Prediction of large esophageal varices in cirrhotic patients using classification and regression tree analysis

Hong, Wandong; Dong, Lemei; Jiang, Zen-cai; Zhu, Qi-huai; Jin, Shuqing

doi:10.1590/s1807-59322011000100021

Cited by 23 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liver cirrhosis-associated portal hypertension causes splenomegaly and hypersplenia and resultant decreases in platelet count and hemoglobin level. Indeed, platelet count/spleen diameter has been shown to be robust in variceal prediction [13,[15][16][17][20][21][22]. Our data are consistent with these reports and further demonstrate a more powerful predictive function for large esophageal varices by pooling these variables together.…”

Section: Discussionsupporting

confidence: 90%

“…e predictive variables included in our nal model were also previously reported to be promising in variceal prediction; for example, the diagnostic e ectiveness of portal vein diameter in prediction of large esophageal varices has been proven in several studies [13,20]. Liver cirrhosis-associated portal hypertension causes splenomegaly and hypersplenia and resultant decreases in platelet count and hemoglobin level.…”

Section: Discussionmentioning

confidence: 96%

See 1 more Smart Citation

Noninvasive prediction of large esophageal varices in liver cirrhosis patients

Wang¹,

Hu²,

Dong³

et al. 2014

CIM

View full text Add to dashboard Cite

Noninvasive prediction of large esophageal varices in liver cirrhosis patients Abstract Purpose: Esophageal varices are a dangerous complication of liver cirrhosis. e development of cost e ective, noninvasive means for prediction of large esophageal varices could reduce the use of upper gastrointestinal endoscopy in variceal screening and also provide an alternative way to con rm the results of conventional endoscopic diagnosis. Previously proposed predictive models are neither sensitive nor speci c.Methods: A retrospective study based on a group of 104 liver cirrhosis patients was performed. Multiple statistical approaches were used to evaluate the association of large esophageal varices with 20 individual and six compound clinical laboratory variables. A new predictive model was developed.Results: Univariate analysis suggested that eight out of 26 variables were signi cantly associated with large esophageal varices. Further stepwise logistic regression eventually identied three variables (hemoglobin level, portal vein diameter and the ratio of platelet count/ spleen diameter) that contributed signi cantly to the nal regression model. Receiver operating characteristic (ROC) curve analysis showed that this new regression model achieved 77.8% and 72% of diagnostic sensitivity and speci city, respectively, for the prediction of large esophageal varices. In our study group, its diagnostic accuracy (AUROC=0.814) was found to be signi cantly higher than six predictive models previously published.Conclusions: No single variable o ers self-su cient predictive function for large esophageal varices. A comprehensive model using multiple variables signi cantly improves the predictive accuracy in screening the most at risk patients with potential variceal hemorrhage.

show abstract

Section: Discussionsupporting

confidence: 90%

Section: Discussionmentioning

confidence: 96%

Noninvasive prediction of large esophageal varices in liver cirrhosis patients

Wang¹,

Hu²,

Dong³

et al. 2014

CIM

View full text Add to dashboard Cite

show abstract

“…Parameters directly or indirectly linked to portal hypertension, such as splenomegaly and decreased platelet count, were predictors of the presence of esophageal varices . 10 conducted a study to develop a decision model based on classification and regression tree analysis for the prediction of large esophageal varices in cirrhotic patients. 309 cirrhotic patients (training sample, 187 patients; test sample 122 patients) were included.…”

Section: Fig-2mentioning

confidence: 99%

Correlation of portal vein diameter, splenomegaly and thrombocytopenia with gastro-espohageal varices in cirrhotic patients

Singh¹,

Sehgal²,

Singh³

et al. 2017

Int. J. Curr. Res. Med. Sci

View full text Add to dashboard Cite

Background: Portal hypertension is one of the complications of chronic liver disease due to cirrhosis liver. Portal vein diameter, Splenomegaly and Thrombocytopenia can be used as Non-Invasive markers for the presence of gastro-esophageal varices in cirrhotic patients. Early detection of gastro-esophageal varices can prevent the UGI variceal bleed in cirrhotic patients. Hence the correlation of portal vein diameter, splenomegaly and thrombocytopenia with Gastro-Esophageal Varices helps in early detection of gastro-esophageal varices. Method: This study was conducted on 100 patients of cirrhosis and investigations for platelet count, ultrasonography for portal vein diameter and upper GI endoscopy for esophageal varices detection were undertaken in all the patients.. Results: Our study demonstrated that thrombocytopenia, presence of portal hypertension with splenomegaly and portal vein diameter are strong predictors of developing gastro-esophageal varices in cirrhotic patients. Conclusion: in cirrhotic patients gastro-esophageal varices has direct correlation with Portal hypertension and inverse correlation with platelet count.

show abstract

“…The high frequencies of the HLA genotypes DQ2 and DQ8 that were found in first-degree relatives would make it difficult to use these HLA genotypes for routine diagnosis of celiac disease in this group. Hong et al (28) aimed to develop a decision model based on classification and regression tree analysis for the prediction of large esophageal varices in cirrhotic patients. They conclude that a decision tree model that consists of spleen width, portal vein diameter and prothrombin time may be useful for prediction of large esophageal varices in cirrhotic patients.…”

Section: Gastroenterologymentioning

confidence: 99%

Untitled

2012

Clinics

View full text Add to dashboard Cite

Prediction of large esophageal varices in cirrhotic patients using classification and regression tree analysis

Cited by 23 publications

References 23 publications

Noninvasive prediction of large esophageal varices in liver cirrhosis patients

Noninvasive prediction of large esophageal varices in liver cirrhosis patients

Correlation of portal vein diameter, splenomegaly and thrombocytopenia with gastro-espohageal varices in cirrhotic patients

Untitled

Contact Info

Product

Resources

About