AIM:To analyze the clinical value of predicting drug resistance in pulmonary tuberculo-sis patients based on improved machine learning models,and to build a visualization system for veri-fication.METHODS:Retrospectively selected 1 025 pulmonary tuberculosis patients hospitalized in Zhuhai Sixth People's Hospital from March 2019 to March 2024 with drug sensitivity test results as the research object.According to the definition of drug-resistant tuberculosis,the patients were divided in-to 631 sensitive groups(drug sensitivity test results showed no drug resistance),271 RR/MDR groups(meeting the definition of rifampicin resistant tu-berculosis or multi drug resistant tuberculosis,but no drug resistance to any kind of fluoroquino-lones),and 123 pre XDR groups(on the basis of multi drug resistant tuberculosis,and at the same time,drug resistance to any kind of fluoroquino-lones).Analyze clinical data based on the improved machine learning model,help build a drug resistant tuberculosis prediction model,synchronously com-plete feature screening,conduct value analysis on the screened features,and build a visual system for verification.RESULTS:Three groups of patients with baseline data comparison shows:Age,Body mass index(BMI),basic treatment of classification,lung diseases,haemoptysis,second-line drug use history,damage to lung,with empty in all statisti-cally significant difference between the three groups(P<0.05);Based on the modified ma-chine learning model,8 variables were screened,which were history of second-line drug use,BMI,treatment classification,destructive lung,underly-ing lung diseases,cavitation,hemoptysis,and age.The modified machine learning model had the high-est prediction accuracy compared with the tradi-tional model,with AUC values of 0.9322(RR/MDR prediction was positive class)and 0.9545(pre-XDR prediction was positive class).CONCLUSION:The application of the improved machine learning mod-el can help predict the occurrence of drug-resistant tuberculosis and assist the clinical formulation of more effective treatment plans.

Objective:To explore effect of Yishen Paidu Formula on inflammatory response in chronic renal failure(CRF)rats and role of Calcineurin/nuclear factor of activated T cell(NFAT).Methods:CRF rat model was constructed,and randomly grouped into model group,low,medium and high doses Yishen Paidu Formula groups,with 10 rats in each group,another 10 rats were fed normally as a blank group;general situation of rats was recorded;urine protein quantification kit was applied to detect 24-hour urine protein level of CRF rats in each group;serum creatinine and urea nitrogen levels of CRF rats were detected;ELISA was applied to detect serum IL-1β,IL-6 and TNF-α levels in CRF rats;pathological changes of renal tissue were observed by HE staining;Western blot was applied to detect expressions of fibroblast growth factor 23(FGF23),Klotho protein,Calcineurin,NFAT protein in renal tissue of CRF rats in each group.Results:Compared with blank group,levels of creatinine,urea nitrogen in serum,24 h urine protein in urine,IL-1β,IL-6,TNF-α in serum,and protein levels of FGF23,Calcineurin,NFAT in kidney tissue were obviously increased in model group,level of Klotho protein was obviously decreased(P<0.05).Compared with model group,levels of creatinine,urea nitrogen in serum,24 h urine protein in urine,IL-1β,IL-6,TNF-α in serum,and protein levels of FGF23,Calcineurin,NFAT in kidney tissue were obviously decreased in low,medium and high doses Yishen Paidu Formula groups,level of Klotho protein was obviously increased,which were more significant with dosage increase(P<0.05).Conclusion:Yishen Paidu Formula may alleviate inflammatory response in CRF rats by inhibiting Calcineurin/NFAT signaling pathway.

