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.

Background::Although the treatment of peripheral T-cell lymphoma (PTCL) has undergone advancements during the past several years, the response rate and long-term effects with respect to patients with PTCL remain unsatisfactory—particularly for relapsed or refractory (R/R) patients. This phase II trial was designed to explore the efficacy and safety of an all-oral regimen of chidamide plus prednisone, cyclophosphamide, and thalidomide (CPCT) for R/R PTCL patients who could not tolerate the standard chemotherapy for a variety of reasons.Methods::We conducted a multicenter phase II clinical trial in which we combined chidamide (30 mg twice weekly) with prednisone (20 mg daily after breakfast), cyclophosphamide (50 mg daily after lunch), and thalidomide (100 mg daily at bedtime) (the CPCT regimen) for a total of fewer than 12 cycles as an induction-combined treatment period, and then applied chidamide as single-drug maintenance. Forty-five patients were ultimately enrolled from August 2016 to April 2021 with respect to Chinese patients at nine centers. Our primary objective was to assess the overall response rate (ORR) after the treatment with CPCT.Results::Of the 45 enrolled patients, the optimal ORR and complete response (CR)/CR unconfirmed (CRu) were 71.1% (32/45) and 28.9% (13/45), respectively, and after a median follow-up period of 56 months, the median progression-free survival (PFS) and overall survival (OS) were 8.5 months and 17.2 months, respectively. The five-year PFS and OS rates were 21.2% (95% confidence interval [CI], 7.9-34.5%) and 43.8% (95% CI, 28.3-59.3%), respectively. The most common adverse event was neutropenia (20/45, 44.4%), but we observed no treatment-related death.Conclusion::The all-oral CPCT regimen was an effective and safe regimen for R/R PTCL patients who could not tolerate standard chemotherapy for various reasons.Trial Registration::ClinicalTrials.gov, NCT02879526.

Objective To compare the effectiveness of TiRobot assisted F screw technique and inverted triangle parallel nail internal fixation in the treatment of unstable femoral neck fractures.Methods A retrospective analysis was conducted on 72 patients with unstable femoral neck fractures who were treated with percutaneous cannulated screw fixation assisted with TiRobot Orthopaedic robot from December 2019 to April 2021.Among them,37 patients were treated with F screw internal fixa-tion,including 16 males and 21 females,aged47 to 64years old with an average of(53.87±5.28)years old;According to Pauwels classification,there were 1 case of type Ⅰ,19 cases of type Ⅱ,17 cases of type Ⅲ;8 cases of combined medical diseases;17 cases of falling,8 cases of traffic accident and 12 cases of falling from height;The time from injury to operation was 29 to 49 hours with average of(35.00±7.34)hours.Another 35 cases used internal fixation with an inverted triangle parallel nail,including 13 males and 22 females with an average age of 46 to 63 years old(52.36±5.05)years old;According to the Pauwels injury classifi-cation:there were 2 cases of type Ⅰ,21 cases of type Ⅱ,12 cases of type Ⅲ;6 cases of medical diseases,15 cases of falling in-jury,9 cases of traffic accident,11 cases of falling injury;The time from injury to operation was 30 to 45 hours with an average of(33.00±6.83)h.The intraoperative blood loss,operation time,intraoperative fluoroscopy times,follow-up time,fracture healing time,postoperative complications were observed and compared between the two groups.The hip joint function was e-valuated by Harris score at 6 months and 12 months after operation.Results There was no significant difference in operation time,intraoperative blood loss,intraoperative fluoroscopy times and other intraoperative data between two groups(P＞0.05).Both groups were followed up regularly,and the follow-up time was 12 to 16 months.The fracture healing time and Harris score of the F screw internal fixation group were better than those of the inverted triangle parallel nail internal fixation group(P＜0.05).There was 1 case of femoral neck shortening in the F screw internal fixation group,1 case of nonunion,1 case of nail withdrawal,and 1 case of lower extremity deep vein thrombosis in the inverted triangle internal fixation group.The incidence of complications in the F screw internal fixation group was lower than that in the inverted triangle parallel nail internal fixation group(P＜0.05).Conclusion Percutaneous cannulated F screw technique using Tirobot navigation positioning system is a safe and effective treatment for patients with unstable femoral neck fractures.It can significantly shorten the fracture healing time,reduce the incidence of postoperative complications,significantly improve hip joint function,and improve the quality of life.

