Objective To construct a quality control model for cervical liquid-based thin cell smears using two different artificial intelligence(AI)techniques and to compare the total use of the two methods to improve the level of quality control of cervical liquid-based thin cell smears through the assistance of hybrid AI.Methods In this study,105 cervical liquid-based thin cell smear samples were used.Convolutional neural network(CNN)algorithm and Transformer network algorithm were used as specific AI algorithms in the AI model.The labeled features included the number of cells in the slice,excessive red blood cells,excessive inflammatory cells,and air bubbles.The smear samples were pre-processed and digitized by smear,followed by image segmentation and feature extraction.Using the labeled feature data,machine learning models were trained and optimized.Statistical AI and physician QC results were analyzed by calculating KAPPA index,sensitivity,specificity,area under the curve(AUC),and other indexes for AI QC results.Results CNN algorithm QC results in normal smear,inflammatory background and bloody background were significantly different from the expert review QC results(P＜0.001).Transformer algorithm QC results were similar to the expert review results,with no statistical difference(P＞0.05).General practitioner QC results were statistically different from the expert review QC results in normal smear detection rate and bloody background(P＜0.001).CNN algorithm Kappa value was 0.567,which had medium consistency with expert review results.Transformer algorithm Kappa value was 0.890,with the best consistency with expert review results.General practitioner Kappa value was 0.675,which had better consistency with expert review results.Using the expert review results as a reference standard,the predictive efficacy of the Transformer algorithm and the general practitioners' QC results was evaluated,and the predictive efficacy of the Transformer algorithm was higher than that of the general practitioners in detecting hemorrhagic backgrounds and normal smears(inflammatory backgrounds:AUC=1.000;normal smears:AUC=0.768)(hemorrhagic backgrounds:AUC=0.849;normal smears:AUC=0.849;normal smear:AUC=0.500).Conclusion In this study,we found that the Transformer algorithm was effective in improving the quality control of cervical liquid-based thin-layer cell smears by assisting doctors to perform smear quality control scoring and improving the efficiency and accuracy of smear sample quality control.It can be used as a new quality control method for cervical cancer cytological screening and has potential clinical applications.

Objective To investigate the effect of α/β hydrolase folded protein 5(ABHD5)and cellular immunity markers on the response to tirellizumab targeted therapy in patients with advanced non-small cell lung cancer(NSCLC).Methods A total of 123 patients with advanced NSCLC who received tiralizumab in Kailuan General Hospital from October 2020 to December 2023 were selected.The efficacy of the target lesions was evaluated 4 weeks after treatment,and the patients were divided into response group and non-response group according to the treatment effect.Quantitative real time polymerase chain reaction(RT-qPCR)was used to detect the relative expression of ABHD5 in lesion tissues.The expression level of ABHD5,immune indexes[CD4+T,CD8+T,CD4+T/CD8+T,regulatory T cell(Treg),T helper cell 17(Th17),Treg/Th17]and other clinical indexes were compared between the two groups.Multivariate logistic regression analysis of independent factors influencing response to tirelizumab targeted therapy.The predictive value of ABHD5,CD4+T and CD8+T in non-response to treatment of advanced NSCLC was analyzed by receiver operating characteristic(ROC).ABHD5 expression was correlated with CD4+T and CD8+T cells by Pearson correlation analysis.Results Among the 123 patients enrolled,90 responded to treatment and 33 did not respond.The expression of ABHD5(1.16±0.18)and the levels of CD4+T(31.52%±4.26%)and CD8+T(24.39%±1.87%)cells in the non-response group were lower than those in the response group(1.47±0.21,36.43%±4.08%,29.13%±2.15%),and the levels of Treg(7.24%±0.89%)and Th17(6.23%±1.10%)cells were higher than those in the response group(6.37%±0.91%,5.42%±0.66%),and the differences were statistically significant(t=4.725～11.200,all P<0.05).There were significant differences in tumor size,number of metastases and levels of carcinoembryonic antigen(CEA),albumin(ALB)and total bilirubin(TBIL)between the two groups,and the differences were statistically significant(t=2.969～6.523,all P<0.05).ABHD5 expression and CD4+T,CD8+T cell levels were independent protective factors affecting the response to tirelizumab targeted therapy in advanced NSCLC(Wald χ2=15.803,7.954,8.631,all P<0.05).ABHD5 predicted that the AUC of non-response to treatment of advanced NSCLC was 0.897,which was higher than that of 0.860 and 0.835 predicted by CD4+T and CD8+T cells,and the prediction sensitivity and specificity were 72.73%and 94.45%,respectively.ABHD5 expression was positively correlated with the levels of CD4+T and CD8+T cells(r=0.367,0.355,all P<0.05).Conclusion The response to tirelizumab targeted therapy in advanced NSCLC is significantly correlated with the expression of ABHD5 and the levels of CD4+T and CD8+T cells,and ABHD5 has high predictive value in the treatment of advanced NSCLC.

