Distinct Subtypes of Hepatorenal Syndrome and Associated Outcomes as Identified by Machine Learning Consensus Clustering

Abstract

Background: The utilization of multi-dimensional patient data to subtype hepatorenal syndrome (HRS) can individualize patient care. Machine learning (ML) consensus clustering may identify HRS subgroups with unique clinical profiles. In this study, we aim to identify clinically meaningful clusters of hospitalized patients for HRS using an unsupervised ML clustering approach.

Methods: Consensus clustering analysis was performed based on patient characteristics in 5564 patients primarily admitted for HRS in the National Inpatient Sample from 2003-2014 to identify clinically distinct HRS subgroups. We applied standardized mean difference to evaluate key subgroup features, and compared in-hospital mortality between assigned clusters.

Results: The algorithm revealed four best distinct HRS subgroups based on patient characteristics. Cluster 1 patients (n = 1617) were older, and more likely to have non-alcoholic fatty liver disease, cardiovascular comorbidities, hypertension, and diabetes. Cluster 2 patients (n = 1577) were younger and more likely to have hepatitis C, and less likely to have acute liver failure. Cluster 3 patients (n = 642) were younger, and more likely to have non-elective admission, acetaminophen overdose, acute liver failure, to develop in-hospital medical complications and organ system failure, and to require supporting therapies, including renal replacement therapy, and mechanical ventilation. Cluster 4 patients (n = 1728) were younger, and more likely to have alcoholic cirrhosis and to smoke. Thirty-three percent of patients died in hospital. In-hospital mortality was higher in cluster 1 (OR 1.53; 95% CI 1.31-1.79) and cluster 3 (OR 7.03; 95% CI 5.73-8.62), compared to cluster 2, while cluster 4 had comparable in-hospital mortality (OR 1.13; 95% CI 0.97-1.32).

Conclusions: Consensus clustering analysis provides the pattern of clinical characteristics and clinically distinct HRS phenotypes with different outcomes.

Keywords: AKI; HRS; acute kidney injury; cirrhosis; clustering; hepatorenal syndrome; machine learning.

Figure 1

Workflow of Consensus Clustering.

Figure 2

(A) CDF plot demonstrating consensus distributions for each cluster (k); (B) Delta area plot representing the relative changes in the area under the CDF curve. (C) Consensus matrix heat map displaying consensus values on a white to blue color scale of each cluster.

Figure 3

(A) The mean cluster consensus score was comparable between a scenario of two or four clusters. (B) Favorable low PACs were demonstrated for two and four clusters.

Figure 4

The standardized differences across four clusters for each baseline parameter. AF: Atrial fibrillation, CAD: Coronary artery disease, CKD: Chronic kidney disease, CHF: Chronic heart failure, DNR: Do not resuscitate, HBV: Hepatitis B virus, HCC: Hepatocellular carcinoma, HCV: Hepatitis C virus, NAFLD: Nonalcoholic fatty liver disease, TIPS: Transjugular intrahepatic portosystemic shunts.