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 investigate localized regional recurrence after chemotherapy and chest radiotherapy in limited stage small cell lung cancer (LS-SCLC),and explore the relationship between recurrence location and radiotherapy and chemotherapy and its influencing factors.Methods From 2006 to 2014,pathological LS-SCLC treated in CAMS,125 patients had local recurrence,Kaplan-Meier statistical method was used to analyze the survival rate and PFS of each recurrence site.Log-rank was used to compare the survival rate of each group.Univariate analysis includes Chi-squareand t-test for the factors for the recurrence site.Multivariate analysis using Logistic regression.Results The 1-,2-and 5-year overall survival rates were 92.0％,46.4％ and 14.7％,respectively.The median progression time was 12.96 months,The median survival time after progression was 1 1.5 months,and the 1-,2-,and 5-year overall survival rates were 45.0％,23.0％,and 10.0％,respectively.The recurrence sites include intrapulmonary recurrence (67 patients),regional lymph nodes (21 patients),simultaneous intrapulmonary and regional lymph nodes (28 patients),and contralateral or supraclavicular lymph nodes (9 patients).The median survival time were 23.96 months,24.76 months,23.23 months,and 18.66 months,and the 2-year survival rates were 49％,52％,46％,and1 1％,respectively (P=0.000,0.004,0.008).In 6 patients (4.0％),5 patients were located in the supraclavicular region,and 1 patient (0.8％) in the field.Conclusions For LS-SCLC undergoing IMRT and chemotherapy,the local failure location is mainly located in the pulmonary,and further treatment of the split dose and targets requires further clinical exploration.

Objective: To evaluate the incidence and risk factors of symptomatic radiation-induced lung toxicity (SRILT) in non-small cell lung cancer (NSCLC) patients treated with modern radiotherapy after surgery. Methods: Clinical data of consecutive NSCLC patients treated with postoperative three-dimensional conformal or intensity-modulated radiotherapy in Cancer Hospital of Chinese Academy of Medical Sciences between November 2002 and December 2011 were retrospectively analyzed. According to the Common Terminology Criteria for Adverse Events (CTCAE, version 3.0), SRILT was defined as ≥grade 2 radiation-induced lung toxicity. Potential clinical risk factors and dosimetric parameters for SRILT were evaluated using logistic regression model. Results: Among 227 enrolled patients, 190 cases underwent lobectomy and 37 patients received pneumonectomy. Twenty-three patients (10.1%) developed SRILT after lobectomy. Seventeen patients experienced grade 2 SRILT, 5 cases of grade 3 SRILT and 1 case of grade 4 SRILT. Univariate analysis showed that postoperative concurrent chemoradiotherapy, relatively large PTV, mean lung dose and V₂₀- V₄₀ were significantly correlated with the incidence of SRILT (P=0.015, 0.048 and<0.001). Multivariate analysis demonstrated that postoperative concurrent chemoradiotherapy and V₂₀ were significantly associated with the incidence of SRILT (P=0.017 and P=0.009). Conclusions The incidence of SRILT is relatively low in NSCLC patients after postoperative radiotherapy. Concurrent chemoradiotherapy and V₂₀ are risk factors of SRILT.

Objective To compare the clinical efficacy and toxicity between nedaplatin-and cisplatin-based regimens in patients with unresectable locally advanced non-small cell lung cancer (NSCLC) receiving concurrent chemoradiotherapy.Methods From January,2015 to December,2016,patients with unresectable locally advanced NSCLC receiving concurrent chemoradiotherapy were included in this study.Patients received thoracic radiotherapy (RT) combined with nedaplatin-based concurrent chemotherapy were enrolled in the nedaplatin group (n=38).Those treated with thoracic RT combined with cisplatin-based chemotherapy were allocated into the cisplatin group (n=84).The chemotherapy regime consisted of platinumin combination with paclitaxel or etoposide.Platinum combined with pemetrexed was adopted in patients with adenocarcinoma.Overall,the median age was 58 years old.Most of the patients were male (86.1％),77.0％ of them had a history of smoking and 63.9％ of the patients were pathologically diagnosed with squamous cell carcinoma.Besides,59.0％ of the patients had Ⅲ B NSCLC.Results In the nedaplatin and cisplatin groups,the overall response rate (ORR) was 79％ and 86％,and the disease control rate was 94％ and 94％.The median follow-up time was 20 months.In the nedaplatin group,the 1-and 2-year PFS was 49％ and 23％,and 67％ and 39％ in the cisplatin group (P=0.160).In the nedaplatin group,the 1-and 2-year OS was 91％ and 72％,and 89％ and 68％ in the cisplatin group (P=0.552).Nine patients (24％) had ≥grade 3 adverse events in the nedaplatin group and 25 patients (30％) in the cisplatin group (P=0.488).No statistical significance was found in radiation-induced esophagitis,bone marrow suppression and gastrointestinal toxicity between two groups.One patient in the nedaplatin group presented with grade 3 radiation-induced pneumonitis and 2 patients died of radiation-induced pneumonitis in the cisplatin group.Conclusions Thoracic radiotherapy combined with nedaplatin-based chemotherapy is a promising option for patients with unresectable locally NSCLC.Compared with the cisplatin-based chemotherapy,nedaplatin-based regime yields equivalent clinical efficacy and less adverse events,especially suitable for the elderly patients with poor tolerance.

