Physiological network approach to prognosis in cirrhosis: A shifting paradigm

Abstract

Decompensated liver disease is complicated by multi-organ failure and poor prognosis. The prognosis of patients with liver failure often dictates clinical management. Current prognostic models have focused on biomarkers considered as individual isolated units. Network physiology assesses the interactions among multiple physiological systems in health and disease irrespective of anatomical connectivity and defines the influence or dependence of one organ system on another. Indeed, recent applications of network mapping methods to patient data have shown improved prediction of response to therapy or prognosis in cirrhosis. Initially, different physical markers have been used to assess physiological coupling in cirrhosis including heart rate variability, heart rate turbulence, and skin temperature variability measures. Further, the parenclitic network analysis was recently applied showing that organ systems connectivity is impaired in patients with decompensated cirrhosis and can predict mortality in cirrhosis independent of current prognostic models while also providing valuable insights into the associated pathological pathways. Moreover, network mapping also predicts response to intravenous albumin in patients hospitalized with decompensated cirrhosis. Thus, this review highlights the importance of evaluating decompensated cirrhosis through the network physiologic prism. It emphasizes the limitations of current prognostic models and the values of network physiologic techniques in cirrhosis.

Keywords: cirrhosis; decompensation; liver failure; network physiology; prognosis; systems connectivity.

FIGURE 1

The gut–liver–brain axis is closely connected via diverse pathways and regulates the activities of each other. Image created using Biorender.

FIGURE 2

The decompensation stage of cirrhosis is heralded by extrahepatic organ involvement affecting various organ systems including the circulatory system (cirrhotic cardiomyopathy), the nervous system (hepatic encephalopathy and dysregulated autonomic cardiac regulation), the kidney (hepatorenal syndrome), the respiratory system (hepatopulmonary syndrome), digestive system (intestinal injury and increased permeability of the intestinal wall), blood coagulation, and immune system. Also, fluid buildup in the peritoneal cavity (ascites) may result from increased portal tension. Image created using Biorender.

FIGURE 3

Correlation network map of compensated (left panel) and decompensated (right panel) cirrhosis. Each link shows a statistically significant correlation between the two biomarkers. Alb, serum albumin; Bili, total bilirubin; Cre; serum creatinine; Hb, hemoglobin; HE, hepatic encephalopathy; Na, serum sodium; NH₄, serum ammonia; PT, prothrombin time. There is more correlation between biomarkers in patients with compensated cirrhosis. Most of the correlation is lost in patients with decompensated cirrhosis. Data were extracted from 106 patients with cirrhosis referred to the University Hospital of Padova (Courtesy of Prof. Sara Montagnese and colleagues) as described in (Zhang et al., 2022). A Bonferroni‐corrected p‐value was used to identify statistically significant correlations for network mapping.

FIGURE 4

Pathogenesis of reduced heart rate variability (HRV) in cirrhosis is linked with systemic inflammation resulting in disruption to the autonomic (vagal) nervous control of cardiac rhythm. Image created using Biorender.

FIGURE 5

A schematic representation of the Parenclitic network mapping method. Top panel: The network mapping of the reference population (i.e., survivors) utilized correlations between biomarker pairs (e.g., A–B, A–C, B–C, and A–D). Individual reference data points are depicted as blue dots, while black regression lines represent the expected relationship models. Notably, r1, r2, r3 and r4 signify statistically significant correlation coefficients. Middle panel: For individual patient network mapping, a parenclitic approach was adopted. This method assesses how individual patients deviate from the anticipated relationships between variables within the reference population. Essentially, parenclitic deviation indicates the extent to which an individual's biomarker levels differ from the expected model. In this instance, the patient depicted in red exhibits closer alignment with the reference population compared with the green patient in terms of biomarker correlations. Consequently, the green patient displays a higher parenclitic deviation (δ) than the red patient. Lower panel: The parenclitic network map showcases nodes A, B, C, and D, with edges weighted (represented by thickness) based on the extent of deviations from the models for two individual patients (red and green). Thicker edges for the green patient indicate greater parenclitic deviation, reflecting reduced functional connectivity between biomarkers. Conversely, the red patient displays lesser parenclitic deviation, indicating a closer alignment with the reference model and heightened functional connectivity between biomarkers.

FIGURE 6

According to the analysis of organ system connectivity using a parenclitic network, patients with lower network disconnection in the inflammatory pathways are more likely to be armed by increased albumin infusion compared with patients with higher inflammatory system isolation for which infused albumin did not result in a significant difference in mortality (see Oyelade et al. , for more). Image created using Biorender.