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 molecular mechanism of hepatic fibrosis(HF)regulation by liver sinusoidal endothelial cells(LSECs)via endothelial mesenchymal transition(EnMT),and to predict the natural active components using bioinformatics,machine learning,and cellular experiments.Methods HF and EnMT gene matrices were obtained and the intersecting genes were extracted and enriched using Limma difference analysis and weighted gene co-expression network analysis(WGCNA).The diagnostic genes were screened using a combination of random forest method,support vector machine-recursive feature elimination and network topology analysis,and immune infiltration analysis and prediction of natural active ingredients were performed.The expression of diagnostic genes and the pharmacological effects of the predicted ingredients were finally verified by cellular experiments.Results Differential analysis yielded 3034 EnMT-associated and 4133 HF-associated differential genes.WGCNA analysis yielded 4589 EnMT-associated Hub genes and 763 HF-associated Hub genes.Thirty-eight intersecting genes were extracted,which were mainly enriched in the pathways of basement membrane and extracellular matrix receptor interaction.Four diagnostic genes,CFP,COL4A2,ITGA1,and GRPEL1,were screened by multidimensional analysis.Immune infiltration analysis showed that the diagnostic genes were closely associated with mast cell resting state,memory B cells,and memory CD4+T cells.Reverse transcription-polymerase chain reaction analysis showed significantly increased mRNA expression levels of the four diagnostic genes in the Jagged1-induced model group(P＜0.05).The predicted components,sterol,kaempferol,and quercetin,all had good binding activities with the diagnostic genes.Enzyme-linked immunosorbent assay result confirmed that all three active components significantly reduced the expression of collagen type Ⅳ α2 chain protein in Jagged1-induced LSECs,with quercetin having the most significant effect(P＜0.01).Conclusions This study elucidated the molecular mechanism of hepatic sinusoidal endothelial cells involved in the pathological process of HF through mesenchymal transition.We also propose a diagnostic marker system including CFP,COL4A2,ITGA1,and GRPEL1 as core genes.The result also suggest that natural active ingredients,such as quercetin,may exert anti-HF pharmacological effects by targeting these diagnostic genes.

Objective To investigate the molecular mechanism of hepatic fibrosis(HF)regulation by liver sinusoidal endothelial cells(LSECs)via endothelial mesenchymal transition(EnMT),and to predict the natural active components using bioinformatics,machine learning,and cellular experiments.Methods HF and EnMT gene matrices were obtained and the intersecting genes were extracted and enriched using Limma difference analysis and weighted gene co-expression network analysis(WGCNA).The diagnostic genes were screened using a combination of random forest method,support vector machine-recursive feature elimination and network topology analysis,and immune infiltration analysis and prediction of natural active ingredients were performed.The expression of diagnostic genes and the pharmacological effects of the predicted ingredients were finally verified by cellular experiments.Results Differential analysis yielded 3034 EnMT-associated and 4133 HF-associated differential genes.WGCNA analysis yielded 4589 EnMT-associated Hub genes and 763 HF-associated Hub genes.Thirty-eight intersecting genes were extracted,which were mainly enriched in the pathways of basement membrane and extracellular matrix receptor interaction.Four diagnostic genes,CFP,COL4A2,ITGA1,and GRPEL1,were screened by multidimensional analysis.Immune infiltration analysis showed that the diagnostic genes were closely associated with mast cell resting state,memory B cells,and memory CD4+T cells.Reverse transcription-polymerase chain reaction analysis showed significantly increased mRNA expression levels of the four diagnostic genes in the Jagged1-induced model group(P＜0.05).The predicted components,sterol,kaempferol,and quercetin,all had good binding activities with the diagnostic genes.Enzyme-linked immunosorbent assay result confirmed that all three active components significantly reduced the expression of collagen type Ⅳ α2 chain protein in Jagged1-induced LSECs,with quercetin having the most significant effect(P＜0.01).Conclusions This study elucidated the molecular mechanism of hepatic sinusoidal endothelial cells involved in the pathological process of HF through mesenchymal transition.We also propose a diagnostic marker system including CFP,COL4A2,ITGA1,and GRPEL1 as core genes.The result also suggest that natural active ingredients,such as quercetin,may exert anti-HF pharmacological effects by targeting these diagnostic genes.

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 establish an automatic microscope scanning system based on the oil-lens for replacing the traditional manual microscopy reading of blood films to improve the efficiency and the detection rate of Plasmodium.Methods The system consisted of an optical microscope,digital camera,control software and general computer-based component.The system and professional persons read the blood films with single-blind method,everyone read 10 blood samples(100 fields of vision per blood film),and the time and results of reading were recorded.Results The system had the function of automatic displacement and focus,automatic scanning and storage,automatic back-bit and reset,annotation,and automatic counting,reporting and printing.The system can increased the speed of reading films by 30.58%,and improved the accuracy by 13.33%.Conclusion The automatic microscope scanning system can improve the speed and accuracy of reading films and the operation is simple.