction fragment and traumatic arthritis after surgery compared to the fixation with screws only.

Objective:To investigate the efficacy of arthroscopic superior capsular reconstruction using composite autologous patch graft combined with tenodesis of the long head of the biceps tendon in the treatment of irreparable massive rotator cuff tears (IMRCT).Methods:A retrospective case series study was performed on 11 IMRCT patients who were admitted to Affiliated Fuyang Hospital of Bengbu Medical University (Fuyang People′s Hospital) from May 2020 to June 2022, including 7 males and 4 females, aged 54-74 years [(62.6±7.3)years]. All the patients were treated with arthroscopic superior capsular reconstruction using composite patch graft combined with tenodesis of the long head of the biceps tendon. The Visual Analogue Scale (VAS), Acromiohumeral Distance (AHD), Constant-Murley score and University of California Los Angeles (UCLA) score and active range of motion of the shoulder joint before, at 6 months after surgery and at the last follow-up were compared. At the last follow-up, the integrity of reconstructed superior capsule and the long head of the biceps tendon was evaluated using MRI of the shoulder joint. Postoperative complications were observed.Results:All the patients were followed up for 13-39 months [16(13, 36)months]. The VAS score, AHD, Constant-Murley score, and UCLA score were 2(2, 3)points, (9.1±1.1)mm, (56.1±5.4)points, and (19.7±2.8)points respectively at 6 months after surgery, which were all significantly improved from those before surgery [6(5, 7)points, (5.1±1.2)mm, (37.9±2.2)points, and (11.8±1.2)points] ( P<0.05). The VAS score, AHD, Constant-Murley score, and UCLA score were 0(0, 1)points, (8.4±0.9)mm, (83.6±3.8)points, and (28.2±2.3)points respectively at the last follow-up, which were all significantly improved from those before surgery ( P<0.05). At the last follow-up, the VAS score or AHD were not significantly improved from those at 6 months after surgery ( P>0.05); Constant-Murley score and UCLA score were both significantly improved from those at 6 months after surgery ( P<0.05). At 6 months after surgery, shoulder active ranges of motion in forward flexion, abduction and external rotation were (134.6±13.5)°, (124.6±18.6)° and 45(40, 50)° respectively, which were all significantly improved compared with those before surgery [(63.2±36.1)°, (65.0±23.1)°, and [30(20, 40)°] ( P<0.05). At the last follow-up, shoulder active ranges of motion in forward flexion, abduction and external rotation were (144.1±12.6)°, (139.6±15.4)° and 60(45, 65)° respectively, which were all significantly improved compared with those before surgery ( P<0.05). There were no significant differences in active range of motion of the shoulder in forward flexion, abduction and external rotation between 6 months after surgery and the last follow-up ( P>0.05). At the last follow-up, MRI revealed integrity of the reconstructed superior joint capsule and the long head of the biceps tendon in 10 patients. One patient developed resorption of the greater tuberosity and 1 showed a partial tear of the supraspinatus tendon at 1 year after surgery. Conclusion:Arthroscopic superior capsular reconstruction using composite autologous patch graft combined with tenodesis of the long head of the biceps tendon can relieve shoulder pain, decrease upward displacement of the humerus head, improve the function and range of motion of the shoulder joint, and reduce complications in the treatment of IMRCT.

The analysis of ammonia nitrogen in real water samples is challenging due to matrix interferences and difficulties for rapid on-site analysis.On the basis of the standard method,i.e.water quality-determination of ammonia nitrogen-salicylic acid spectrophotometry(HJ 536-2009),a simple device for online detecting ammonia nitrogen was developed using a sequential injection analysis(SIA)system in this work.The ammonia nitrogen transformation system,color reaction system,and detection system were built in compatible with the SIA system,respectively.In particular,the detection system was assembled by employing light-emitting diode as the light source,photodiode as the detector,and polyvinylchloride tube as the cuvette,thus significantly reducing the volume,energy consumption and fabricating cost of the detection system.As a result,the accurate analysis of ammonia nitrogen in complex water samples was achieved.A quantitative detection of ammonia nitrogen in water sample was obtained in 12 min,along with linear range extending to 1000 μmol/L,precisions(Relative standard deviation,RSD)of 4.3%(C=10 μmol/L,n=7)and 4.2%(C=500 μmol/L,n=7),and limit of detection(LOD)of 0.65 μmol/L(S/N=3,n=7).The results of interfering experiments showed that the detection of ammonia nitrogen by the developed device was not interfered by the common coexisting ions and components,therefore the environmental water could be directly analyzed,such as reservoir water,domestic sewage,sea water and leachate of waste landfill.The analytical results were consistent with those obtained by the environmental protection standard method(Water quality determination of ammonia nitrogen-salicylic acid spectrophotometry,HJ 536-2009).In addition,the spiking recoveries were in the range of 92.3%-98.1%,further confirming the accuracy and practicality of the developed device.