Singapore team develops new tool that accurately predicts liver cancer recurrence

• Liver cancer often returns after surgery, but doctors currently lack reliable tools to identify which patients face the greatest risk. 
• Singapore researchers have uncovered two distinct ways that hepatocellular carcinoma, the most common type of liver cancer, recurs at the molecular level and have used these insights to develop a new machine-learning prediction tool. 
• Validated across independent patient groups, the tool leverages on both genomics and clinical data and outperformed the commonly used TNM staging system – which assesses disease stage based on tumour burden alone – in predicting recurrence risk and could aid surveillance, treatment decision-making and clinical trials.

Singapore, 3 August 2026 – A Singapore team of clinician-scientists and researchers has developed a new tool that accurately predicts which liver cancer patients are likely to experience a recurrence after surgery. The machine-learning tool combines genomic and clinical information and was found to outperform the commonly used TNM staging system, which is based on tumour burden alone, across independent patient groups.

Researchers from the National Cancer Centre Singapore (NCCS), Duke-NUS Medical School (Duke-NUS) and the A*STAR Genome Institute of Singapore (A*STAR GIS) also uncovered two biologically distinct ways in which hepatocellular carcinoma (HCC), the most common form of primary liver cancer, can recur. The findings could help doctors tailor follow-up care, identify patients most likely to benefit from additional treatment after surgery and design more targeted clinical trials.

The study was conducted through the National Medical Research Council-funded PLANet (Precision Medicine in Liver Cancer across an Asia-Pacific Network) research programme and published in the level-1 journal Gut in July 2026.

Liver cancer often returns after surgery

Liver cancer is the third leading cause of cancer-related death globally and disproportionately affects Asian populations. In Singapore, it is the third most common cause of cancer death in men and the fifth in women,¹ with approximately 72% of global cases occurring in Asia, largely driven by the high prevalence of hepatitis B virus (HBV) infection in the region.² Even in patients with early-stage disease, recurrence rates of HCC remain high after surgical resection. Intrahepatic recurrence - where cancer returns within the liver - accounts for 70-80% of all recurrences, while the remaining cases involve distant metastasis, where the cancer spreads beyond the liver to other parts of the body. Better tools to identify patients at highest risk of recurrence could enable the development of more precise therapies to prevent recurrence after surgery and help match patients to clinical trials most likely to benefit them.

Yet, clinicians currently lack reliable biomarkers to identify which patients are most at risk of recurrence. This makes it difficult to tailor follow-up care, as well as select patients for additional treatment and design clinical trials efficiently.

“Liver cancer frequently returns after surgery, yet we still lack effective therapies to prevent recurrence,” said Professor Pierce Chow, co-senior author of the study and Principal Investigator of the PLANet programme.

“Our findings, and the tool we developed, present a new way to understand liver cancer evolution, as well as an accurate means of identifying patients who will benefit from participation in studies with adjuvant therapies to prevent recurrence. Current practice enrols all post-resection HCC patients into adjuvant clinical trials indiscriminately, without accounting for biological differences, which has yielded largely negative results. Our discovery could change how clinical studies on adjuvant therapies are designed and executed, and provide new hope for patients,” added Professor Chow, who is a Senior Consultant Surgeon, Division of Surgery and Surgical Oncology, Singapore General Hospital and NCCS and a programme director at Duke-NUS Medical School.

Two distinct routes to recurrence

To better understand why HCC returns after surgery, the research team analysed clinical data and conducted comprehensive matched genetic analyses of tumour samples from patients in the PLANet cohort, including recurrent tumour samples from a subset of patients. Of the 106 patients studied, 68 (64.2%) experienced recurrence: 48 within the liver, 11 in other parts of the body, and 9 in both locations.

Two main patterns of recurrence were uncovered:

1. Polyclonal seeding, in which multiple groups of cancer cells spread simultaneously from the original tumour. This was more often associated with recurrence within the liver. Tumours in this group have distinct characteristics that suggest they may respond better to certain immunotherapies. 
2. Monoclonal seeding, in which the recurrence develops from a single clone from the original tumour. This pattern was more commonly associated with later recurrence and cancer spreading beyond the liver to other parts of the body.

“By uncovering two distinct mechanisms of liver cancer recurrence, we have gained new insights into the biological processes that drive disease progression after surgery. Understanding these differences is an important step towards more personalised approaches to risk prediction, and the development of more precise biomarkers and targeted therapies for HCC patients,” said Dr Zhang Ying, co-first author of the study and Senior Scientist at A*STAR GIS.

An accurate prediction tool to identify high-risk patients

Building on these findings, the team developed a new, machine-learning based multi-omics tool that predicts a patient’s risk of liver cancer recurrence after surgery. It combines multiple biological and clinical indicators such as tumour size and genetics, levels of blood markers and cancer stage, while also taking into account a group of 15 genes that were strongly linked to cancer recurrence.

The tool was validated in three independent cohorts, including the publicly available Cancer Genome Atlas Liver Hepatocellular Carcinoma (TCGA) dataset. Successful validation in TCGA, an independent, publicly available cohort of a largely Western population which complements the PLANet programme’s Asia-Pacific population, supports the tool’s reproducibility and broader generalisability across different populations.

The new tool was found to be a much better predictor than the commonly used TNM staging for resected liver cancer which does not take cancer genetics into account, achieving a performance score of 86 per cent, compared with 56-68 per cent for TNM.

