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 evaluate the efficacy and safety of a subanesthetic dose of esketamine in prevent-ing postoperative nausea and vomiting following carboprost administration during cesarean section.Methods One hundred thirty-five full-term singleton parturients,ASAⅠ-Ⅱ,aged 20-40 years,scheduled for elective cesarean section,were recruited.They were randomly assigned to three groups(n=45):the normal saline group(Group C),the palonosetron group(Group P),and the esketamine group(Group E).All parturients received combined spinal-epidural anesthesia,achieving a sensory level of T5-7.Following umbilical cord clamping,carboprost tromethamine was injected into the uterine body.Concurrently,Group C received intravenous normal saline,Group P received palonosetron,and Group E received esketamine.The incidence of nausea,vomiting,and chest discomfort was recorded from the time of carboprost administration until the parturients left the operating theater.Additionally,mean arterial pressure(MAP),heart rate(HR),oxygen saturation(SpO2),and Ramsay sedation scores were mea-sured at six time points:upon entering the room(T0),1 minute before intervention(T1),2 minutes(T2),5 min-utes(T3),15 minutes(T4),and 30 minutes(T5)post-intervention.Maternal satisfaction was evaluated as the parturients left the operating room.Results Compared with group C,the incidence of nausea,vomiting,and chest discomfort in group E was significantly lower(all P<0.05).Additionally,group E showed a significantly lower incidence of nausea and chest discomfort compared to group P(all P<0.05).In terms of maternal satisfaction,group E reported significantly higher levels than both group C(P<0.05)and group P(P<0.05).No significant differences were observed in the incidence of nausea,vomiting,chest discomfort,or satisfaction between the other groups(P>0.05).Conclusion The administration of subanesthetic doses of esketamine significantly decreases the incidence of adverse effects such as nausea,vomiting,and chest tightness that are commonly associated with carboprost tromethamine use during cesarean sections,thereby enhancing patient satisfaction in the perioperative period.

OBJECTIVE: To investigate the clinical characteristics, treatment and prognosis of adult AML patients with NUP98::HOXA9 fusion gene. METHODS: From May 2017 to October 2023， among 2 113 AML patients who visited the Hematology Department of our hospital, patients with NUP98 rearrangements were screened. The clinical characteristics, chromosome karyotypes, immunophenotypes, gene mutations, treatment efficacy and prognosis of the patients with NUP98::HOXA9 positive were analyzed. RESULTS: Among the 2 113 AML patients, there were 18 cases with NUP98 rearrangement, including 14 NUP98::HOXA9 positive cases, with a detection rate of 0.66% (14/2 113). The median age of the NUP98::HOXA9 positive patients was 42.5 (23-64) years old. The most common chromosome karyotype was t(7; 11)(p15; p15). The immunophenotypes of all patients expressed CD13, CD33, CD117 and CD38, and most patients expressed CD34 and cMPO, while only a few expressed HLA-DR. Second-generation sequencing (NGS) was performed to detect genetic mutations associated with leukemia in all 14 patients, and the genes exhibiting a high frequency of mutation were WT1 (10/14), TET2 (7/14), and FLT3-ITD (6/14). Additionally, mutations were also observed in KRAS/NRAS, IDH1, and KIT. Of the 13 patients who received treatment, 9 achieved complete remission (CR), and all 3 patients who received azacytidine(AZA)+ venetoclax (VEN) regimen achieved CR after the first course of treatment. Within this cohort, 6 patients were classified as relapsed/refractory (6/13). 4 patients underwent allogeneic hematopoietic stem cell transplantation (allo-HSCT), of which two achieved long-term survival. The median follow-up time was 12 (2.1-65.0) months, while the median overall survival (OS) and relapse-free survival (RFS) were recorded as 11.4 months and 9.6 months, respectively. CONCLUSION The most common type of NUP98 rearrangement in adults AML patients is NUP98::HOXA9 , which is often accompanied by somatic mutations in WT1, TET2, and FLT3-ITD. These patients are prone to relapse, have short survival time, and generally face poor prognoses. Hopefully, utilization of the AZA+VEN regimen is anticipated to enhance the rate of induced remission in the patients, and some patients may prolong their survival through allo-HSCT. However, more effective treatment methods are still needed to improve the overall prognosis of these patients.
Humans ; Adult ; Leukemia, Myeloid, Acute/genetics* ; Middle Aged ; Prognosis ; Nuclear Pore Complex Proteins/genetics* ; Oncogene Proteins, Fusion/genetics* ; Mutation ; Male ; Female ; Young Adult ; Homeodomain Proteins/genetics*

