Development of a Web Application based on Machine Learning for screening esophageal varices in cirrhosis


Soumaya Mrabet
Kamel Aloui
Elhem Ben Jazia


Introduction : Esophageal varices (EV) are a common manifestation of portal hypertension in cirrhotic patients. Upper gastrointestinal endoscopy (UGE) is the gold standard for diagnosing EV. However, it is an invasive examination with a relatively high cost.

Aim : To develop a machine learning model for the prediction of EV in cirrhotic patients.

Methods: This is a cross-sectional observational study including all cirrhotic patients, for whom an UGE was performed, between January 2010 and December 2019. We adopted a structured methodical approach with reference to CRISP-DM (Cross-Industry Standard Process for Data Mining). The different steps carried out were: data collection and preparation, modelization, and deployment of the predictive models in a web application.

Results: We included 166 patients, 92 women (55.4%) and 74 men (44.6%). The mean age was 57.2 years. In UGE, 16 patients (9.6%) did not have EV. Other patients had EV grade 1 in 41 cases (24.7%), grade 2 in 81 cases (24.7%) and grade 3 in 28 cases (16.9%). After the selection phase, among the 36 initial variables, 19 were retained. Three machine learning models have been developed with a performance of 90%.

Conclusions: We developed a machine learning model combining several clinical and para-clinical variables for the predcition of EV in cirrhotic patients.


artificial intelligence, machine learning, esophageal varices, cirrhosis



  1. - Sanyal AJ, Bosch J, Blei A, et al. Portal hypertension andits complications. Gastroenterology 2008;134:1715—28.
  2. - De Franchis R. Revising consensus in portal hypertension:report of the Baveno V consensus workshop on methodologyof diagnosis and therapy in portal hypertension. J Hepatol2010;53:762—8.
  3. - Moulion Tapouh JR, Njoya O, Monabang Zoé C, el al. Approche non Endoscopique du Diagnostic des Varices OEsophagiennes d’Origine Cirrhotique dans une Population d’Afrique Noire Subsaharienne. Health Sci. Dis 2015;16.
  4. - Dong T, Kalani A, Aby E, et al. Machine Learning-based Development and Validation of a Scoring System for Screening High-Risk Esophageal Varices. Clinical Gastroenterology and Hepatology 2019;17:1894–1901
  5. - Microsoft Experiences, Tout savoir sur l’Intelligence Artificielle, available on: ia business/comprendre-utiliser-intelligence-artificielle/
  6. - Seong Ho P, Kyung-Hyun D, Sungwon K, et al. What should medical students know about artificial intelligence in medicine? J Educ Eval Health Prof 2019;16:18.
  7. - Adadi A , Adadi S ,Berrada M, et al. Gastroenterology Meets Machine Learning. Hindawi Advances in Bioinformatics 2019; 2019
  8. - Guide CRISP-DM de IBM SPSS Modeler.
  9. - Hong W, Ji Y, Wang D, et al. Use of artificial neural network to predict esophageal varices in pa¬tients with HBV related cirrhosis. Hepat Mon. 2011;11(7):544.
  10. - Stefanescu H, Radu C, Procopet B, et al. Noninvasive menage a trois for the predictionof high-risk varices: stepwise algorithm using lok score, liverand spleen stiffness. Liver Int 2015;35:317—25.
  11. - Pateu E, Oberti F, Cales P, et al. The noninvasive diagnosis of esophageal varices and its application in clinical practice. Clin Res Hepatol Gastroenterol 2018;42(1), 6-16.