Objective:To investigate the expression of chondroitin sulfate proteoglycan 4 pseudogene 12(CSPG4P12)in the small cell lung cancer(SCLC)tissue,its relationship with immune infiltration,and its effect on cell biological functions,and to clarify its effect in the occurrence and development of SCLC.Methods:The E-GEOD-60052 cohort was obtained by searching the ArrayExpress database for SCLC.The R language Bioconductor package was used to complete data filtering standardization,and 63 samples of SCLC tumor tissues and 7 samples of normal tissues were obtained.The Mann-Whitney U test was used to analyze the difference in CSPG4P12 expression levels between two groups.Pearson correlation analysis was used to evaluate the associations between CSPG4P12 expression levels and 47 immune checkpoint genes.The ESTIMATE algorithm and CIBERSORT algorithm were used to evaluate the correlations between CSPG4P12 expression and tumor immune cell infiltration.A case-control study was used to analyze the clinical data.A total of 230 patients with SCLC were selected as case group,and 230 healthy subjects were selected as control group.The genotyping of CSPG4P12 rs2880765,rs6496932 and rs8040855 was performed using TaqMan-MGB fluorescent probe labeling method.Odds ratio(OR)and 95％confidence interval(CI)were calculated by unconditional Logistic regression model to analyze the association between polymorphic genetic variation of CSPG4P12 gene and the risk of SCLC.The SCLC DMS114 cells were transfected with pUC-57 plasmid(control group)and CSPG4P12 over-expression plasmid(OV-CSPG4P12 group),respectively.The efficiencies of CSPG4P12 over-expression in two groups were verified by real-time fluorescence quantitative PCR(RT-qPCR)method.Cell counting kit-8(CCK-8)method was used to detect the cell proliferation activities of cells in two groups.Transwell chamber assay was used to detect the numbers of migration and invasion cells in two groups,respectively.Hoechst 33342 fluorescence staining was used to observe the cell apoptosis in two groups.Results:The ArrayExpress database E-GEOD-60052 cohort analysis showed that the expression level of CSPG4P12 mRNA in SCLC tissue was decreased compared with normal tissue(P＜0.001).The expression of CSPG4P12 had positive correlations with the immune checkpoint genes including leukocyte associated immunoglobulin like receptor 1(LAIR1)(r=0.47,P＜0.001),tumor necrosis factor(TNF)receptor superfamily member 9(TNFRSF9)(r=0.38,P＜0.01),and TNF superfamily member 9(TNFSF9)(r=0.44,P＜0.001).The ESTIMATE algorithm results showed that the matrix score,immune score and ESTIMATE composite score of the patients in CSPG4P12 low expression group were lower than those in CSPG4P12 high expression group(P＜0.01).The CIBERSORT algorithm results showed that compared with CSPG4P12 high expression group,the infiltration of M0 macrophages in CSPG4P12 low expression group was increased(P＜0.05)and the infiltration of mast cells resting was decreased(P＜0.05).The CSPG4P12 expression level had positive correlations with infiltration of mast cells resting(r=0.35,P=0.03)and mononuclear cell infiltration(r=0.34,P=0.034).In case-control studies,compared with AA genotype,CSPG4P12 rs2880765 AT and TT genotype carriers had a higher risk of SCLC(OR=1.68,95％CI=1.15-2.45,P＜0.01).The stratified analysis showed that genetic variation of rs2880765 A＞T increased the risk of SCLC in the male,younger age group(≤60 years)and smoking subgroups(males:OR=1.86,95％CI=1.18-2.93,P＜0.01;≤60 years:OR=1.73,95％CI=1.11-2.68,P＜0.01;smoking:OR=2.76,95％CI=1.49-5.13,P=0.001).The cell biology experiment showed that compared with control group,the proliferation abilities of the cells in OV-CSPG4P12 group were significantly decreased at 48 and 72 h(P＜0.01),while the number of migration cells at 24 h was significantly decreased(P＜0.01),the number of apoptotic cells at 24 h was increased(P＜0.05)and the number of invasion cells at 48 h was significantly decreased(P＜0.01).Conclusion:CSPG4P12 is lowly expressed in SCLC tumor tissue,which is associated with immune infiltration.The genetic variation of CSPG4P12 rs2880765 A＞T can increase the risk of SCLC,and its over-expression can inhibit cell proliferation,migration and invasion,and promote apoptosis.