“The tool we developed is robust and comprehensively evaluated. It is based on area under the curve (AUC), a widely used and internationally recognised metric for measuring how well a predictive model distinguishes between two groups, and its high score indicates a strong ability to identify which patients are at greater risk of recurrence. With it, we can now determine which patients are most likely to experience recurrence and, by extension, most likely to benefit from specific systemic therapies, ensuring that they are neither overtreated nor undertreated,” said Mr Karthik Sekar, co-first author of the study and Senior Bioinformatics Specialist at NCCS who led the development of the tool.

Looking ahead

"Our study provides valuable insight into disease evolution that can directly improve patient care. It is an example of how multidisciplinary, collaborative expertise can open new pathways to combat a deadly disease. We are gratified that this research will make a real difference in the treatment of HCC which is prevalent in Asian populations," said co-senior author Associate Professor Tam Wai Leong, Deputy Chief Executive Officer (Research) at NCCS and Director of the Cancer Stem Cell and Biology Signature Research Programme at Duke-NUS Medical School.

Building on these findings, the research team is currently using spatial sequencing technologies to identify tumour microenvironment biomarkers that could serve as drug targets to treat HCC. They are also working to further improve the accuracy of the multi-omics tool by incorporating additional data sources such as CT imaging. This could further enhance recurrence prediction and improve targeted surveillance for high-risk patients.

Funding

This research is supported by the Singapore Ministry of Health's National Medical Research Council under its Open Fund-Large Collaborative Grant (MOH-001067, MOH-001090), Open Fund-Large Collaborative Grant (NMRC/OFLCG/003/2018), Clinician Scientist Award – Senior Investigator (NMRC/CSA-SI/0018/2017), and Collaborative Investigator Research Grant (NMRC/CIRG/1454/2016), as well as the National Research Foundation, Singapore under its NRF Investigatorship (NRF-NRFI08-2022) and Competitive Research Programme (CRP23-2019-0072). It is also supported by the Agency for Science, Technology and Research, Singapore, and the Singapore Ministry of Education under its Research Centres of Excellence initiative.

Study citation:

“Clonal diversity underpins distinct modes of recurrence in hepatocellular carcinoma: the PLANet cohort study Zhang Y, Sekar K, et al. Gut 2026. https://doi.org/10.1136/gutjnl-2026-338227

¹National Registry of Diseases Office. (2026). Singapore Cancer Registry Annual Report 2023. Ministry of Health Singapore.

²Chan S, Sun H, Xu Y et al. The Lancet Commission on addressing the global hepatocellular carcinoma burden: comprehensive strategies from prevention to treatment. The Lancet, 2025; 406, 731-778

-END-

For media enquiries, please contact:

Amadea Tan
Corporate Communications
National Cancer Centre Singapore
Email : amadea.tan.sl@nccs.com.sg 

Dharshini Subbiah
Corporate Communications
National Cancer Centre Singapore
Email : dharshini.subbiah@nccs.com.sg 

Dione Chew
Corporate Communications
Agency for Science, Technology and Research (A*STAR)
Email: Dione_Chew@a-star.edu.sg

Benjamin Tan
Communications
Duke-NUS Medical School
Email: ben.zh.tan@duke-nus.edu.sg 

About the National Cancer Centre Singapore (NCCS)

The National Cancer Centre Singapore (NCCS) is a leading national and regional tertiary cancer centre dedicated to advancing cancer care, research and education. With a comprehensive suite of specialties and services, NCCS treats all cancers and offers personalised and multidisciplinary care to ensure that patients receive holistic, compassionate care and support. Advanced and innovative treatments such as proton therapy at the Goh Cheng Liang Proton Therapy Centre, immunotherapy, and cell therapy give patients at NCCS the best treatment outcomes.

Ranked among the top cancer centres in Asia, NCCS is globally recognised for its research expertise, with clinicians and scientists collaborating with local and international partners to conduct cutting-edge clinical and translational research that makes a real impact and offers hope of a cancer-free tomorrow. As an academic healthcare institution, NCCS is committed to nurturing future generations by delivering specialised training to local and overseas oncology healthcare professionals. For more information, please visit www.nccs.com.sg

About A*STAR Genome Institute of Singapore (A*STAR GIS)

The A*STAR Genome Institute of Singapore (A*STAR GIS) is an institute of the Agency for Science, Technology and Research (A*STAR). It has a global vision that seeks to use genomic sciences to achieve extraordinary improvements in human health and public prosperity. Established in 2000 as a centre for genomic discovery, A*STAR GIS pursues the integration of technology, genetics, and biology towards academic, economic and societal impact, with a mission to harness genomic technologies for a better Singapore and world.

Key research areas at the A*STAR GIS include RNA & DNA Technologies, Single Cell & Spatial Technologies, Population Health, Precision Medicine, and AI & Compute. A*STAR GIS’s genomics infrastructure is also utilised to train new scientific talent, to function as a bridge for academic and industrial research, and to explore scientific questions of high impact. For more information about A*STAR GIS, please visit www.a-star.edu.sg/gis.

About Duke-NUS Medical School

Duke-NUS is Singapore’s flagship graduate-entry medical school, established in 2005 with a strategic, government-led partnership between two world-class institutions: Duke University and the National University of Singapore (NUS). Through an innovative curriculum, students at Duke-NUS are nurtured to become multi-faceted ‘Clinicians Plus’ poised to steer the healthcare and biomedical ecosystem in Singapore and beyond. A leader in ground-breaking research and translational innovation, Duke-NUS has gained international renown through its five Signature Research Programmes and ten Centres. The enduring impact of its discoveries is amplified by its successful Academic Medicine partnership with Singapore Health Services (SingHealth), Singapore’s largest healthcare group. This strategic alliance has led to the creation of 15 Academic Clinical Programmes, which harness multi-disciplinary research and education to transform medicine and improve lives.

For more information, please visit www.duke-nus.edu.sg