Noninvasive Predictors of High-Risk Varices in Patients with Non-Cirrhotic Portal Hypertension

Non-cirrhotic portal hypertension (NCPH) comprises a heterogeneous group of liver disorders causing portal hypertension without cirrhosis and carries a high risk of variceal bleeding. Recent guidelines, based largely on patients with viral cirrhosis, suggest low likelihood of high risk varices (HRV) in patients with a liver stiffness measurement (LSM) <20kPa and platelet count >150 x 10(9)/L. In NCPH, LSM is often higher than healthy controls but lower than matched cirrhotic patients. The aim of this study was to assess whether LSM or other noninvasive assessments of portal hypertension could predict HRV in NCPH patients. Methods. Records of patients with NCPH seen at a single centre between 2007 and 2018 were reviewed retrospectively. Primary outcome measure was presence or absence of HRV at gastroscopy within 12 months of clinical assessment. Association of LSM or other clinical features of portal hypertension (spleen size, platelet count, platelet count/spleen length ratio (PSL), LSM-spleen length/platelet count ratio score (LSP)) with HRV and ability of these variables to predict HRV was analysed. Results. Of 44 patients with NCPH who met inclusion criteria, 34% (15/44) had HRV. In a multivariate model, spleen size and PSL correlated with HRV but platelet count, LSM, and LSP did not (spleen size: = 0.35, p = 0.02; OR 1.42, 95% CI 1.06-1.92; PSL: = -1.47, p = 0.02; OR 0.23, 95% CI 0.07-0.80). There was no significant difference between spleen size and PSL in predicting HRV (AUROC 0.81 (95% CI 0.66 - 0.91) versus 0.71 (95% CI 0.54 - 0.84), respectively, p = 0.400). Spleen size >17.2cm had sensitivity 78.6% and specificity 64.3% for prediction of HRV. Conclusions. In NCPH patients, spleen size may predict risk of HRV at gastroscopy within 12 months. LSM and platelet count are not useful to assess risk of HRV in NCPH.