HRS2C2 - Hemorrhagic Risk Scoring System in Cirrhotic Children by DNAlytics and UCLouvain

Université catholique de Louvain
Cliniques universitaires Saint-Luc-Département de Pédiatrie-Service de Gastroentérologie et Hépatologie Pédiatrique

Nicolas Bonnet, Etienne Sokal and Xavier Stephenne

Cirrhosis in children happens and often stems from a wide variety of causes. Up to now, biliary atresia, after failed Kasai surgery, remains the leading cause of children cirrhosis and pediatric transplantation. While awaiting a transplant, cirrhotic patients, whatever the cause, run the risk of gastrointestinal (GI) bleeding due to portal hypertension. In cases of portal hypertension in children, it is established that bleeding risk is correlated with esophageal varices characteristics (Grade III varices; red color signs) [1, 2]. While recommended in adults [2, 3, 4], prophylactic treatment remains controversial in children, despite being suggested by several authors [2, 5, 6]. The procedure is indeed a delicate one and not devoid of complications. Moreover, living donor related liver transplantation, an increasingly common solution in recent years, has significantly reduced waiting times, leading to doubts about interest of prophylactic treatment. In a retrospective study, we had identified three clinically relevant predictive factors for the risk of bleeding from EV in 83 patients suffering from biliary atresia. These factors included red color signs and high-grade EV on first endoscopic examination, as well as low fibrinogen levels. Based on them, we were able to build a predictive model of EV bleeding risk [7]. This model was validated in a prospective study with cirrhotic children waiting for a liver transplant [8].

In the left column of this page, you can find the way to calculate the bleeding risk of cirrhotic children. This can help you in the decision of varices banding prophylactically.

How to interpret the results ?

The model used to compute the bleeding risk has an estimated predictive performance of 81.03% in balanced classification rate (average between specificity and sensitivity) with a 95% confidence interval of [70.49, 91.56]. The accuracy is of 88.55% with a 95% confidence interval of [82.83, 94.26]. Note: The probability output with the label reflects the confidence that the model has in its prediction. The predictive performances mentionned above are computed using a cutoff at 50% on this probability.

Esophageal varices classification [9]

  • Grade 0: No varices
  • Grade 1: Varices that are flattened with insufflation during endoscopy
  • Grade 2: Varices that are not flattened with insufflation and that are non-confluent
  • Grade 3: Varices that are not flattened with insufflation and that are confluent
  • Grade 4: Pseudo-tumoral varices obstructing the esophageal lumen

About DNAlytics

DNAlytics is a Belgian company founded in 2012 as a UCLouvain Spin-Off that bases its activities on a data mining technology platform. Based on this technology platform, DNAlytics covers the whole development of data-driven personalized medicine solutions, from R&D to market access. DNAlytics proposes its expertise in the form of two separate offers: a data mining consultancy service and the development of a data-driven personalized medicine product pipeline. DNAlytics received various awards, namely from IBM, Microsoft and the European Commission, both for its technology and its business model.

How to cite this calculator ?

To cite this calculator, use this reference: "Jérôme Paul, Xavier Stephenne, Thibault Helleputte - HRS2C2, an online calculator for the Hemorrhagic Risk Scoring System in Cirrhotic Children,, 2015.". To cite the scientific work behind this calculator, use the references below to Wanty et al. and/or Bonnet et al.


  1. de Francis R. Revising consensus in portal hypertension: report of the Baveno V consensus workshop on methodology of diagnosis and therapy in portal hypertension. J Hepatology 2010; 53:762-768.
  2. Duché M, Ducot B, Tournay E, Fabre M, Cohen J, Jacquemin E, et al. Prognostic value of endoscopy in children with biliary atresia at risk for early development of varices and bleeding. Gastroenterology 2010; 139:1952-1960.
  3. Garcia-Pagan JC, De GA, Bosch J. The modern management of portal hypertension—primary and secondary prophylaxis of variceal bleeding in cirrhotic patients. Aliment Pharmacol Ther 2008; 28:178-186.
  4. Tiani C, Abraldes JG, Bosch J. Portal hypertension: pre-primary and primary prophylaxis of variceal bleeding. Dig Liver Dis 2008;40:318-327.
  5. Duché M, Habès D, Roulleau P, Haas V, Jacquemin E, Bernard O. Prophylactic endoscopic sclerotherapy of large esophagogastric varices in infants with biliary atresia. Gastrointest Endos. 2008;67:732-737.
  6. Celińska-Cedro D, Teisseyre M, Woynarowski M, Socha P, Socha J, Ryzko J. Endoscopic ligation of esophageal varices for prophylaxis of first bleeding in children and adolescents with portal hypertension: preliminary results of a prospective study. J Pediatr Surg 2003; 38: 1008-1011.
  7. Wanty C, Helleputte T, Smets F, Sokal EM, Stephenne X. Assessment of risk of bleeding from esophageal varices during management of biliary atresia in children. J Pediatr Gastroenterol Nutr. 2013;56(5):537-543.
  8. Bonnet N, Castanarès D, Smets F, Eeckhoudt S, Hermans C, Sokal E, Stephenne X. Evaluation du risque de saignement de varices oesophagiennes chez des enfants atteints de cirrhose et en attente d’une greffe de foie. Présentation orale GFHGNP 2016, mars, Paris.
  9. Beppu K, Inokuchi K, Koyanagi N et al. Prediction of variceal hemorrhage by esophageal endoscopy. Gastrointest Endosc. 1981 Nov; 27(4):213-8.
and icons designed by Freepik