Portosystemic shunts in a large cohort of patients with liver cirrhosis: detection rate and clinical relevance

This study aimed to determine the detection rate and clinical relevance of portosystemic collaterals. We studied 326 cirrhotics. Portosystemic collaterals, portal vein diameter, and splenic area were evaluated by color Doppler sonography; esophageal varices were detected by endoscopy. Of the cirrhotics, 130 had portosystemic collaterals (39.9% total, left gastric vein 11%, paraumbilical vein 7.4%, splenorenal shunts 13.8%, and combined shunts 7.7%). Cirrhotics without portosystemic collaterals or with a paraumbilical vein had a significantly narrower portal vein diameter than cirrhotics with a left gastric vein (P < 0.001). Cirrhotics with a paraumbilical vein had a significantly smaller splenic area than cirrhotics with a left gastric vein (P < 0.001), splenorenal shunts (P < 0.001), combined shunts (P < 0.001), or without portosystemic collaterals (P < 0.05). A significant association between portosystemic collaterals and Child's classes or presence and type of esophageal varices was found (P < 0.0001 and P = 0.0004, respectively). The highest prevalence of Child's class C and large (F-3) esophageal varices was found in cirrhotics with a left gastric vein (41.7% and 36.1%, respectively), whereas esophageal varices were absent in 47.4% of cirrhotics without portosystemic collaterals and in 58.3% of cirrhotics with a paraumbilical vein. The left gastric vein is associated with some sonographic and clinical markers of disease severity, whereas the absence of portosystemic collaterals or the presence of paraumbilical veins seems to identify cirrhotics with markers predictive of a more favorable clinical course.