Objective:To explore effect of Yishen Paidu Formula on inflammatory response in chronic renal failure(CRF)rats and role of Calcineurin/nuclear factor of activated T cell(NFAT).Methods:CRF rat model was constructed,and randomly grouped into model group,low,medium and high doses Yishen Paidu Formula groups,with 10 rats in each group,another 10 rats were fed normally as a blank group;general situation of rats was recorded;urine protein quantification kit was applied to detect 24-hour urine protein level of CRF rats in each group;serum creatinine and urea nitrogen levels of CRF rats were detected;ELISA was applied to detect serum IL-1β,IL-6 and TNF-α levels in CRF rats;pathological changes of renal tissue were observed by HE staining;Western blot was applied to detect expressions of fibroblast growth factor 23(FGF23),Klotho protein,Calcineurin,NFAT protein in renal tissue of CRF rats in each group.Results:Compared with blank group,levels of creatinine,urea nitrogen in serum,24 h urine protein in urine,IL-1β,IL-6,TNF-α in serum,and protein levels of FGF23,Calcineurin,NFAT in kidney tissue were obviously increased in model group,level of Klotho protein was obviously decreased(P<0.05).Compared with model group,levels of creatinine,urea nitrogen in serum,24 h urine protein in urine,IL-1β,IL-6,TNF-α in serum,and protein levels of FGF23,Calcineurin,NFAT in kidney tissue were obviously decreased in low,medium and high doses Yishen Paidu Formula groups,level of Klotho protein was obviously increased,which were more significant with dosage increase(P<0.05).Conclusion:Yishen Paidu Formula may alleviate inflammatory response in CRF rats by inhibiting Calcineurin/NFAT signaling pathway.

AIM:To analyze the clinical value of predicting drug resistance in pulmonary tuberculo-sis patients based on improved machine learning models,and to build a visualization system for veri-fication.METHODS:Retrospectively selected 1 025 pulmonary tuberculosis patients hospitalized in Zhuhai Sixth People's Hospital from March 2019 to March 2024 with drug sensitivity test results as the research object.According to the definition of drug-resistant tuberculosis,the patients were divided in-to 631 sensitive groups(drug sensitivity test results showed no drug resistance),271 RR/MDR groups(meeting the definition of rifampicin resistant tu-berculosis or multi drug resistant tuberculosis,but no drug resistance to any kind of fluoroquino-lones),and 123 pre XDR groups(on the basis of multi drug resistant tuberculosis,and at the same time,drug resistance to any kind of fluoroquino-lones).Analyze clinical data based on the improved machine learning model,help build a drug resistant tuberculosis prediction model,synchronously com-plete feature screening,conduct value analysis on the screened features,and build a visual system for verification.RESULTS:Three groups of patients with baseline data comparison shows:Age,Body mass index(BMI),basic treatment of classification,lung diseases,haemoptysis,second-line drug use history,damage to lung,with empty in all statisti-cally significant difference between the three groups(P<0.05);Based on the modified ma-chine learning model,8 variables were screened,which were history of second-line drug use,BMI,treatment classification,destructive lung,underly-ing lung diseases,cavitation,hemoptysis,and age.The modified machine learning model had the high-est prediction accuracy compared with the tradi-tional model,with AUC values of 0.9322(RR/MDR prediction was positive class)and 0.9545(pre-XDR prediction was positive class).CONCLUSION:The application of the improved machine learning mod-el can help predict the occurrence of drug-resistant tuberculosis and assist the clinical formulation of more effective treatment plans.

Objective:To investigate the effect of early gradual diet on reducing delirium in elderly patients with hip arthroplasty.Methods:From January 2018 to January 2020, 74 cases of hip arthroplasty patients aged over 65 years old who were treated in the Third Affiliated Hospital of Sun Yat-sen University were selected as the observation objects. They were randomly divided into experimental group and control group with 37 cases in each group. The experimental group was given early gradual diet on the basis of routine postoperative care, while the control group was given routine postoperative diet on the basis of routine postoperative care. The incidence of postoperative delirium, Pittsburgh Sleep Quality Index (PSQI), patient satisfaction rate, average hospitalization days and average hospitalization expenses were used to evaluate the effect of early gradual diet on reducing delirium in elderly patients with hip arthroplasty.Results:The incidence of delirium in the experimental group was 2.70% (1/37) and 16.22% (6/37) in the control group, the difference was statistically significant ( χ2 value was 3.945, P<0.05); the hospitalization days of the experimental group were (10.68±5.13) d, (13.62±7.19) d in the control group. The difference of hospitalization days was statistically significant ( t value was 2.877, P<0.01). The incidence of difficulty in falling asleep and the satisfaction rate of the experimental group were 8.11% (3/37) and 94.59% (35/37) respectively, and those in the control group were 29.73% (11/37) and 78.38% (29/37) respectively, and the differences were statistically significant ( χ2 value was 5.638, 4.163, P<0.05). Conclusions:Early gradual diet after operation can reduce the incidence of delirium in elderly patients with hip arthroplasty, shorten the average hospitalization days, reduce the incidence of difficulty in falling asleep, improve patients' satisfaction, and help patients to pass through the perioperative period more safely and comfortably.

