Objective To construct a risk prediction model for post-stroke depression based on the neural network algorithm.Methods A prospective study was conducted on 260 stroke patients admitted in our center from March 2021 to March 2024.They were randomly divided into a train-ing set(80％,208 cases)and a verification set(20％,52 cases).According to the occurrence of post-stroke depression within 1 month after stroke,the training set was assigned into post-stroke depression group(62 cases)and non-post-stroke depression group(146 cases).The predictive fac-tors for post-stroke depression occurrence were screened through the training set,and the risk prediction models for post-stroke depression occurrence were constructed with multivariate logis-tic and neural network algorithms in the training set.The prediction efficiency of the two predic-tion models was compared and verified in the verification set.Results Within 1 month after stroke,76 cases(29.23％)experienced post-stroke depression(62 cases in training set and 14 in the validation set).Based on the data in the training set,the levels of CRP,FIB,IL-6,IL-lβ,TNF-αand IL-18,and neutrophil and lymphocyte ratio(NLR)were significant higher in the post-stroke depression group than the non-post-stroke depression group(P＜0.01).Multivariate logistic re-gression analysis showed that CRP(OR=1.494,95％CI:1.239-1.802),FIB(OR=1.924,95％CI:1.191-3.109),IL-6(OR=1.128,95％CI:1.001-1.272),TNF-α(OR=1.051,95％CI:1.010-1.093),IL-1β(OR=1.096,95％CI:1.006-1.194),IL-18(OR=1.019,95％CI:1.002-1.036),and NLR(OR=1.873,95％CI:1.027-3.418)were risk factors for post-stroke depression(P＜0.05,P＜0.01).ROC curve analysis indicated that the AUC value of the predictive model of the neural network algorithm was higher than that of the model of multivariate logistic regression(0.931 vs 0.855,Z=3.448,P＜0.05).Based on the validation set,the former model also had bet-ter accuracy than the latter one(92.31％vs 75.00％,P＜0.05).Conclusion Circulating inflam-matory factors CRP,FIB,IL-6,IL-1β,TNF-α and IL-18,and NLR are related to the risk of post-stroke depression.The prediction model based on above factors combined with neural network al-gorithm can more effectively predict the risk of post-stroke depression.

Objective:To explore associated factors of post-discharge depressive symptom severity in patients with bipolar disorder.Methods:A longitudinal follow-up was conducted to investigate the demographic,behavioral,and clinical characteristics,and social function among discharged patients with bipolar disorder who met the DSM-5 diagnostic criteria.Clinical characteristics were assessed with the Hamilton Depression Scale(HAMD)and Brief Psychiatric Rating Scale(BPRS).Single factor and multivariate regression were carried out to explore the associat-ed factors of depressive symptom severity in patients with bipolar disorder.Results:A total of 298 discharged pa-tients with bipolar disorder were face-to-face interviewed to complete the follow-up survey.At follow-up time,psy-chotic symptoms(standardized(β)=0.18),housework((β)=0.23),social interaction((β)=0.17)and BPRS total score((β)=0.46)were positively associated with HAMD total score.Productive labor and work((β)=-0.27)and person-al life management((β)=-0.15)were negatively associated with HAMD total scores.Conclusion:Post-discharge depressive symptom severity in bipolar disorder patients is influenced by multiple factors.Effective management of psychotic symptoms,combined with enhanced community-based social rehabilitation and functional recovery,may help reduce the persistence or worsening of depressive symptoms and improve prognosis.

Objective:To explore associated factors of post-discharge depressive symptom severity in patients with bipolar disorder.Methods:A longitudinal follow-up was conducted to investigate the demographic,behavioral,and clinical characteristics,and social function among discharged patients with bipolar disorder who met the DSM-5 diagnostic criteria.Clinical characteristics were assessed with the Hamilton Depression Scale(HAMD)and Brief Psychiatric Rating Scale(BPRS).Single factor and multivariate regression were carried out to explore the associat-ed factors of depressive symptom severity in patients with bipolar disorder.Results:A total of 298 discharged pa-tients with bipolar disorder were face-to-face interviewed to complete the follow-up survey.At follow-up time,psy-chotic symptoms(standardized(β)=0.18),housework((β)=0.23),social interaction((β)=0.17)and BPRS total score((β)=0.46)were positively associated with HAMD total score.Productive labor and work((β)=-0.27)and person-al life management((β)=-0.15)were negatively associated with HAMD total scores.Conclusion:Post-discharge depressive symptom severity in bipolar disorder patients is influenced by multiple factors.Effective management of psychotic symptoms,combined with enhanced community-based social rehabilitation and functional recovery,may help reduce the persistence or worsening of depressive symptoms and improve prognosis.