Objective:To discuss the causal association between sterol esters and intrahepatic duct,biliary tract,and gallbladder malignancies using two-sample Mendelian randomization(MR)analysis,and to clarify the biological mechanisms of sterol esters,and to provide the a basis for early prevention and treatment of these malignancies.Methods:The instrumental variable data for 15 different types of sterol ester traits were obtained from the Finnish database(FinnGen).The genome-wide association study(GWAS)data for intrahepatic duct,biliary tract,and gallbladder malignancies were retrieved from the GWAS database using the keywords"sterol ester"and"intrahepatic duct,biliary tract,and gallbladder malignancies"(accession numbers:ICD-O-3 and GCST90277238-GCST9027725).The inverse-variance weighted(IVW)method,MR-Egger regression,and weighted median(WM)method were used to assess the causal association between sterol esters and the risk of these malignancies.Pleiotropy was tested using the MR-Egger intercept method;heterogeneity was evaluated using Cochran's Q test;and sensitivity analysis was performed using the leave-one-out approach to comprehensively assess the reliability and robustness of the results.Results:The IVW analysis results showed that Sterol ester(27:1/14:0)odds ratio(OR)=2.349,95%confidence interval(CI)=1.371-4.025,P=0.002),Sterol ester(27:1/16:0)(OR=1.248,95%CI=1.018-1.523,P=0.033),Sterol ester(27:1/18:2)(OR=1.361,95%CI=1.078-1.718,P=0.009),and Sterol ester(27:1/22:6)(OR=1.339,95%CI=1.001-1.791,P=0.049)were associated with an increased risk of intrahepatic duct,biliary tract,and gallbladder malignancies.The MR-Egger regression analysis results indicated that Sterol ester(27:1/18:2)(OR=2.038,95%CI=1.337-3.105,P=0.011)was a risk factor for these malignancies.The WM analysis results revealed that Sterol ester(27:1/14:0)(OR=2.786,95%CI=1.419-5.468,P=0.003)and Sterol ester(27:1/18:2)(OR=1.548,95%CI=1.148-2.088,P=0.004)were also risk factors.The MR-Egger intercept analysis and Cochran's Q test results indicated no significant horizontal pleiotropy or heterogeneity.The leave-one-out sensitivity analysis did not identify any influential outlier single nucleotide polymorphism(SNPs),confirming the reliability of the study.Conclusion:Sterol ester(27:1/14:0),Sterol ester(27:1/16:0),Sterol ester(27:1/18:2),and Sterol ester(27:1/22:6)exhibit causal associations with intrahepatic duct,biliary tract,and gallbladder malignancies and may promote their development.

