1.Comparison of different prediction models based on machine learning algorithms for the risk of poor postoperative wound healing in patients with spinal tuberculosis
Jinglian WEN ; Wei TANG ; Chengli WU ; Run LI ; Qing YE ; Guoxuan PENG
Chongqing Medicine 2025;54(11):2552-2558
Objective To analyze risk factors for poor postoperative wound healing in spinal tuberculo-sis patients and construct prediction models along with a risk scoring table using machine learning algorithms,providing references for early prevention and management.Methods Clinical data from 420 spinal tuberculo-sis patients treated at four tertiary hospitals in Guizhou Province between January 2017 and February 2024 were retrospectively analyzed.Risk factors were identified through univariate and multivariate analyses.Logis-tic regression,random forest,and support vector machine prediction models were constructed.Model perform-ance was evaluated using receiver operating characteristic(ROC)curves,precision,recall,accuracy,and F1-score.A risk prediction scoring table for poor postoperative wound healing was subsequently developed.Re-sults Among the 420 patients with spinal tuberculosis,132 experienced poor postoperative wound healing,with an incidence rate of 31.43%.Logistic regression analysis showed that BMI≤18.5 kg/m2,preoperative albumin≤30 g/L,combined surgical procedure,intraoperative blood loss>1 000 mL,direct bilirubin>8 μmol/L within 3 days after surgery,neutrophil count≤75×109/L within 3 days after surgery,and postopera-tive drainage volume>500 mL were risk factors for poor postoperative wound healing(P<0.05).In the comparison among the three risk prediction models constructed based on machine learning algorithms,the ran-dom forest model demonstrated the best predictive performance.A risk prediction scoring table was construc-ted based on the partial regression coefficients from the multivariate analysis,with a total score range from 0 to 11 points.A score>6 points indicated an increased risk of poor postoperative wound healing.The area un-der the ROC curve(AUC)for this risk prediction scoring table was 0.846(95%CI:0.769 to 0.923),indica-ting good predictive performance.Conclusion The random forest model based on machine learning algorithms and the risk prediction scoring table have certain predictive value for assessing the risk of poor postoperative wound healing in patients with spinal tuberculosis;they can assist healthcare professionals in early identifica-tion of high-risk patients.
2.Evaluation of the efifcacy of endoscopic tissue adhesive injection in treatment of gastric varices bleeding from liver cirrhosis
Chuankang TANG ; Chengli WEN ; Xiaobin HE ; Yan PENG ; Xujuan LUO ; Xia CHEN ; Youjian ZHANG
China Journal of Endoscopy 2017;23(2):81-86
Astract: Objective To explore the efifcacy and safety of endoscopic tissue adhesive injection in treatment of gastric variceal bleeding from liver cirrhosis.Methods Object of study are 92 cirrhotic patients (72 male/20 female) in hospital, who had been diagnosed with gastric varices bleeding from June 2014 to May 2016. Child-Pugh score at presentation for cirrhotic patients was A-28; B-36; C-28. According to endoscopic classiifcation of gastric varices, GEV1 were detected in 80 patients, GEV2 in 12. All patients were treated with endoscopic hypertonic glucose tissue adhesive ‘sandwich’ injection.Result Successful injection rate was 100.0% in 92 patients, among which 40 patients had accepted emergency endoscopic treatment and the immediate hemostasis rate was 100.0%. 65 patients were Having gastroscope review after the injection six months, 22 patients were significantly effective, accounting for 33.8%; 38 patients were effective, accounting for 58.4%; 5 patients were invalid, accounting for 7.7%. All the patients were followed up in 1 to 24 months. The late-rebleeding rate was 2.2%. None of them were having early-rebleeding or dead; Complications the incidence of rebleeding rate which caused by removing the needles which trapped in the varices was 2.2%. The incidence of chest pain rate was 4.3%, the bloating rate was 6.5% and the ulceration rate was 15.2%. There was no complications like fever, infection, stomachache, embolism and so on.Conclusion With low rebleeding rate and light side-effect, endoscopic tissue adhesive injection in the treatment of gastric variceal bleeding caused by cirrhosis portal hypertension has really good effect.
3.Molecular cloning and expression analysis of sucrose synthase gene from Dendrobium officinale.
Hengling MENG ; Chengli DUAN ; Fenghui XIAO ; Shengchao YANG ; Yinghong ZHA ; Guosong WEN
China Journal of Chinese Materia Medica 2011;36(7):833-837
OBJECTIVEClone of sucrose synthase of Dendribium officinale and expression analysis, to provide the theory basis for research the relationship between polysaccharide synthesis of D. officinale and sucrose synthase activity.
METHODAccording to homologous sequence of sucrose synthase gene on GenBank, application the technology of RT-PCR and RACE, clone the full length of D. officinale. Target gene amplified with T vector was transformed into competent E. coli. BL21, IPTG induced expression, SDS-PAGE analysis.
RESULTA full length cDNA encoding sucrose synthase was isolated from the D. officinale, named DOSS1, the GenBank accession number is HQ856835, the cDNA is 2781 bp in length containing an open reading frame of 2424 bp encoding 807 amino acids with a predicted molecular mass of 92.3 x 10(3), the deduced amino acid sequence of D. officinale sucrose synthase shares 95% identity with Mokara yellow (AF530568); shares 90% identity with Oncidium goldiana (AF530567); shares more than 80% with other monocotyledonous plants.
CONCLUSIONCloned the sucrose synthase gene and induced an obvious band successfully.
3' Untranslated Regions ; genetics ; 5' Untranslated Regions ; genetics ; Cloning, Molecular ; Dendrobium ; enzymology ; genetics ; metabolism ; Escherichia coli ; genetics ; Gene Expression Regulation, Plant ; Glucosyltransferases ; genetics ; metabolism ; Phylogeny ; Polysaccharides ; biosynthesis

Result Analysis
Print
Save
E-mail