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.

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 evaluate the measurement uncertainty in the determination of paracetamol tablets by UV. Methods:The mathematical model of content determination by UV was established and the uncertainty sources were analyzed. Each active component of uncertainty was calculated, and the expanded uncertainty was obtained. Results:The expanded uncertainty for the UV determination of paracetamol tablets was 1. 2%,and the content determination result was (97. 0 ± 1. 2) % (k=2). Conclusion:The main sources of uncertainty are analyzed, which can provide reliable theoretical basis for the effective control of the method.

Objective:To establish a method for the uncertainty evaluation of the determination of benzoic acid. Methods: The content of benzoic acid was determined by acid-base titration. By constructed mathematics model, the source of the measurement uncer-tainty was analyzed, and the uncertainty components were quantized and combined. Results:The expanded uncertainty of benzoic acid was 0. 36% and the results were expressed as(99. 99 ± 0. 36%,k=2). Conclusion:The mathematics model is reasonable and relia-ble,and can be used in the uncertainty evaluation of content measurement of benzoic acid.

Objective:To establish an HPLC method for the determination of two components and the preservative in compound dextromethorphan hydrobromide syrups. Methods:An Agilent Zobax SB-C18 column(250 mm × 4. 6 mm,5 μm) was used with meth-anesulfonic acid solution (adding 4. 8g methanesulfonic acid and 10ml triethylamine into 750ml water,and adjusting the pH value to 3. 5 by phosphoric acid)-acetonitrile (75∶25) as the mobile phase at the flow rate of 1. 0 ml·min-1 and 280nm as the detection wave-length. Results:The calibration curve was linear within the range of 102-1 025μg·ml-1 for guaifenesin,15-619μg ·ml-1 for dextro-methorphan hydrobromide and 10-407μg·ml-1 for benzoic acid. The average recovery of guaifenesin, dextromethorphan hydrobromide and benzoic acid was 100. 0% (RSD=0. 35%), 100. 1%(RSD=0. 77%)and 100. 8%(RSD=0. 49%), respectively. Conclusion:The method is simple,rapid and accurate,and suitable for the quality assessment of compound dextromethorphan hydrobromide syrups.

AIM: To establish the fingerprint analysis method of Jiketing Granules(Fructus Forsythiae,Radix Scutellariae,Radix Bupleuri,etc) by HPLC-UV.METHODS: Aanalysis was performed on an alltima C_(18)(4.6 mm?250 mm,5 ?m) column with a acetonitrile-0.1% acetic acid gradient.Detection time was 55 min.The flow rate was 1.0 mL/min.The montoring wavelength was changed.The colunm temperature was at 30℃. RESULTS: 21 peaks were separated on HPLC fingerprint in Jiketing Granules. CONCLUSION: The method is reliable,accurate and can be used as a quality control for Jiketing Granules.