Novel, high accuracy models for hepatocellular carcinoma prediction based on longitudinal data and cell-free DNA signatures

Background & AimsCurrent hepatocellular carcinoma (HCC) risk scores do not reflect changes in the HCC risk assessment resulting from liver disease progression/regression over time. We aimed to develop and validate two novel prediction models using multivariate longitudinal data, with or without incorporating cell-free DNA (cfDNA) signatures.Methods13,728 patients from two nationwide multicentre prospective observational cohorts with majority of chronic hepatitis B virus (HBV) infection were enrolled. aMAP score, as one of the most promising HCC prediction models, was evaluated for each patient. Low-pass whole genome sequencing was used to derive multi-modal cfDNA fragmentomics features. Longitudinal Discriminant Analysis (LoDA) algorithm was used to model longitudinal profiles of patient biomarkers and estimate HCC development risk.ResultsWe developed and externally validated two novel HCC prediction models having a greater accuracy called aMAP-2 and aMAP-2 Plus scores. The aMAP-2 score, calculated with longitudinal data of aMAP score and α-fetoprotein values during up to 8-year follow-up, performed superbly in the training and external validation cohorts (AUC 0.83 - 0.84). The aMAP-2 score showed further improvement and accurately divided aMAP defined high-risk patients into two groups with 5-year cumulative HCC incidence of 23.4% and 4.1%, respectively (p=0.0065). The aMAP-2 Plus score, which incorporates cfDNA signatures (Nucleosome, Fragment and Motif scores), optimized the performance in predicting HCC development, especially for cirrhotic patients (AUC 0.85 - 0.89). Importantly, the stepwise approach (aMAP -> aMAP-2 -> aMAP-2 Plus) identified 90.0% and 10.0% of cirrhotic patients with annual HCC incidence of 0.8% and 12.5%, respectively (p<0.0001).ConclusionsAMAP-2 and aMAP-2 Plus scores are highly accurate in predicting HCC. The stepwise application of aMAP scores provides an improved enrichment strategy of high-risk HCC patients, which could effectively guide nationwide individualized HCC surveillance.