Objective To construct a risk prediction model for post-stroke depression based on the neural network algorithm.Methods A prospective study was conducted on 260 stroke patients admitted in our center from March 2021 to March 2024.They were randomly divided into a train-ing set(80％,208 cases)and a verification set(20％,52 cases).According to the occurrence of post-stroke depression within 1 month after stroke,the training set was assigned into post-stroke depression group(62 cases)and non-post-stroke depression group(146 cases).The predictive fac-tors for post-stroke depression occurrence were screened through the training set,and the risk prediction models for post-stroke depression occurrence were constructed with multivariate logis-tic and neural network algorithms in the training set.The prediction efficiency of the two predic-tion models was compared and verified in the verification set.Results Within 1 month after stroke,76 cases(29.23％)experienced post-stroke depression(62 cases in training set and 14 in the validation set).Based on the data in the training set,the levels of CRP,FIB,IL-6,IL-lβ,TNF-αand IL-18,and neutrophil and lymphocyte ratio(NLR)were significant higher in the post-stroke depression group than the non-post-stroke depression group(P＜0.01).Multivariate logistic re-gression analysis showed that CRP(OR=1.494,95％CI:1.239-1.802),FIB(OR=1.924,95％CI:1.191-3.109),IL-6(OR=1.128,95％CI:1.001-1.272),TNF-α(OR=1.051,95％CI:1.010-1.093),IL-1β(OR=1.096,95％CI:1.006-1.194),IL-18(OR=1.019,95％CI:1.002-1.036),and NLR(OR=1.873,95％CI:1.027-3.418)were risk factors for post-stroke depression(P＜0.05,P＜0.01).ROC curve analysis indicated that the AUC value of the predictive model of the neural network algorithm was higher than that of the model of multivariate logistic regression(0.931 vs 0.855,Z=3.448,P＜0.05).Based on the validation set,the former model also had bet-ter accuracy than the latter one(92.31％vs 75.00％,P＜0.05).Conclusion Circulating inflam-matory factors CRP,FIB,IL-6,IL-1β,TNF-α and IL-18,and NLR are related to the risk of post-stroke depression.The prediction model based on above factors combined with neural network al-gorithm can more effectively predict the risk of post-stroke depression.

Objective To investigate the effects of laparoscopic radiofrequency ablation(LRFA)and percutaneous radiofrequency ablation(PRFA)on anti-tumor immunity,complication rate and recurrence rate in patients with primary liver cancer.Methods A total of 81 patients with primary liver cancer treated in Dazhou Central Hospital from January 2020 to August 2022 were selected and divided into observation group(LRFA,n=42)and control group(PRFA,n=39)according to the treatment plan.Compare the total ablation rate,postoperative complication rate,recurrence rate of the two groups,as well as tumor necrosis factor-α(TNF-α),carbohydrate antigen 199(CA199),interleukin-6(IL-6),Golgi protein 73(GP73),C-reactive protein(CRP),alpha-fetoprotein(AFP)and peripheral blood T lymphocyte subpopulation levels before and after surgery.Results There was no significant difference between the observation group(95.24％)and the control group(92.31％)(P＞0.05).At 1 d postoperatively,IL-6 was(124.63±45.41)pg/ml and(168.28±51.26)pg/ml,CRP was(19.14±5.03)ng/L and(28.26±7.47)ng/L,and TNF-α was(94.32±18.49)pg/ml and(108.41±20.11)pg/ml;at 3 d postoperatively,IL-6 was(92.37±24.11)pg/ml and(105.83±27.45)pg/ml in the observation group and the control group,respectively,CRP was(14.87±4.37)ng/L and(17.25±5.06)ng/L,and TNF-α was(75.41±12.10)pg/ml and(82.64±16.83)pg/ml,which were all higher than that of preoperative period(P＜0.05).At 7 d postoperatively,CD3+in the observation group and control group were(66.27±7.82)％and(65.14±7.63)％,AFP was(156.23±30.27)μg/mland(160.84±32.33)μg/ml,GP73 was(65.21±10.26)μg/L and(67.44±11.03)μg/L,CA199 was(44.89±11.41)U/L and(45.12±13.07)U/L,CD4 was(32.02±6.03)％and(31.53±6.11)％,and CD4+/CD8+was(1.31±0.39)and(1.29±0.37)respectively;at 14 d postoperatively,CD3+was(71.25±6.83)％and(70.89±6.76)％,AFP was(48.52±18.31)μg/ml and(50.11±19.12)μg/ml,GP73 was(48.25±8.46)μg/L and(49.12±10.12)μg/L,CA199 was(19.27±5.16)U/L and(20.07±5.39)U/L,and CD4 was(38.25±7.7)U/L and(20.07±5.39)U/L,respectively,in the observation and control groups.g/L,CA199 was(19.27±5.16)U/L and(20.07±5.39)U/L,CD4 was(38.25±7.45)％and(37.61±7.92)％,and CD4+/CD8+was(1.49±0.42)and(1.47±0.45),respectively,which were higher than that of preoperative period(P＜0.05),but the difference between the two groups was not statistically significant(P＞0.05).The postoperative complication rate of 42.86％and recurrence rate of 2.38％in the observation group were lower than 66.67％and 17.95％in the control group(P＜0.05).The 12-month postoperative survival rate of 97.62％in the observation group was not statistically significant compared with 94.87％in the control group(P＞0.05).Conclusion The efficacy of LRFA and PRFA in the treatment of primary hepatocellular carcinoma is comparable,which can effectively improve the body's anti-tumor immunity and reduce the release of serum tumor markers;however,LRFA has less stressful reaction,reduces the occurrence of postoperative complications,and has a lower recurrence rate,which is especially advantageous in the treatment of hepatocellular carcinoma at special sites.

