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 compare the bioavailability and bioequivalence of pivastatin calcium dispersive tablets in healthy Chinese subjects.Methods A single dose of pitavastatin calcium(2 mg)was orally administered to the test preparation or reference preparation under fasting and postprandial conditions,respectively.The plasma concentrations of pitavastatin calcium were measured at different time points before and after administration by high performance liquid chromatography-tandem mass spectrometry(HPLC-MS/MS).The bioequivalence of the two formulations was evaluated.Results Subjects received pitavastatin calcium test preparation and reference preparation in fasting condition,the Cmax were(47.79±23.99)and(46.03±21.82)ng·L-1;AUC0_,were(96.56±42.64)and(97.96±35.40)ng·h·L-1;AUC0_∞ were(102.09±43.01)and(103.46±35.62)ng·h·L-1,respectively.The 90％confidence intervals of the geometric mean ratios of Cmax,AUC0_t and AUC0-∞ of pitavastin-calcium test formulation and reference formulation were 96.28％-111.16％,94.46％-101.19％and 94.77％-101.31％,respectively.Subjects received pitavastatin calcium test preparation and reference preparation in fasting condition,the Cmax were(27.32±10.68)and(28.58±11.39)ng·L-1;AUC0_t were(82.76±27.58)and(84.06±29.12)ng·h·L-1;AUC0_∞ were(87.88±26.93)and(89.29±29.18)ng·h·L-1,respectively.The 90％confidence intervals of the geometric mean ratios of Cmax,AUC0_t and AUC0_∞ of the test formulation and the reference formulation of pitavastatin calcium were 87.39％-102.10％,94.62％-101.34％and 94.88％-101.47％,respectively.All of them were within the bioequivalence range of 80.00％to 125.00％.Conclusion Two pivastatin calcium dispersion tablets were bioequivalent and safe in healthy Chinese adult subjects.

Objective To study the bioequivalence and safety of two olmesartan medoxomil and hydrochlorothiazide tablets in Chinese healthy subjects.Methods A total of 24 healthy subjects underwent fasting and postprandial tests in a single-center,randomized,open-label,single-dose,two-formulation,two-sequence,two-period,self-cross-over controlled design.The subjects were administered a single oral dose of the test formulation and reference formulation(each containingolmesartan medoxomil 20 mg and hydrochlorothiazide 12.5 mg)in a random cross-over fashion.The plasma concentrations of olmesartan and hydrochlorothiazide were determined by LC-MS/MS.The non-compartmental model analysis of olmesartan and hydrochlorothiazide was conducted using WinNonlin 7.0 software to calculate pharmacokinetic parameters and assess bioequivalence.Results In the fasting test,the pharmacokinetic parameters of olmesartan of test and reference were as follows:Cmax were(798.35±206.78)and(664.52±168.25)ng·mL-1,AUC0-t were(4 430.71±1 294.87)and(3 976.67±1 083.54)h·ng·mL-1,AUC0-∞ were(4 551.67±1 303.06)and(4 090.37±1 103.97)h·ng·mL-1.The pharmacokinetic parameters of hydrochlorothiazide of test and reference were as follows:Cmax were(92.39±35.96)and(96.15±38.76)ng·mL-1,AUC0_t were(548.69±217.11)and(564.41±208.68)h·ng·mL-1,AUC0-∞ were(603.04±228.59)and(619.26±223.27)h·ng·mL-1.In the fed test,the pharmacokinetic parameters of olmesartan of T and R were as follows:Cmax were(583.15±149.48)and(550.57±104.76)ng·mL-1,AUC0-t were(3 585.18±952.72)and(3 292.19±904.58)h·ng·mL-1,AUC0-∞ were(3 696.05±996.55)and(3 396.30±923.41)h·ng·mL-1.The pharmacokinetic parameters of hydrochlorothiazide of test and reference were as follows:Cmax were(70.30±17.88)and(74.70±21.65)ng·mL-1,AUC0-t were(476.60±119.39)and(492.91±144.81)h·ng·mL-1,AUC0-∞ were(523.37±132.67)and(535.81±151.92)h·ng·mL-1.In fasting and fed condition,the 90％confidence interval(90％CI)of Cmax,AUC0-t and AUC0-∞ of olmesartan and hydrochlorothiazide were in 80.00％-125.00％.Conclusion The two olmesartan medoxomil and hydrochlorothiazide tablets were bioequivalent under fasting and fed conditions,and good security.