Objective:Network meta-analyses (NMA) were used to evaluate and compare the effectiveness and acceptability of 20 maintenance treatment strategies for bipolar disorder (BD), such as lithium, imipramine, lithium+imipramine, carbamazepine, lithium+carbamazepine, valproic acid salt, lamotrigine, fluoxetine, olanzapine, aripiprazole, oxcarbazepine, quetiapine, lithium+valproic acid, risperidone long-acting injection, lamotrigine+valproic acid salt, aripiprazole+lamotrigine, paliperidone, ziprasidone, lurasidone, quetiapine sustained release.Methods:The Literatures were systematically searched from PubMed, EMBASE, PsycINFO, China national knowledge infrastructure (CNKI), Wanfang data (Wanfang), China biology medicine disc (CBMdisc) until 11/21/2019. Randomized controlled studies of the maintenance therapy with single or combination drugs for at least 12 weeks were selected. The primary outcome was the proportion of patients who got recurrence in the total number of patients. Efficacy of pharmacological treatments was assessed during the maintenance treatment treatments by using a random-effects network meta-analysis model within a Frequentists framework. Data analysis was performed in Stata 14.0 software.Results:40 studies covering with 10 431 patients were included, and 20 kinds of maintenance treatments for BD were performed. In terms of clinical efficacy, the top 5 treatments were lurasidone,quetiapine, olazanpine, lithium+carbamazepine, aripiprazole+lamotrigine.lithium ( RR:0.78, 95% CI: 0.62-0.97), olanzapine ( RR:0.51, 95% CI: 0.35-0.75), quetiapine ( RR:0.50, 95% CI: 0.33-0.74) and lurasidone ( RR:0.40, 95% CI: 0.19-0.83) were significantly superior to placebo. Conclusions:Lithium, olanzapine, quetiapine and lurasidone may be more effective than placebo,.but the efficaly of other monotherapy and combination therapy strategies need to be proven.

Objective:Network meta-analyses (NMA) were used to evaluate and compare the effectiveness and acceptability of 20 maintenance treatment strategies for bipolar disorder (BD), such as lithium, imipramine, lithium+imipramine, carbamazepine, lithium+carbamazepine, valproic acid salt, lamotrigine, fluoxetine, olanzapine, aripiprazole, oxcarbazepine, quetiapine, lithium+valproic acid, risperidone long-acting injection, lamotrigine+valproic acid salt, aripiprazole+lamotrigine, paliperidone, ziprasidone, lurasidone, quetiapine sustained release.Methods:The Literatures were systematically searched from PubMed, EMBASE, PsycINFO, China national knowledge infrastructure (CNKI), Wanfang data (Wanfang), China biology medicine disc (CBMdisc) until 11/21/2019. Randomized controlled studies of the maintenance therapy with single or combination drugs for at least 12 weeks were selected. The primary outcome was the proportion of patients who got recurrence in the total number of patients. Efficacy of pharmacological treatments was assessed during the maintenance treatment treatments by using a random-effects network meta-analysis model within a Frequentists framework. Data analysis was performed in Stata 14.0 software.Results:40 studies covering with 10 431 patients were included, and 20 kinds of maintenance treatments for BD were performed. In terms of clinical efficacy, the top 5 treatments were lurasidone,quetiapine, olazanpine, lithium+carbamazepine, aripiprazole+lamotrigine.lithium ( RR:0.78, 95% CI: 0.62-0.97), olanzapine ( RR:0.51, 95% CI: 0.35-0.75), quetiapine ( RR:0.50, 95% CI: 0.33-0.74) and lurasidone ( RR:0.40, 95% CI: 0.19-0.83) were significantly superior to placebo. Conclusions:Lithium, olanzapine, quetiapine and lurasidone may be more effective than placebo,.but the efficaly of other monotherapy and combination therapy strategies need to be proven.