Objective:To evaluate the efficacy of acute T-cell lymphoblastic leukemia(T-ALL)in children and explore the prognostic risk factors.Methods:The clinical data of 127 newly diagnosed children with T-ALL admitted to five hospitals in Fujian province from April 2011 to December 2020 were retrospectively analyzed,and compared with children with newly diagnosed acute precursor B-cell lymphoblastic leukemia(B-ALL)in the same period.Kaplan-Meier analysis was used to evaluate the overall survival(OS)and event-free survival(EFS),and COX proportional hazard regression model was used to evaluate the prognostic factors.Among 116 children with T-ALL who received standard treatment,78 cases received the Chinese Childhood Leukemia Collaborative Group(CCLG)-ALL 2008 protocol(CCLG-ALL 2008 group),and 38 cases received the China Childhood Cancer Collaborative Group(CCCG)-ALL 2015 protocol(CCCG-ALL 2015 group).The efficacy and serious adverse event(SAE)incidence of the two groups were compared.Results:Proportion of male,age ≥ 10 years old,white blood cell count(WBC)≥ 50 × 109/L,central nervous system leukemia,minimal residual disease(MRD)≥ 1％during induction therapy,and MRD ≥ 0.01％at the end of induction in T-ALL children were significantly higher than those in B-ALL children(P＜0.05).The expected 10-year EFS and OS of T-ALL were 59.7％and 66.0％,respectively,which were significantly lower than those of B-ALL(P＜0.001).COX analysis showed that WBC ≥ 100 x 109/L at initial diagnosis and failure to achieve complete remission(CR)after induction were independent risk factors for poor prognosis.Compared with CCLG-ALL 2008 group,CCCG-ALL 2015 group had lower incidence of infection-related SAE(15.8％vs 34.6％,P=0.042),but higher EFS and OS(73.9％vs 57.2％,PEFS=0.090;86.5％vs 62.3％,PoS=0.023).Conclusions:The prognosis of children with T-ALL is worse than children with B-ALL.WBC ≥ 100 × 109/L at initial diagnosis and non-CR after induction(especially mediastinal mass has not disappeared)are the risk factors for poor prognosis.CCCG-ALL 2015 regimen may reduce infection-related SAE and improve efficacy.

Objective:To analyze the prognostic value of del(1p32)in patients with newly diagnosed multiple myeloma(MM).Methods:The clinical data of 341 newly diagnosed MM attended in Jiangsu Province Hospital were retrospective analyzed.Clinical characteristic combined with genetic features,especially del(1p32),were analyzed for survival and prognostic of patients.Results:Among the 341 patients with newly diagnosed MM,24(7.0％)patients were del(1p32)positive.The progression-free survival(PFS)and overall survival(OS)were significantly shorter in MM patients with del(1p3 2)than those without de1(1p32)(PFS:P＜0.001;OS:P＜0.001).The COX proportional-hazards model showed that del(1 p32)was an independent risk factor for PFS and OS of patients with MM.The patients with both 1q21 gain/amplification and del(1p32),as"double-hit chromosome 1",have worse prognosis than those with only 1q21 gain/amplification or only del(1 p32)(PFS:P＜0.001;OS:P＜0.001).Conclusion:Del(1p32)is an independent risk factor for PFS and OS of patients with MM.Del(1p32)detection should be widely used in the prognostic analysis for newly diagnosed MM patients.

Objective:To investigate the protective effect of endogenous ω-3 polyunsaturated fatty acid(PUFA)against cisplatin-induced myelosuppression and the mechanism of reducing apoptosis in bone marrow nucleated cells using mfat-1 transgenic mice.Methods:The experimental animals were divided into 4 groups:wild-type mice normal control group,mfat-1 transgenic mice normal control group,wild-type mice model group and mfat-1 transgenic mice model group.The mice in the model group were injected intraperitoneally with 7.5 mg/kg cisplatin on day 0 and day 7 to construct a myelosuppression model,while the mice in the normal control group were injected intraperitoneally with an equal amount of saline,and their status was observed and their body weight was measured daily.Peripheral blood was taken after 14 day for routine blood analysis,and the content and proportion of PUFA in peripheral blood were detected using gas chromatography.Bone marrow nucleated cells in the femur of mice were counted.The histopathological changes in bone marrow were observed by histopathological staining.The apoptosis of nucleated cells and the expression level changes of apoptosis-related genes in the bone marrow of mice were detected by flow cytometry and fluorescence quantitative PCR.Results:Compared with wild-type mice,mfat-1 transgenic mice showed significantly increased levels of ω-3 PUFA in peripheral blood and greater tolerance to cisplatin.Peripheral blood analysis showed that endogenous ω-3 PUFA promoted the recovery of leukocytes,erythrocytes,platelets and haemoglobin in peripheral blood of myelosuppressed mice.The results of HE staining showed that endogenous ω-3 PUFA significantly improved the structural damage of bone marrow tissue induced by cisplatin.Flow cytometry and PCR showed that,compared with wild-type mice model group,the apoptosis rate of bone marrow nucleated cells in mfat-1 transgenic mice was significantly reduced(P＜0.001),and the expression of anti-apoptotic genes Bcl-2 mRNA was significantly increased(P＜0.01),while the expressions of pro-apoptotic genes Bax and Bak mRNA were significantly reduced(P＜0.001,P＜0.05).Conclusion:Endogenous ω-3 PUFA can reduce cisplatin-induced apoptosis in bone marrow nucleated cells,increase the number of peripheral blood cells and exert a protective effect against cisplatin-induced myelosuppression by regulating the expression of apoptosis-related genes.