Objective To evaluate the cost-effectiveness of enzalutamide in the treatment of metastatic prostate cancer from the perspective of healthcare in China.Methods Based on the published phase Ⅲ randomized controlled trial(ENZAMET),the disease process of metastatic prostate cancer was classified into three states:progression-free survival,progression survival and death,and the model period was defined as 28 days,and the study period was lifelong,and a Markov model was established to evaluate the cost-effectiveness of the treatment of enzalutamide versus standard antiandrogen drugs in metastatic prostate cancer.Setting the willingness-to-pay(WTP)threshold at 3 times our 2022 gross domestic product(GDP)per capita and the robustness of the model analysis was verified by sensitivity analysis.Results Compared to the control group standard antiandrogen therapy,the incremental effect of enzalutamide was 0.92 quality-adjusted life years(QALYs),the incremental cost was 311 863.30 yuan,and the incremental cost-effectiveness ratio(ICER)was 338 981.85 yuan/QALY,which was higher than WTP threshold(257 094 yuan/QALY).The results of univariate sensitivity analyses showed that the total cost of the enzalutamide group,the PFS utility value,the cost of the PD status of enzalutamide group,and the unit price of enzalutamide had a greater impact on the model results.The results of the probabilistic sensitivity analysis suggested that the enzalutamide treatment regimen was not economical within the willingness-to-pay threshold of 3 times our 2022 GDP per capita.Conclusion Compared with the standard anti-androgen drugs,enzalutamide does not offer a cost-effectiveness advantage in the treatment of metastatic prostate cancer.

Objective To explore the clinical values of voxel-based morphometry(VBM)analysis in magnetic resonance imaging(MRI)for detecting secondary damage to the distant thalamus and substantia nigra in patients with cerebral infarction.Methods A total of nineteen patients with first-time unilateral middle cerebral artery(MCA)ischemic stroke were prospectively recruited.Three-dimensional whole-brain MRI scans were performed at 1 week,1 month,and 3 months after onset.VBM analysis was used to analyze changes in the thalamus and substantia nigra volumes.Results VBM analysis revealed that compared to ipsilateral thalamic volume at 1 week after onset,ipsilateral thalamic volume was significantly reduced at 1 month or 3 months after onset(reduced by 637 mm3 and 1488 mm3,respectively;P<0.01),with the atrophy primarily located in the dorsomedial nucleus of the thalamus.Similarly,compared to ipsilateral substantia nigra volume at 1 week after onset,the ipsilateral substantia nigra volume was significantly reduced at 1 month or 3 months after onset(reduced by 64 mm3 and 76 mm3,respectively;P<0.05).Conclusions VBM technology can be used to evaluate the ipsilateral thalamic and substantia nigra volume reduction in patients with cerebral infarction in the MCA supply area at 1-3 months after stroke,and to detect secondary damage.

