Machine learning models predicting decompensation in cirrhosis

SophieElisabeth Müller; Cristina Ripoll; Alexander Zipprich; Tony Bruns; Paul Horn; Marcin Krawczyk; Frank Lammert; MatthiasChristian Reichert

doi:10.1055/s-0041-1740706

Zeitschrift für Gastroenterologie, Table of Contents

Z Gastroenterol 2022; 60(01): e18-e19
DOI: 10.1055/s-0041-1740706

Abstracts | GASL

Machine learning models predicting decompensation in cirrhosis

SophieElisabeth Müller

¹Department of Medicine II, Saarland University Medical Center, Saarland University, Homburg, Germany

,

Cristina Ripoll

²Clinic for Internal Medicine IV, University Hospital Jena, Jena, Germany

,

Alexander Zipprich

²Clinic for Internal Medicine IV, University Hospital Jena, Jena, Germany

,

Tony Bruns

³Department of Medicine III, Aachen University Hospital, Aachen, Germany

,

Paul Horn

⁴Centre for Liver and Gastrointestinal Research, Institute of Immunology and Immunotherapy, University of Birmingham, Birmingham, UK

,

Marcin Krawczyk

⁵Liver and Internal Medicine Unit, Medical University of Warsaw, Warszawa, Poland; Department of Medicine II, Saarland University Medical Center, Saarland University, Homburg, Germany

,

Frank Lammert

⁶Department of Medicine II, Saarland University Medical Center, Saarland University, Homburg, Germany; Hannover Health Science Campus, Hannover Medical School (MHH), Hannover, Germany

,

MatthiasChristian Reichert

¹Department of Medicine II, Saarland University Medical Center, Saarland University, Homburg, Germany

› Author Affiliations

Abstract

Full Text

Background & Aim Since decompensation of cirrhosis significantly increases patients mortality, the prevention and early treatment is paramount. We applied machine learning techniques to identify parameters predicting decompensation.

Methods Using Python, Keras, and Scikit-Learn, several machine learning techniques including Random Forests, Neural Networks and Support Vector Machines (SVM) were trained and tested with 85:15 split on the INCA trial database containing 1,415 patients with cirrhosis from three German university hospitals. In addition to laboratory values and anamnestic data, genetic data including NOD2 genotypes were analysed. Permutation features importance (PFI) as model inspecting technique evaluated the impact of features on the prediction of decompensation.

Results At the index date, 313 patients were always compensated, 354 patients were decompensated before, and 748 were currently decompensated. 825 patients (46.5% decompensated) attended follow up. SVM showed the best performance in predicting decompensation, achieving an accuracy of 84.1% for the training- and 77.7% for the test data set (retrospective assessment) and 78.4% respectively 73.8% (prospective assessment). PFI revealed baseline levels of albumin, bilirubin and minimum serum sodium concentration were highest ranked to assess former decompensation. Maximum level of bilirubin and baseline levels of sodium and albumin were highest ranked for prospective data. In addition to parameters of established scores including MELD and Child-Pugh, NOD2 genotype and parameters related to infections were highly ranked.

Conclusions Among various machine learning models, the highest accuracy to predict decompensation was found for SVM. In addition to classical laboratory parameters, genetic factors and infections were critical parameters for individual predictions.