Using Machine Learning Methods to Predict 28-day Mortality in Patients with Hepatic Encephalopathy

Overview

Journal BMC Gastroenterol

Publisher Biomed Central

Specialty Gastroenterology

Date 2023 Apr 6

PMID 37024814

Authors

Zhe Zhang

Jian Wang

Wei Han

Li Zhao

Affiliations

Soon will be listed here.

Abstract

Background: Hepatic encephalopathy (HE) is associated with marked increases in morbidity and mortality for cirrhosis patients. This study aimed to develop and validate machine learning (ML) models to predict 28-day mortality for patients with HE.

Methods: A retrospective cohort study was conducted in the Medical Information Mart for Intensive Care (MIMIC)-IV database. Patients from MIMIC-IV were randomized into training and validation cohorts in a ratio of 7:3. Training cohort was used for establishing the model while validation cohort was used for validation. The outcome was defined as 28-day mortality. Predictors were identified by recursive feature elimination (RFE) within 24 h of intensive care unit (ICU) admission. The area under the curve (AUC) and calibration curve were used to determine the predictive performance of different ML models.

Results: In the MIMIC-IV database, 601 patients were eventually diagnosed with HE. Of these, 112 (18.64%) experienced death within 28 days. Acute physiology score III (APSIII), sepsis related organ failure assessment (SOFA), international normalized ratio (INR), total bilirubin (TBIL), albumin, blood urea nitrogen (BUN), acute kidney injury (AKI) and mechanical ventilation were identified as independent risk factors. Validation set indicated that the artificial neural network (NNET) model had the highest AUC of 0.837 (95% CI:0.774-0.901). Furthermore, in the calibration curve, the NNET model was also well-calibrated (P = 0.323), which means that it can better predict the 28-day mortality in HE patients. Additionally, the performance of the NNET is superior to existing scores, including Model for End-Stage Liver Disease (MELD) and Model for End-Stage Liver Disease-Sodium (MELD-Na).

Conclusions: In this study, the NNET model demonstrated better discrimination in predicting 28-day mortality as compared to other models. This developed model could potentially improve the early detection of HE with high mortality, subsequently improving clinical outcomes in these patients with HE, but further external prospective validation is still required.

Citing Articles

AI in Hepatology: Revolutionizing the Diagnosis and Management of Liver Disease.

Malik S, Das R, Thongtan T, Thompson K, Dbouk N J Clin Med. 2025; 13(24.

PMID: 39768756 PMC: 11678868. DOI: 10.3390/jcm13247833.

Hepatic encephalopathy post-TIPS: Current status and prospects in predictive assessment.

Xu X, Yang Y, Tan X, Zhang Z, Wang B, Yang X Comput Struct Biotechnol J. 2024; 24:493-506.

PMID: 39076168 PMC: 11284497. DOI: 10.1016/j.csbj.2024.07.008.

The evolution and revolution of artificial intelligence in hepatology: From current applications to future paradigms.

Simsek C Hepatol Forum. 2024; 5(3):97-99.

PMID: 39006141 PMC: 11237248. DOI: 10.14744/hf.2024.2024.ed0001.

References

Labenz C, Toenges G, Huber Y, Nagel M, Marquardt J, Schattenberg J . Development and Validation of a Prognostic Score to Predict Covert Hepatic Encephalopathy in Patients With Cirrhosis. Am J Gastroenterol. 2019; 114(5):764-770. DOI: 10.14309/ajg.0000000000000121. View

Bassi T, Rohrs E, Reynolds S . Systematic review of cognitive impairment and brain insult after mechanical ventilation. Crit Care. 2021; 25(1):99. PMC: 7945325. DOI: 10.1186/s13054-021-03521-9. View

de Jongh F, Janssen H, de Man R, Hop W, Schalm S, van Blankenstein M . Survival and prognostic indicators in hepatitis B surface antigen-positive cirrhosis of the liver. Gastroenterology. 1992; 103(5):1630-5. DOI: 10.1016/0016-5085(92)91188-a. View

Guevara M, Baccaro M, Rios J, Martin-Llahi M, Uriz J, Del Arbol L . Risk factors for hepatic encephalopathy in patients with cirrhosis and refractory ascites: relevance of serum sodium concentration. Liver Int. 2010; 30(8):1137-42. DOI: 10.1111/j.1478-3231.2010.02293.x. View

Lin R, Lee F, Lee S, Tsai Y, Lin H, Lu R . Endotoxemia in patients with chronic liver diseases: relationship to severity of liver diseases, presence of esophageal varices, and hyperdynamic circulation. J Hepatol. 1995; 22(2):165-72. DOI: 10.1016/0168-8278(95)80424-2. View