Objective To construct a quality control model for cervical liquid-based thin cell smears using two different artificial intelligence(AI)techniques and to compare the total use of the two methods to improve the level of quality control of cervical liquid-based thin cell smears through the assistance of hybrid AI.Methods In this study,105 cervical liquid-based thin cell smear samples were used.Convolutional neural network(CNN)algorithm and Transformer network algorithm were used as specific AI algorithms in the AI model.The labeled features included the number of cells in the slice,excessive red blood cells,excessive inflammatory cells,and air bubbles.The smear samples were pre-processed and digitized by smear,followed by image segmentation and feature extraction.Using the labeled feature data,machine learning models were trained and optimized.Statistical AI and physician QC results were analyzed by calculating KAPPA index,sensitivity,specificity,area under the curve(AUC),and other indexes for AI QC results.Results CNN algorithm QC results in normal smear,inflammatory background and bloody background were significantly different from the expert review QC results(P＜0.001).Transformer algorithm QC results were similar to the expert review results,with no statistical difference(P＞0.05).General practitioner QC results were statistically different from the expert review QC results in normal smear detection rate and bloody background(P＜0.001).CNN algorithm Kappa value was 0.567,which had medium consistency with expert review results.Transformer algorithm Kappa value was 0.890,with the best consistency with expert review results.General practitioner Kappa value was 0.675,which had better consistency with expert review results.Using the expert review results as a reference standard,the predictive efficacy of the Transformer algorithm and the general practitioners' QC results was evaluated,and the predictive efficacy of the Transformer algorithm was higher than that of the general practitioners in detecting hemorrhagic backgrounds and normal smears(inflammatory backgrounds:AUC=1.000;normal smears:AUC=0.768)(hemorrhagic backgrounds:AUC=0.849;normal smears:AUC=0.849;normal smear:AUC=0.500).Conclusion In this study,we found that the Transformer algorithm was effective in improving the quality control of cervical liquid-based thin-layer cell smears by assisting doctors to perform smear quality control scoring and improving the efficiency and accuracy of smear sample quality control.It can be used as a new quality control method for cervical cancer cytological screening and has potential clinical applications.

Objective To investigate the effect of α/β hydrolase folded protein 5(ABHD5)and cellular immunity markers on the response to tirellizumab targeted therapy in patients with advanced non-small cell lung cancer(NSCLC).Methods A total of 123 patients with advanced NSCLC who received tiralizumab in Kailuan General Hospital from October 2020 to December 2023 were selected.The efficacy of the target lesions was evaluated 4 weeks after treatment,and the patients were divided into response group and non-response group according to the treatment effect.Quantitative real time polymerase chain reaction(RT-qPCR)was used to detect the relative expression of ABHD5 in lesion tissues.The expression level of ABHD5,immune indexes[CD4+T,CD8+T,CD4+T/CD8+T,regulatory T cell(Treg),T helper cell 17(Th17),Treg/Th17]and other clinical indexes were compared between the two groups.Multivariate logistic regression analysis of independent factors influencing response to tirelizumab targeted therapy.The predictive value of ABHD5,CD4+T and CD8+T in non-response to treatment of advanced NSCLC was analyzed by receiver operating characteristic(ROC).ABHD5 expression was correlated with CD4+T and CD8+T cells by Pearson correlation analysis.Results Among the 123 patients enrolled,90 responded to treatment and 33 did not respond.The expression of ABHD5(1.16±0.18)and the levels of CD4+T(31.52%±4.26%)and CD8+T(24.39%±1.87%)cells in the non-response group were lower than those in the response group(1.47±0.21,36.43%±4.08%,29.13%±2.15%),and the levels of Treg(7.24%±0.89%)and Th17(6.23%±1.10%)cells were higher than those in the response group(6.37%±0.91%,5.42%±0.66%),and the differences were statistically significant(t=4.725～11.200,all P<0.05).There were significant differences in tumor size,number of metastases and levels of carcinoembryonic antigen(CEA),albumin(ALB)and total bilirubin(TBIL)between the two groups,and the differences were statistically significant(t=2.969～6.523,all P<0.05).ABHD5 expression and CD4+T,CD8+T cell levels were independent protective factors affecting the response to tirelizumab targeted therapy in advanced NSCLC(Wald χ2=15.803,7.954,8.631,all P<0.05).ABHD5 predicted that the AUC of non-response to treatment of advanced NSCLC was 0.897,which was higher than that of 0.860 and 0.835 predicted by CD4+T and CD8+T cells,and the prediction sensitivity and specificity were 72.73%and 94.45%,respectively.ABHD5 expression was positively correlated with the levels of CD4+T and CD8+T cells(r=0.367,0.355,all P<0.05).Conclusion The response to tirelizumab targeted therapy in advanced NSCLC is significantly correlated with the expression of ABHD5 and the levels of CD4+T and CD8+T cells,and ABHD5 has high predictive value in the treatment of advanced NSCLC.