Objective:To observe the clinical effect of initiating continuous blood purification (CBP) treatment at different times for patients with severe acute pancreatitis (SAP), and to explore the optimal timing for starting CBP treatment for SAP, so as to provide evidence for clinicians to start CBP treatment.Methods:A retrospective cohort study was used to select patients with SAP who received CBP treatment in People's Hospital of Hunan Province from January 2020 to December 2023. According to the timing of CBP initiation, the patients were divided into early initiation group (diagnosis of SAP to the first CBP treatment time < 24 hours) and late initiation group (diagnosis of SAP to the first CBP treatment time of 24-48 hours). The general data, acute physiology and chronic health evaluationⅡ(APACHEⅡ), bedside index for severity in acute pancreatitis (BISAP) score and laboratory indicators, local complications and systemic complications, intensive care unit (ICU) treatment time, hospital stay, treatment cost, and clinical outcome of the two groups were collected and compared.Results:A total of 130 patients with SAP who received CBP treatment were enrolled, including 90 patients in the early initiation group and 40 patients in the late initiation group. Before treatment, there were no significant differences in gender, age, APACHEⅡscore, BISAP score, etiology and laboratory examination indexes between the early initiation group and late initiation group. At 48, 72, 96 hours after treatment, the blood calcium level of the two groups was significantly higher than that before treatment, and the levels of white blood cell count (WBC), C-reactive protein (CRP), lactic acid, interleukin-6 (IL-6), tumor necrosis factor-α (TNF-α), APACHEⅡscore and BISAP score were significantly lower than those before treatment. The WBC level, APACHEⅡscore and BISAP score of the late initiation group were significantly lower than those of the early initiation group at 72 hours and 96 hours after treatment [WBC (×10 9/L): 10.96 (8.68, 13.04) vs. 12.45 (8.93, 16.30) at 72 hours after treatment, and 10.18 (8.68, 12.42) vs. 11.96 (8.81, 16.87) at 96 hours after treatment; APACHEⅡscore: 9.50 (5.75, 12.00) vs. 11.00 (6.25, 14.00) at 72 hours after treatment, and 10.00 (4.00, 12.00) vs. 12.00 (7.00, 14.75) at 96 hours after treatment; BISAP score: 2.35±1.03 vs. 2.76±1.10 at 72 hours after treatment, and 2.08±1.21 vs. 2.70±1.11 at 96 hours after treatment], the differences were statistically significant (all P < 0.05). In terms of complications, the incidence of pancreatic abscess in the late initiation group was significantly lower than that in the early initiation group [5.00% (2/40) vs. 20.00% (18/90)], but the incidence of abdominal compartment syndrome was significantly higher than that in the early initiation group [42.50% (17/40) vs. 13.33% (12/90)], the differences were statistically significant (all P < 0.05). In addition, the ICU treatment time in the early initiation group was significantly shorter than that in the late initiation group [days: 11.00 (6.00, 20.00) vs. 15.00 (9.75, 25.00), P < 0.05], and there were no statistically significant differences in hospitalization costs, length of stay and mortality between the two groups. Conclusions:CBP can effectively increase the level of blood calcium and decrease the level of lactic acid and inflammatory factors. Starting CBP within 24-48 hours after diagnosis of SAP can reduce WBC level and disease severity score faster, and reduce the occurrence of pancreatic abscess. Initiation of CBP within 24 hours after diagnosis of SAP can reduce the incidence of abdominal compartment syndrome and shorten the duration of ICU treatment.

OBJECTIVE To provide reference for safe use of risperidone in clinic. METHODS Data mining and analysis of risperidone-related adverse drug event （ADE） reports from the first quarter of 2017 to the third quarter of 2021 in the United States FAERS database were carried out using reported odds ratio and composite criteria methods from Medicines and Healthcare Products Regulatory Agency. RESULTS There were 101 181 ADE reports with risperidone as the primary suspect drug，involving a total of 33 179 patients. Among those reports，the male-to-female ratio was about 6.21 to 1； most of them were ＜18 years old （15.01%）； ADE was mainly reported by consumers （69.74%） and mainly reported by the United States （79.72%）； oral dosage form was the most used，accounting for 83.71%. A total of 409 ADE signals were obtained，including male breast development， pseudogynecomastia，abnormal increase in body mass，hyperprolactinemia and Wellens syndrome，etc. Twenty-six systems and organs were involved，mainly including reproductive system and breast diseases，various injuries，poisoning and operational complications， mental diseases，metabolic and nutritional diseases，and various nervous system diseases，etc. CONCLUSIONS The common ADE signals of risperidone and the system involved are consistent with the instructions，but we should also be alert to the ADE not recorded in the instruction，such as Wellens syndrome，fibroproliferative endocarditis，cavernous degeneration of portal vein，rabbit syndrome，etc.