Objective To explore the correlation between serum lipid levels of total cholesterol(TC)and triglyceride(TG)and the survival prognosis in postoperative patients with early lung cancer,and to observe the effect of Fuzheng Quxie Prescription on serum lipid levels in postoperative patients with early lung cancer,so as to explore the mechanism of Fuzheng Quxie Prescription in improving the survival prognosis of postoperative patients with early lung cancer.Methods The correlation of serum TC and TG levels with survival prognosis of 257 postoperative patients with early lung cancer admitted in Shanghai Municipal Hospital of Traditional Chinese Medicine from July 2010 to December 2015 was retrospectively analyzed.The changes of serum TC and TG levels in postoperative patients with early lung cancer before and after treatment with Fuzheng Quxie Prescription were statistically analyzed.From January 2017 to April 2021,a prospective analysis of the one-year,two-year,three-year and four-year disease-free survival rates and serum TC and TG levels was carried out in 281 postoperative patients with early lung cancer treated with Fuzheng Quxie Prescription orally in Shanghai Municipal Hospital of Traditional Chinese Medicine(treatment group)and in 287 postoperative patients with early lung cancer who were followed up in clinic while had no medciation in Shanghai Pulmonary Hospital(control group).Results(1)The retrospective study showed that pre-treatment TC level was correlated with progression-free survival(PFS)in postoperative patients with early lung cancer,and the patients with high TC level had longer PFS.There was no significant correlation between pre-treatment TG level and PFS in postoperative patients with early lung cancer.The patients with high TG level had higher short-term survival rate while the patients with low TG level had higher long-term survival rate.(2)The prospective study showed that there were nine cases of recurrence in the treatment group and 24 cases of recurrence in the control group till the last follow-up time on April 1,2021.The one-year,two-year,three-year and four-year disease-free survival rates in the treatment group were 99.3％,96.8％,95.7％and 95.7％,respectively,which were superior to 97.6％,92.3％,89.2％and 87.1％in the control group(P＜0.05),indicating that the recurrence and metastasis in the postoperative patients with early lung cancer treated by Fuzheng Quxie Prescription were significantly reduced when compared with the control group,and the disease-free survival rate was significantly improved.After treatment,the serum levels of TC and TG in the treatment group were increased when compared with those before treatment(P＜0.05)while the control group showed no obvious changes(P＞0.05).The intergroup comparison showed that the increase of serum TC and TG levels in the treatment group was superior to that in the control group(P＜0.05),indicating that Fuzheng Quxie Prescription had regulatory effect on the blood lipid level of patients to a certain extent.Conclusion The analysis of the correlation between pre-treatment blood lipids and PFS prognosis in postoperative patients with early lung cancer indicated that lung cancer patients with high TC level had longer PFS;Fuzheng Quxie Prescription can regulate the blood lipid level of postoperative patients with early lung adenocarcinoma.It is speculated that Fuzheng Quxie Prescription may improve the survival prognosis of postoperative patients with early lung cancer probably by regulating the blood lipid level of the patients.

Objective To analyze the stresses in implanted titanium solid and bone trabecular prosthesis hip replacements.Methods A femur model was built inversely based on Mimics software,and optimized using Geomagic software,and then materialized by SolidWorks software.The osteotomized femur was assembled with the metal femoral stem to form a model,and then the model was imported into ABAQUS for finite element calculation.The upper femur was divided into four regions in different states of integration:medial proximal point(small trochanter region),lateral proximal region(large trochanter region),proximal point of the femoral stem(region around the mid-portion of the styloid process)and distal region(around the end of the styloid process and distal portion).Calculations were carried out over the femoral stresses before and after implantation of titanium solid and trabecular prostheses under gait and stair-climbing loads and the interfacial stresses when the region was unintegrated.The type of deformation at the bone interface was analyzed by means of a stress ellipsoid.Results At the small trochanter region,the stress shielding rates of the trabecular prosthesis under gait and stair climbing loads were reduced by 20.5％and 14.7％compared to the titanium solid prosthesis,respectively.In case of different integration states of the titanium solid prosthesis,the interface tensile stresses under the gait and stair climbing loads were up to 10.842 MPa and 12.900 MPa,and the shear stresses reached 7.050 MPa and 6.805 MPa,respectively;in case of different integration states of the trabecular prosthesis,the interface tensile stresses under the gait and stair climbing loads were up to 3.858 MPa and 4.389 MPa,and the shear stresses reached 4.156 MPa and 3.854 MPa,respectively.Under the 2 different loads,the inboard shear stress ellipsoid of the interface opened toward the sides and the bone interface showed tensile deformation;the outboard shear stress ellipsoid of the interface opened up and down and had compressive deformation.Conclusion After total hip arthroplasty,the overall performance of the trabecular prosthesis is better than that of the titanium solid prosthesis.The unintegrated edges of the prosthesis-bone interface are susceptible to stress concentrations and distortion which may result in occurrence of failures.[Chinese Medical Equipment Journal,2024,45(3):29-35]

Purpose::In patients with heatstroke, disseminated intravascular coagulation (DIC) is associated with greater risk of in-hospital mortality. However, time-consuming assays or a complex diagnostic system may delay immediate treatment. Therefore, the present study proposes a new heatstroke-induced coagulopathy (HIC) score in patients with heat illness as an early warning indicator for DIC.Methods::This retrospective study enrolled patients with heat illness in 24 Chinese hospitals from March 2021 to May 2022. Patients under 18 years old, with a congenital clotting disorder or liver disease, or using anticoagulants were excluded. Data were collected on demographic characteristics, routine blood tests, conventional coagulation assays and biochemical indexes. The risk factors related to coagulation function in heatstroke were identified by regression analysis, and used to construct a scoring system for HIC. The data of patients who met the diagnostic criteria for HIC and International Society on Thrombosis and Haemostasis defined-DIC were analyzed. All statistical analyses were performed using SPSS 26.0.Results::The final analysis included 302 patients with heat illness, of whom 131 (43.4%) suffered from heatstroke, including 7 death (5.3%). Core temperature ( OR = 1.681, 95% CI 1.291 - 2.189, p < 0.001), prothrombin time ( OR = 1.427, 95% CI 1.175 - 1.733, p < 0.001) and D-dimer ( OR = 1.242, 95% CI 1.049 - 1.471, p = 0.012) were independent risk factors for heatstroke, and therefore used to construct an HIC scoring system because of their close relation with abnormal coagulation. A total score ≥ 3 indicated HIC, and HIC scores correlated with the score for International Society of Thrombosis and Hemostasis-DIC ( r = 0.8848, p < 0.001). The incidence of HIC (27.5%) was higher than that of DIC (11.2%) in all of 131 heatstroke patients. Meanwhile, the mortality rate of HIC (19.4%) was lower than that of DIC (46.7%). When HIC developed into DIC, parameters of coagulation dysfunction changed significantly: platelet count decreased, D-dimer level rose, and prothrombin time and activated partial thromboplastin time prolonged ( p < 0.05). Conclusions::The newly proposed HIC score may provide a valuable tool for early detection of HIC and prompt initiation of treatment.