Objective To explore and validate the application value of a deep learning model based on the Huawei Cloud ModelArts platform in the diagnosis of atypical cervical cells in liquid-based cytology(LBC)and to evaluate its assistive effect for pathologists with different diagnostic experiences.Methods We retrospectively analyzed 1 044 cervical cytology specimens from Dongguan People's Hospital in 2020.The artifical intelligence(AI)-assisted diagnostic system developed on the Huawei Cloud ModelArts platform was compared with junior,intermediate,and senior pathologists for diagnosis.Sensitivity,specificity,precision,recall,and area under the receiver operating characteristic curve(AUC)were calculated to assess the diagnostic performance of the Al system and its assistive effect for pathologists with different levels of experience.The McNemar test was used to compare the differences between the Al system and manual diagnosis.P＜0.05 was considered statistically significant.Results For the 1 044 cervical exfoliated cytology specimens,the sensitivity and specificity of the AI system in detecting atypical cells was 98.96％and 89.15％,both of which were higher than those of junior doctors(81.95％and 91.81％,respectively).The overall diagnostic accuracy of the Al system was 93.68％,which was significantly higher than that of junior doctors(87.26％,P＜0.001).Al assistance could significantly improve junior doctors'ability to detect atypical cells,with the sensitivity and specificity increasing from 80.1％to 96.5％and from 85.6％to 92.3％,respectively.Conclusion The AI-assisted cervical cytology diagnostic system developed in this study demonstrated superior performance,particularly in significantly improving the diagnostic level of junior pathologists,showing promising clinical application prospects.

Objective To investigate the value of peripheral blood soluble interleukin-2 receptor(sIL-2R),CD4+lymphocyte percentage/CD8+lymphocyte percentage ratio(hereinafter referred to as CD4+/CD8+)and tumor necrosis factor-α(TNF-α)in evaluating the efficacy of chemotherapy in elderly patients with newly treated active pulmonary tuberculosis.Methods A total of 102 elderly patients with newly treated active tu-berculosis admitted to the hospital from December 2019 to December 2022 were enrolled in the study as the observation group,and 102 healthy people aged 60 and older who underwent physical examination in the hos-pital during the same period were enrolled as the control group.The levels of sIL-2R,TNF-α and CD4+/CD8+in peripheral blood were compared between the two groups,and the correlations between sIL-2R,TNF-α and CD4+/CD8+were analyzed.The observation group was treated with 2HRZE/4HR anti-tuberculosis treatment regimen.The levels of sIL-2R,TNF-α and CD4+/CD8+in peripheral blood of patients with different efficacy before treatment,1 month and 6 months after treatment in the observation group were compared.The correla-tion between sIL-2R,CD4+/CD8+,TNF-α levels and therapeutic effect was analyzed.The receiver operating characteristic(ROC)curve was used to analyze the efficacy of indicators in evaluating the efficacy of chemo-therapy in elderly patients.Results The levels of sIL-2R and TNF-α in the observation group were higher than those in the control group,while CD4+/CD8+was lower than that in the control group,and the differ-ences were statistically significant(P＜0.05).In the observation group,sIL-2R and TNF-α were negatively correlated with CD4+/CD8+(P＜0.05),sIL-2R was positively correlated with TNF-α(P＜0.05).After 1 month and 6 months of treatment,the levels of sIL-2R and TNF-α in patients with apparent efficacy were low-er than those in patients with efficacy,and the latter were lower than those in patients with no effect,while the CD4+/CD8+in patients with apparent efficacy was higher than that in patients with efficacy,and the latter was higher than that in patients with no efficacy,and the differences were statistically significant(P＜0.05).The levels of sIL-2R and TNF-α were negatively correlated with the efficacy(P＜0.05),and CD4+/CD8+was positively correlated with the efficacy(P＜0.05).ROC curve analysis showed that the area under the curve(AUC)of sIL-2R,CD4+/CD8+,and TNF-α used in combination to assess efficacy was significantly greater than the AUCs of the single indicators used in the assessment at each time point of treatment(P＜0.05),and the AUC of the combination of the indicators was greater after 6 months of treatment than after 1 month of treatment(P＜0.05).Conclusion The levels of sIL-2R,CD4+/CD8+and TNF-α are closely related to the ef-ficacy of chemotherapy in elderly patients with newly treated active pulmonary tuberculosis,and the combina-tion of the above indicators has certain reference value in evaluating the efficacy of chemotherapy in patients.

