Salivary Metabolites are Promising Non-Invasive Biomarkers of Hepatocellular Carcinoma and Chronic Liver Disease

Abstract

Background: Hepatocellular carcinoma (HCC) is a leading causes of cancer mortality worldwide. Improved tools are needed for detecting HCC so that treatment can begin as early as possible. Current diagnostic approaches and existing biomarkers, such as alpha-fetoprotein (AFP) lack sensitivity, resulting in too many false negative diagnoses. Machine-learning may be able to identify combinations of biomarkers that provide more robust predictions and improve sensitivity for detecting HCC. We sought to evaluate whether metabolites in patient saliva could distinguish those with HCC, cirrhosis, and those with no documented liver disease.

Methods and results: We tested 125 salivary metabolites from 110 individuals (43 healthy, 37 HCC, 30 cirrhosis) and identified 4 metabolites that displayed significantly different abundance between groups (FDR P <.2). We also developed four tree-based, machine-learning models, optimized to include different numbers of metabolites, that were trained using cross-validation on 99 patients and validated on a withheld test set of 11 patients. A model using 12 metabolites -octadecanol, acetophenone, lauric acid, 1-monopalmitin, dodecanol, salicylaldehyde, glycyl-proline, 1-monostearin, creatinine, glutamine, serine and 4-hydroxybutyric acid- had a cross-validated sensitivity of 84.8%, specificity of 92.4% and correctly classified 90% of the HCC patients in the test cohort. This model outperformed previously reported sensitivities and specificities for AFP (20-100ng/ml) (61%, 86%) and AFP plus ultrasound (62%, 88%).

Conclusions and impact: Metabolites detectable in saliva may represent products of disease pathology or a breakdown in liver function. Notably, combinations of salivary metabolites derived from machine-learning may serve as promising non-invasive biomarkers for the detection of HCC.

Keywords: Metabolomics; cirrhosis; liver cancer; machine learnings; risk factor.

Figure 1:

Workflow diagram for data collection, processing, analysis and generation of predictive models for disease state classification using metabolite relative abundance.

Figure 2:. Eight metabolites differ between patient cohorts.

a) Volcano plot depicting false discovery rate (FDR) and Log₂ Fold Change (Log₂ FC) derived for all metabolites in pair-wise comparisons of disease status, adjusted for differences in age and sex. Metabolites with an FDR P<.2 (dotted red line) are highlighted. b) Box plots displaying distribution of relative abundance stratified by disease status for significantly differing metabolites in at least one comparison (FDR P < .2, adjusted for age and sex).

Figure 3:. Random Forest model predicts disease status from metabolite abundance.

a) An iterative random forest (iRF) approach was used, whereby RF models were generated after iteratively removing the metabolite with the lowest mean Gini score within a leave-one-out cross-validation (LOOCV) framework. The range (min, mean, max) of OOB error across the models is displayed. The model including 125 metabolites is shown in red (RF125), the model including 12 metabolites is shown in blue (iRF12) and the model including 4 metabolites is shown in red (iRF4). b) The range of Gini scores (minimum, mean, maximum) across all metabolites in model RF125. Red coloring indicates the selected metabolites for the iRF models. c) The range of Gini scores of metabolites included in the iRF8. d) The range of Gini scores of metabolites included in iRF4.

Figure 4:. Classification of disease status predicted by decision tree model.

a) A decision tree model based on selected metabolites from the iterative random forest (iRF12) approach optimized with a classification accuracy of 86%. Colored squares indicate the disease status of each individual by disease status at each branch of the decision tree. b) Comparison of accuracy metrics from RF with all metabolites (RF125), iRFs with selected metabolites (iRF12, iRF4), and the decision tree models (DT) using leave-one-out cross-validation.