Development of a Plasma Screening Panel for Pediatric Nonalcoholic Fatty Liver Disease Using Metabolomics

Abstract

Nonalcoholic fatty liver disease (NAFLD) is the most common chronic liver disease in children, but diagnosis is challenging due to limited availability of noninvasive biomarkers. Machine learning applied to high‐resolution metabolomics and clinical phenotype data offers a novel framework for developing a NAFLD screening panel in youth. Here, untargeted metabolomics by liquid chromatography–mass spectrometry was performed on plasma samples from a combined cross‐sectional sample of children and adolescents ages 2‐25 years old with NAFLD (n = 222) and without NAFLD (n = 337), confirmed by liver biopsy or magnetic resonance imaging. Anthropometrics, blood lipids, liver enzymes, and glucose and insulin metabolism were also assessed. A machine learning approach was applied to the metabolomics and clinical phenotype data sets, which were split into training and test sets, and included dimension reduction, feature selection, and classification model development. The selected metabolite features were the amino acids serine, leucine/isoleucine, and tryptophan; three putatively annotated compounds (dihydrothymine and two phospholipids); and two unknowns. The selected clinical phenotype variables were waist circumference, whole‐body insulin sensitivity index (WBISI) based on the oral glucose tolerance test, and blood triglycerides. The highest performing classification model was random forest, which had an area under the receiver operating characteristic curve (AUROC) of 0.94, sensitivity of 73%, and specificity of 97% for detecting NAFLD cases. A second classification model was developed using the homeostasis model assessment of insulin resistance substituted for the WBISI. Similarly, the highest performing classification model was random forest, which had an AUROC of 0.92, sensitivity of 73%, and specificity of 94%. Conclusion: The identified screening panel consisting of both metabolomics and clinical features has promising potential for screening for NAFLD in youth. Further development of this panel and independent validation testing in other cohorts are warranted.

Metabolomic and Lipidomic Biomarkers for Premalignant Liver Disease Diagnosis and Therapy

“…These authors generated a model using random forests machine learning with a sensitivity of 73% and specificity of 97% for detecting NAFLD. Random forests was applied to a combination of metabolite and clinical data, such as waist circumference, whole-body insulin sensitivity index (based on an oral glucose tolerance test) and blood triglyceride level [217].…”

Perspectives on youth‐onset nonalcoholic fatty liver disease

“…With the addition of key clinical variables into the panel, which were also selected using machine learning, the specificity increased to 97%. 99 While panels such as this one, as well as the other biomarkers describe above, require further validation, combination panels that incorporate established clinical assessments with novel biomarkers of disease have promise for improving the disease screening, diagnosis and monitoring in the future.…”

Plasma lipidomics identifies a signature of NAFLD in children that couples with cardiometabolic outcomes in adults

“…We also found higher levels of several lyso-PCs in NASH, similar to the findings by Puri et al (in the livers of adults with NASH) 10 . In addition, lyso-PC(18:1) was one of the top species identified in a separate study that differentiated controls from children with NAFLD 16 . The lyso-PCs identified in the present study (LPC(16:0, 18:0)) are consistent with the activity of phospholipase A2 (PLA2) on PCs 28 , therefore increased PLA2 activity might account for these observations.…”

“…A wide range of associations have been identified in previous metabolite (or lipid) profiling studies in children with NAFLD. Several have found higher levels of (branched-chain) amino acids 16,17,[46][47][48][49][50] . There is strong evidence that levels of circulating amino acids, particularly branched chain amino acids, are highly correlated to (and even causal of) insulin resistance 51,52 .…”

“…This work has identified perturbation of pathways related to hepatic de novo lipogenesis, desaturase activity, and phospholipid metabolism. To date, lipidomic studies in children have focused on species that differentiate NAFLD patients from healthy controls 16,17 .…”