Objective To observe the objective response rate, survival and safety of radiotherapy combined with Iressa for patients with locally advanced non-small cell lung cancer ( NSCLC) unsuitable for surgery or concurrent chemoradiotherapy. Methods The patients with locally advanced NSCLC unsuitable for surgery or concurrent chemoradiotherapy were recruited and received thoracic intensity-modulated radiotherapy ( IMRT) combined with Iressa 250 mg daily. Results A total of 30 patients were enrolled between July 2014 and March 2017. Twenty-nine patients were analyzed. At 1 month after radiotherapy,the complete response (CR) was 0,partial response (PR) was 21(72％),stable disease (SD) was 6(21％), progressive disease (PD) was 2(7％),the disease control rate (CR+PR+SD) was 93％,and the objective response rate was 72％. The median follow-up time was 25 months. Fourteen ( 48％) patients died,and 15 (52％) survived. Twenty-three (79％) patients obtained PD including local progression in 18(62％) and distant metastasis in 14(48％). The median survival time (MST) was 26 months and the median PFS was 11 months. The 1-year OS and PFS were 79％ and 44％,and the 2-year OS and PFS were 55％ and 18％. Univariate analysis demonstrated that smoking history and disease stage were influencing factors for OS ( P=0. 035,0. 031) . Moreover, disease stage, the primary tumor diameter, the volume of GTV and PTV were influencing factors for PFS (P=0. 000,0. 016,0. 039,0. 030). Multivariable analysis revealed that disease stage and the volume of PTV were independent prognostic factors for PFS (P=0. 000,0. 012).Two patients ( 7％) developed grade 3 acute adverse events and 7 ( 24％) experienced grade 2 acute irradiation pneumonitis. Conclusions For patients with locally advanced NSCLC unsuitable for surgery or concurrent chemoradiotherapy,IMRT combined with Iressa yields high objective response rate and well tolerance. The long-term clinical efficacy remains to be validated.

Functional proteins designed de novo have potential application in chemical engineering, agriculture and healthcare. Metal binding sites are commonly used to incorporate functions. Based on a de novo designed protein DS119 with a βαβ structure, we have computationally engineered zinc binding sites into it using a home-made searching program. Seven out of the eight designed sequences tested were shown to bind Zn(2+) with micromolar affinity, and one of them bound Zn(2+) with 1:1 stoichiometry. This is the first time that metalloproteins with an α, β mixed structure have been designed from scratch.
Amino Acid Sequence ; Binding Sites ; Computer Simulation ; Escherichia coli ; Hydrogen Bonding ; Hydrophobic and Hydrophilic Interactions ; Kinetics ; Magnetic Resonance Spectroscopy ; Metalloproteins ; chemistry ; genetics ; metabolism ; Models, Molecular ; Molecular Sequence Data ; Mutagenesis, Site-Directed ; Protein Binding ; Protein Engineering ; Protein Structure, Secondary ; Recombinant Proteins ; chemistry ; genetics ; metabolism ; Zinc ; chemistry ; metabolism

Objective To study the value of image-guided radiotherapy (IGRT) in lung cancer. Methods From Mar. 2007 to Dec. 2007,58 patients with lung cancer were treated with IGRT. Set-up er-rors in each axial direction was calculated based on IGRT images of each patient. The change of GTV was e-valuated on both cone-beam CT and CT simulator images. Results Twenty-two patients with left lung cane-er,30 with right lung cancer,5 with mediastinal lymphanode metastasis and one with vertebra metastasis were included. The set-up error in x,y and z axes was (0.02±0.26) cm, (0.14±0.49) cm and ( -0. 13± 0.27) cm, respectively,while the rotary set-up error in each axis was -0.15°± 1.59°, -0.01°± 1.50° and 0.12°±1.08°, respectively. The set-up errors were siguifieantly decreased by using of IGRT. GTV movement was observed in 15 patients (25.9%) ,including 5 with left upper lung cancer. GTV moving to the anterior direction was observed in 9 patients,including 4 with]eft upper lung cancer. GTV reduced in 23 (44.2%) patients during treatment. Asymmetric GTV reduction of 22 lesions was observed,with a mean re-ductive volume of 4.9 cm3. When GTV began to shrink,the irradiation dose was 4 -46 Gy,with 20 -30 Gy in 9 patients. Conclusions The use of IGRT can significantly reduce set-up errors. GTV movement and reduction are observed in some cases. The time to modify the target volume needs to be further studied.

Objective To evaluate the efficacy of three-dimensional conformal radiation therapy (3DCRT) for esophageal carcinoma and identify prognostic factors in this patient group.Methods From May 2002 to Jun 2005,132 patients with unresectable or inoperable esophageal cancer were treated with 3DCRT in our hospital.Their chnical data were analyzed retrospectively.ResultsThe 1-and 2-year local control rates was 65.4% and 52.1% in the whole group,respectively.The overall 1-and 2-year survival rate was 50.7% and 32.2% ,respectively.The median survival time was 13 months.The 1-and 2-year survival rate was 56.7%and 36.7% in stageⅠ + Ⅲ ,respectively,with 35.2% and 14.7% in stage IV.The median survival time were 15 months and 9 months for stage Ⅰ +Ⅲ and Ⅳ,respectively(x2 = 8.17,P = 0.004). Of patients with stage Ⅰ + Ⅲ disease who were absent of perforation sign before radiotherapy,with lesion length less than 8.0 cm and whole course given by 3DCRT,the 1-and 2-year survival rate was 73.0% and 49.9%,respectively.Univariate analysis revealed that condition of alimentation,absence of perforation sign, short lesion length,early TNM stage were associated with good survival.Multivariate analysis confirmed that absence of perforation sign and lesion length were independent prognostic factors for survival. Conclusions 3DCRT is effective for esophageal carcinomas in terms of survival and local control.Further improvement could be achieved with muhi-modality treatment.Absence of perforation sign and lesion length are independ ent prognostic factors for survival.