Wan S, Nie Y, Zhang Y, Liu C, Zhu X . Assessing the Prognostic Performance of the Child-Pugh, Model for End-Stage Liver Disease, and Albumin-Bilirubin Scores in Patients with Decompensated Cirrhosis: A Large Asian Cohort from Gastroenterology Department. Dis Markers. 2020; 2020:5193028. PMC: 7048909. DOI: 10.1155/2020/5193028. View

Zhang Z, Ho K, Hong Y . Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care. Crit Care. 2019; 23(1):112. PMC: 6454725. DOI: 10.1186/s13054-019-2411-z. View

Biggins S, Kim W, Terrault N, Saab S, Balan V, Schiano T . Evidence-based incorporation of serum sodium concentration into MELD. Gastroenterology. 2006; 130(6):1652-60. DOI: 10.1053/j.gastro.2006.02.010. View

Bai Z, Guo X, Tacke F, Li Y, Li H, Qi X . Association of serum albumin level with incidence and mortality of overt hepatic encephalopathy in cirrhosis during hospitalization. Therap Adv Gastroenterol. 2019; 12:1756284819881302. PMC: 6783662. DOI: 10.1177/1756284819881302. View

10.

Wasmuth H, Kunz D, Yagmur E, Timmer-Stranghoner A, Vidacek D, Siewert E . Patients with acute on chronic liver failure display "sepsis-like" immune paralysis. J Hepatol. 2005; 42(2):195-201. DOI: 10.1016/j.jhep.2004.10.019. View

11.

Guevara M, Baccaro M, Gomez-Anson B, Frisoni G, Testa C, Torre A . Cerebral magnetic resonance imaging reveals marked abnormalities of brain tissue density in patients with cirrhosis without overt hepatic encephalopathy. J Hepatol. 2010; 55(3):564-573. DOI: 10.1016/j.jhep.2010.12.008. View

12.

Cordoba J, Ventura-Cots M, Simon-Talero M, Amoros A, Pavesi M, Vilstrup H . Characteristics, risk factors, and mortality of cirrhotic patients hospitalized for hepatic encephalopathy with and without acute-on-chronic liver failure (ACLF). J Hepatol. 2013; 60(2):275-81. DOI: 10.1016/j.jhep.2013.10.004. View

13.

Tapper E, Parikh N, Sengupta N, Mellinger J, Ratz D, Lok A . A risk score to predict the development of hepatic encephalopathy in a population-based cohort of patients with cirrhosis. Hepatology. 2017; 68(4):1498-1507. DOI: 10.1002/hep.29628. View

14.

. Hepatic encephalopathy in chronic liver disease: 2014 practice guideline by the European Association for the Study of the Liver and the American Association for the Study of Liver Diseases. J Hepatol. 2014; 61(3):642-59. DOI: 10.1016/j.jhep.2014.05.042. View

15.

Durand F, Buyse S, Francoz C, Laouenan C, Bruno O, Belghiti J . Prognostic value of muscle atrophy in cirrhosis using psoas muscle thickness on computed tomography. J Hepatol. 2014; 60(6):1151-7. DOI: 10.1016/j.jhep.2014.02.026. View

16.

Udayakumar N, Subramaniam K, Umashankar L, Verghese J, Jayanthi V . Predictors of mortality in hepatic encephalopathy in acute and chronic liver disease: a preliminary observation. J Clin Gastroenterol. 2007; 41(10):922-6. DOI: 10.1097/01.mcg.0000225639.45157.ee. View

17.

Patidar K, Thacker L, Wade J, Sterling R, Sanyal A, Siddiqui M . Covert hepatic encephalopathy is independently associated with poor survival and increased risk of hospitalization. Am J Gastroenterol. 2014; 109(11):1757-63. PMC: 4321782. DOI: 10.1038/ajg.2014.264. View

18.

Kamath P, Kim W . The model for end-stage liver disease (MELD). Hepatology. 2007; 45(3):797-805. DOI: 10.1002/hep.21563. View

19.

Nardelli S, Gioia S, Ridola L, Farcomeni A, Merli M, Riggio O . Proton Pump Inhibitors Are Associated With Minimal and Overt Hepatic Encephalopathy and Increased Mortality in Patients With Cirrhosis. Hepatology. 2018; 70(2):640-649. DOI: 10.1002/hep.30304. View

20.

Peng Y, Wei Q, Liu Y, Wu Z, Zhang H, Wu H . Prediction and Risk Factors for Prognosis of Cirrhotic Patients with Hepatic Encephalopathy. Gastroenterol Res Pract. 2021; 2021:5623601. PMC: 8546404. DOI: 10.1155/2021/5623601. View