Objective:This study aimed to evaluate the efficacy of decitabine (DAC) and identify factors influencing treatment responses in patients with primary immune thrombocytopenia (ITP) who had failed glucocorticoid therapy.Methods:Clinical data of 61 patients with glucocorticoid-resistant ITP who received DAC therapy (5 mg·m -2·d -1×3 d via intravenous infusion) for at least three cycles with 3-4-week intervals at the Department of Hematology, Qilu Hospital of Shandong University, from November 2015 to June 2021 were analyzed retrospectively. Results:The 61 patients comprised 20 males and 41 females, with a median age of 45 years (range: 15-81 years). Among them, 43 patients were glucocorticoid-dependent (glucocorticoid-dependent group), while 18 patients were glucocorticoid-resistant (glucocorticoid-resistant group). Following DAC treatment, 12 patients (19.67% ) achieved complete response (CR), and 16 patients (26.23% ) exhibited response (R), resulting in an overall response (OR) rate of 45.90% (28/61). Comparison between the OR group ( n=28) and the non-response (NR) group ( n=33) revealed significant differences in responses to glucocorticoids (dependent or resistant) and platelet counts before treatment ( χ2=8.789, P=0.003; z=-2.416, P=0.016). The glucocorticoid-dependent group showed higher platelet counts than the glucocorticoid-resistant group after the second and third cycles of DAC treatment ( P=0.032, 0.024). Moreover, the OR rates after the first, second, and third cycles of DAC treatment in the glucocorticoid-dependent group were all higher than those in the glucocorticoid-resistant group ( P=0.042, P=0.012, P=0.029). A significant correlation was observed between glucocorticoid dependence and responses to DAC treatment ( OR=9.213, 95% CI 1.937-43.820, P=0.005) . Conclusion:DAC demonstrates definitive efficacy with mild adverse effects in a subset of patients with glucocorticoid-resistant primary ITP. Glucocorticoid dependence and higher platelet counts before treatment are associated with a favorable response to DAC therapy.

OBJECTIVES: The long-term trends of cognitive function and its associations with physical performance remain unclear, particularly in Asian populations. The study objectives were to determine cognitive trajectories in middle-aged and elderly Chinese individuals, as well as to examine differences in physical performance across cognitive trajectory groups. METHODS: Data were extracted from the China Health and Retirement Longitudinal Study. A total of 5,701 participants (47.7% male) with a mean age of 57.8 (standard deviation, 8.4) years at enrollment were included. A group-based trajectory model was used to identify cognitive trajectory groups for each sex. Grip strength, repeated chair stand, and standing balance tests were used to evaluate physical performance. An ordered logistic regression model was employed to analyze differences in physical performance across cognitive trajectory groups. RESULTS: Three cognitive trajectory groups were identified for each sex: low, middle, and high. For both sexes, higher cognitive trajectory groups exhibited smaller declines with age. In the fully adjusted model, relative to the low trajectory group, the odds ratios (ORs) of better physical performance in the middle cognitive group were 1.37 (95% confidence interval [CI], 1.17 to 1.59; p<0.001) during follow-up and 1.40 (95% CI, 1.20 to 1.64; p<0.001) at the endpoint. The ORs in the high trajectory group were 1.94 (95% CI, 1.61 to 2.32; p<0.001) during follow-up and 2.04 (95% CI, 1.69 to 2.45; p<0.001) at the endpoint. CONCLUSIONS Cognitive function was better preserved in male participants and individuals with higher baseline cognitive function. A higher cognitive trajectory was associated with better physical performance over time.