Objective:To evaluate the early outcomes of total hip arthroplasty (THA) and discuss the revisions post THA in the treatment for Kashin-Beck disease (KBD) with severe hip problems.Methods:This retrospective cohort study enrolled 50 patients (64 hips) with a mean age of 52.4±8.7 years, including 25 male patients and 25 female patients (36 left hips and 28 right hips), who were diagnosed as KBD with hip problems and received THA at Arthritis Clinical and Research Centre, Peking University People's Hospital from October 2019 to January 2024. The leg length discrepancy (LLD), femoral offset (FO), abduction angle and anteversion angle were calculated preoperatively and one week post-operation. The postoperative radiological indexes and the functional outcomes in the last follow-up were compared with the preoperative assessment.Results:The surgical duration was 105(80, 120) min and the bleeding amount was 300(200, 400) ml. All the cases were followed up for an average of 37 months (ranging from 21 to 44 months). Significant differences were found on postoperative radiological images, with LLD improving to 0.50±0.78 cm from a preoperative value of -1.36±0.79 cm, and FO increasing to 3.28±1.01 cm from 2.72±0.83 cm ( P<0.05). The mean postoperative abduction angle and anteversion angle were 42.5°±7.7° and 15.1°±5.9°, respectively. A total of 71.8% and 95.3% hips fell within the Lewinnek safe zones of abduction angle and anteversion angle, respectively. In terms of functional outcomes, the average range of motion improved significantly to 185°(173°, 210°) from a preoperative value of 99°(76°, 123°), and the Harris Hip Score increased from 35(26, 43) preoperatively to 70(63, 80) postoperatively ( P<0.05). During the follow-up, there were complications for two cases of femoral stem loosening, one case of periprosthetic femoral fracture, one case of hip dislocation, and one case of acetabular component loosening with hip subluxation. Additionally, seven patients exhibited Trendelenburg gait. A total of five hips required revision surgery due to severe complications, including two cases of femoral stem loosening, one case of periprosthetic femoral fracture, one case of hip dislocation, and one case of acetabular component loosening with subluxation. Conclusions:Patients with KBD demonstrated significant early improvements in both radiological and functional outcomes following THA.

Objective:To explore the independent association between handgrip strength and chronic kidney disease (CKD) in adult residents in Anhui Province using data from the China Adult Chronic Disease and Risk Factor Surveillance (2023).Methods:A multi-stage stratified cluster random sampling method was used to select residents aged ≥18 years for surveys, physical measurements, and laboratory tests. Relevant covariates were adjusted, and a multivariable logistic regression model was established to infer the association between handgrip strength and CKD, followed by subgroup analysis.Results:A total of 7 295 participants were included in the study, with age of (61.5±13.2) years, and 55.6% of the study participants were women. The results of the multivariate logistic regression analysis showed that with each 1.0 kg increase in handgrip strength, the risk for CKD decreased by 1.3% ( OR=0.987, 95% CI: 0.978-0.997). Compared with those with low handgrip strength, the people with moderate hasdgrip strength ( OR=0.818, 95% CI: 0.694-0.964) and high handgrip strength ( OR=0.729, 95% CI: 0.598-0.989) had lower risk for CKD. In the subgroup analysis, the association between handgrip strength and risk for CKD remained unchanged regardless age, sex, smoking status, and alcohol consumption statuys, and the prevalence of hypertension and hyperlipidemia (interaction P>0.05), except BMI and diabetes. Conclusion:The decline in handgrip strength is associated with an increased risk for CKD in adult residents in Anhui.

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.

AIM To optimize the cellulase-assisted ultrasound extraction process for total flavonoids from Plumbago zeylanica L.,and to evaluate their anti-oxidant activity.METHODS With extraction time,liquid-solid ratio,cellulase addition amount,extraction temperature and ultrasonic power as influencing factors,extraction rate of total flavonoids as an evaluation index,the extraction process was optimized by response surface method on the basis of single factor test.Subsequently,The scavenging rates of extract on DPPH,ABTS and OH free radicals were determined.RESULTS The optimal conditions were determined to be 34∶1 for liquid-solid ratio,3％for cellulase addition amount,51 ℃ for extraction temperature,38 min for extraction time,and 400 W for ultrasonic power,the extraction rate of total flavonoids was(33.411±0.97)％.The IC50 values of three free radicals were 0.13,0.042,3.29 mg/mL,respectively.CONCLUSION This reasonable and reliable method can be used for the cellulase-assisted ultrasound extraction of total flavonoids from P.zeylanica with strong anti-oxidant activity.