Characteristics of congenital hepatic fibrosis in a large cohort of patients with autosomal recessive polycystic kidney disease

Abstract

Background & aims: Autosomal recessive polycystic kidney disease (ARPKD), the most common ciliopathy of childhood, is characterized by congenital hepatic fibrosis and progressive cystic degeneration of kidneys. We aimed to describe congenital hepatic fibrosis in patients with ARPKD, confirmed by detection of mutations in PKHD1.

Methods: Patients with ARPKD and congenital hepatic fibrosis were evaluated at the National Institutes of Health from 2003 to 2009. We analyzed clinical, molecular, and imaging data from 73 patients (age, 1-56 years; average, 12.7 ± 13.1 years) with kidney and liver involvement (based on clinical, imaging, or biopsy analyses) and mutations in PKHD1.

Results: Initial symptoms were liver related in 26% of patients, and others presented with kidney disease. One patient underwent liver and kidney transplantation, and 10 others received kidney transplants. Four presented with cholangitis and one with variceal bleeding. Sixty-nine percent of patients had enlarged left lobes on magnetic resonance imaging, 92% had increased liver echogenicity on ultrasonography, and 65% had splenomegaly. Splenomegaly started early in life; 60% of children younger than 5 years had enlarged spleens. Spleen volume had an inverse correlation with platelet count and prothrombin time but not with serum albumin level. Platelet count was the best predictor of spleen volume (area under the curve of 0.88905), and spleen length corrected for patient's height correlated inversely with platelet count (R(2) = 0.42, P < .0001). Spleen volume did not correlate with renal function or type of PKHD1 mutation. Twenty-two of 31 patients who underwent endoscopy were found to have varices. Five had variceal bleeding, and 2 had portosystemic shunts. Forty-percent had Caroli syndrome, and 30% had an isolated dilated common bile duct.

Conclusions: Platelet count is the best predictor of the severity of portal hypertension, which has early onset but is underdiagnosed in patients with ARPKD. Seventy percent of patients with ARPKD have biliary abnormalities. Kidney and liver disease are independent, and variability in severity is not explainable by type of PKHD1 mutation; ClinicalTrials.gov number, NCT00068224.

Figure 1

Schematic representation of fibrocystin/polyductin, the protein encoded by the PKHD1 gene, with positions of the mutations identified in our cohort indicated. Missense mutations are listed above and frameshifting mutations are listed below the bar. Domains of the protein are colorcoded as follows: pink, transmembrane; orange, TMEM2 homology; green, TIG/TIG-like (immunoglobulin-like fold shared by plexins and transcription factors).

Figure 2

Findings on abdominal imaging in patients with ARPKD and CHF. (A) USG showing severely increased echogenicity of the liver. (B) Color Doppler USG showing multiple vessels at the porta hepatis with a patent portal vein (arrow) resembling the cavernomatous transformation. (C) MRI showing enlarged left lobe and multiple intrahepatic biliary cysts as well as splenomegaly. (D) MRI showing enlarged left lobe of the liver extending to the left subdiaphragmatic area. (E)MRI showing large collaterals (arrow) between the spleen and the liver, in addition to splenomegaly and multiple small liver cysts. (F) Anterior coronal MRI section showing patent umbilical vein (arrow).

Figure 3

Artist’s rendering and MRCP images showing the spectrum of biliary abnormalities in ARPKD. (A) Drawing of a normal liver. MRCP is normal except for an enlarged gallbladder. S, stomach. (B) Enlarged extrahepatic CBD and gallbladder. MRCP also shows dilated intrahepatic peripheral ducts. The kidney (K) is enlarged due to diffuse microcystic disease. (C) Fusiform and small cystic dilatations of peripheral and central intrahepatic bile ducts as well as fusiform dilatation of the extrahepatic CBD (arrow) and large gallbladder. (D) Fusiform and macrocystic intrahepatic and extrahepatic dilatations and enlarged gallbladder. All patient livers were abnormally shaped with a disproportionately large left lobe as indicated in the artist’s rendering (B–D).

Figure 4

Serum albumin level and renal glomerular function showed no correlation with severity of PH, whereas PT and platelet count showed significant correlation with PH. (A) Serum albumin level did not decrease with worsening PH assessed by spleen volume (y = 4.2515x^−0.016, R² = 0.0164, P = .6386). (B) Platelet count displayed a negative correlation with spleen volume (y = 4903x^−0.593, R² = 0.6487, P < .0001). (C) PT increased with worsening PH measured by spleen volume (y = 0.0019x + 12.842, R² = 0.51, P < .0001). (D) Renal GFR did not show a good correlation with severity of PH based on spleen volume, although there was a trend (y = 14.205x^0.3025, R² = 0.1021, P = .0225).

Figure 5

(A) SL/H ratio plotted against age. The black line indicates the upper limit of normal range, and the red line is the mean in healthy individuals. Patients whose SL/H ratio was greater than the upper limit of normal were classified as having splenomegaly. (B) SL/H ratio correlated inversely with platelet count (R² = 0.42, P < .0001). (C) SL/H ratios of patients with missense mutations and with truncating mutations were similar (P = .73). (D) SL/H ratio correlated with APRI (R² = 0.19, P = .0002).