THURSDAY, April 2, 2026 (HealthDay News) -- A machine learning model can predict hepatocellular carcinoma (HCC) risk using routinely available data, according to a study published online March 26 in Cancer Discovery.
Jan Clusmann, M.D., from the University Hospital RWTH Aachen in Germany, and colleagues used prospectively collected multimodal data from more than 900,000 individuals with 983 cases of HCC across the U.K. Biobank study (development cohort) and the All of Us Research Program (external testing cohort) to develop an interpretable machine learning framework for HCC risk stratification. Individual and cumulative contributions of data modalities, including demographics, lifestyle, health records, blood, genomics, and metabolomics, were assessed.
The researchers found that on internal and external test sets, the final, random-forest-based models significantly outperformed all publicly available risk scores. Robustness was demonstrated across ethnic subgroups, providing comprehensive interpretability.
"Our study highlights the potential of a simple, easily utilized machine learning model to improve risk stratification for HCC using only routinely collected clinical data," co-senior author Carolin V. Schneider, M.D., also from the University Hospital RWTH Aachen, said in a statement. "If validated in additional populations, our model would enable primary care physicians to efficiently identify at-risk patients and refer them to liver cancer screening. This could enable earlier detection and improved outcomes for patients with this aggressive disease."
Several authors disclosed ties to the biopharmaceutical industry.
Abstract/Full Text