Objective To explore the the characteristics of non-motor symptoms of essential tremor(ET).Methods Totally 50 ET patients and 45 age-gender-matched healthy volunteers,admitted in Department of Neurology,The Second Affiliated Hospital of Zhejiang University School of Medicine from May 2015 to April 2016,were included.Clinical data and tremor analyses under different postures were obtained.The non-motor symptoms were evaluated using the Pittsburgh Sleep Quality Index(PSQI),Hamilton anxiety scale(HAMA),Hamilton's Depression Scale(HAMD),and the MOS item short from health survey (SF-36).Cognitive functions were evaluated by the Minimental state examination(MMSE).Results ET group had lower MMSE total score of (25.81 ±2.75 vs.28.16 ± 1.71),increased rate of dyssomnia (62.0％ vs.15.6％) and higher PQSI score (6.42±2.71 vs.3.84±2.13)compared with the control group(all P＜0.05).Moreover,more patients in the ET group had moderate and severe anxiety(60.0 ％ vs.37.8 ％),moderate and severe depression (34.0％ vs.15.6％)than the control group(both P ＜ 0.05).Anxiety and depression had effects on physical and mental health and were also related to the quality of life.Conclusions Non-motor symptoms,such as mild cognitive deficits,depression,anxiety and dyssomnia are common in ET patients.Furthermore,depression and anxiety have negative effects on physical and mental health.

Objective: To explore the expression of FAT1 in esophageal squamous cell carcinoma (ESCC) tissues, and its effect on cell proliferation. Methods: The expression levels of FAT1 protein in human ESCC tissues and matched adjacent normal tissues were determined by immunohistochemistry (IHC). Lentivirus based knockdown of FAT1 was carried out in YSE2 and Colo680N cell lines and 3-(4, 5-dimethyl-2-thiazolyl)-2, 5-diphenyl-2H tetrazolium bromide (MTT) assays was performed to examine the effect of FAT1 on the proliferation of these ESCC cells. Colony formation assay was used to detect the colony formation ability. Flow cytometry was performed to analyze the cell cycle and apoptosis. The expression levels of cell cycle markers in FAT1 knock out ESCC cell lines were detected by real-time quantitative reverse transcription polymerase chain reaction(qRT-PCR) and Western blot. Results: The relative expression of FAT1 in ESCC tissues was 66.97±21.53, significantly lower than 78.13±16.76 of adjacent normal tissues(P<0.05). Knockdown of FAT1 promoted cell proliferation and colony formation. In YSE2 cell, the division time in negative control (NC) group was (1 570±51) min, significantly longer than (1 356±31) min in shFAT1 group. In Colo680N cell, division time in NC group was (1 532±53) min, significantly longer than (1 290±30) min in shFAT1 group (P<0.05). Knockdown of FAT1 promoted G1-to S-phase transition and resulted in the upregulation of CDK4/CDK6/CCND1. Conclusion FAT1 inhibits the proliferation and G1-to S-phase transition of ESCC cells through regulating the protein expression of CDK4/CDK6/CCND1 complex.

Objective To explore the expression of FAT1 in esophageal squamous cell carcinoma ( ESCC) tissues, and its effect on cell proliferation. Methods The expression levels of FAT1 protein in human ESCC tissues and matched adjacent normal tissues were determined by immunohistochemistry ( IHC) . Lentivirus based knockdown of FAT1 was carried out in YSE2 and Colo680N cell lines and 3?( 4,5?dimethyl?2?thiazolyl)?2,5?diphenyl?2H tetrazolium bromide ( MTT) assays was performed to examine the effect of FAT1 on the proliferation of these ESCC cells. Colony formation assay was used to detect the colony formation ability. Flow cytometry was performed to analyze the cell cycle and apoptosis. The expression levels of cell cycle markers in FAT1 knock out ESCC cell lines were detected by real?time quantitative reverse transcription polymerase chain reaction( qRT?PCR) and Western blot. Results The relative expression of FAT1 in ESCC tissues was 66. 97 ± 21. 53, significantly lower than 78. 13 ± 16. 76 of adjacent normal tissues ( P<0.05) . Knockdown of FAT1 promoted cell proliferation and colony formation. In YSE2 cell, the division time in negative control (NC) group was (1570±51) min, significantly longer than (1356±31) min in shFAT1 group. In Colo680N cell, division time in NC group was (1532±53) min, significantly longer than (1290±30) min in shFAT1 group (P<0.05). Knockdown of FAT1 promoted G1?to S?phase transition and resulted in the upregulation of CDK4/CDK6/CCND1. Conclusion FAT1 inhibits the proliferation and G1?to S?phase transition of ESCC cells through regulating the protein expression of CDK4/CDK6/CCND1 complex.