Researchers in Singapore have developed two advanced tools for predicting liver cancer recurrence that use artificial intelligence and machine learning to assess the risk of recurrence after surgery. Developed by teams from the National Cancer Centre Singapore (NCCS), Duke-NUS Medical School, A*STAR, and Singapore General Hospital (SGH), the tools could help doctors personalise treatment and improve long-term patient outcomes.
The first breakthrough comes from the PLANet liver cancer study, published in the journal Gut. The machine-learning model combines genetic and clinical data to predict recurrence in patients with hepatocellular carcinoma (HCC), the most common type of liver cancer. The tool outperformed the widely used TNM staging system, which primarily assesses tumour size and spread. Researchers also identified two distinct biological pathways through which liver cancer can recur, potentially enabling more targeted follow-up care and future clinical trials.
The second innovation is the TIMES score liver cancer AI system, published as a cover feature in Nature. Developed by scientists from A*STAR’s Institute of Molecular and Cell Biology (IMCB) and Singapore General Hospital, the AI-powered tool analyses the spatial arrangement of natural killer (NK) immune cells alongside five key genes in tumour tissue. It predicts liver cancer recurrence with approximately 82% accuracy, outperforming existing staging methods.
Researchers validated the TIMES score liver cancer AI using samples from 231 patients across five hospitals. The platform is now available through a free research portal, while work continues to integrate both tools into routine clinical practice. Together, these innovations could transform how doctors assess recurrence risk, personalise treatment, and improve survival rates for liver cancer patients.
