The approach addresses a central challenge in modern medicine: patients generate large amounts of clinically important data, but those data are frequently stored in separate systems and interpreted independently. A CT scan may reveal the physical structure of a tumour, while genomic testing may indicate the molecular pathways driving its growth and clinical notes may document symptoms, treatment history and adverse reactions. Conventional artificial intelligence tools often analyse only one of these sources, limiting their ability to capture the biological complexity of cancer. PolyU’s system instead uses multimodal data integration, allowing algorithms to examine relationships among imaging features, biomarkers, genomic profiles and treatment outcomes.

At the centre of the platform is a patient-centric “digital twin”—a computational model that is updated as new information becomes available. In principle, this model can reflect changes in disease status, laboratory measurements, symptoms and other clinically relevant signals. Its purpose is not simply to archive information, but to support predictive analysis. When a patient’s condition changes, the system can help healthcare professionals assess possible future trajectories and compare the potential effects of alternative treatment plans. Such simulations could be particularly valuable in cancer and critical care, where disease progression may be rapid, therapeutic options may carry serious risks and decisions often require input from multiple medical specialties.

The platform includes tools for healthcare professionals as well as a mobile application for patients. Doctors can use the clinical interface to assemble a more comprehensive view of a patient’s history and to support diagnosis, monitoring and treatment assessment. The system is also intended to facilitate multidisciplinary consultations and referrals by making relevant information easier to review across clinical teams. Through the patient-facing application, individuals can upload medical records, record daily symptoms and follow changes in their health status. This design aims to shift patients from passive recipients of care toward active participants in managing their conditions, while giving clinicians access to a more continuous stream of patient-reported information.

Data exchange is supported by an encrypted Deep Feature QR code, which the team says can help transfer medical information securely across clinics, hospitals and devices. The technology is intended to improve interoperability without abandoning privacy protections, a critical requirement for any system handling genomic and clinical data. However, secure transmission is only one part of responsible medical AI. Systems used in healthcare must also address data quality, consent, cybersecurity, algorithmic bias and the interpretability of predictions. PolyU’s platform is being developed as a decision-support tool rather than a replacement for clinical judgment, with healthcare professionals remaining responsible for interpreting results in the context of each patient’s circumstances.

To demonstrate the system’s potential in oncology, the researchers introduced a clinical, data-driven, multiscale framework for predicting responses to immunotherapy in people with non-small cell lung cancer (NSCLC). The framework, called the Visual-Global Relation Fusion Network, or ViGNet, is designed for digital pathology and combines histopathological image features with clinical information. Its inputs include gene-expression profiles and cancer-related text, allowing the model to connect microscopic tissue patterns with molecular and clinical factors associated with treatment response. This is technically important because immunotherapy outcomes can depend on interactions between tumour biology, the surrounding immune environment and patient-specific clinical characteristics.

ViGNet uses a multiscale visual encoder to examine pathology images at different levels of detail. At a fine scale, the model can identify cellular and tissue-level patterns; at broader scales, it can assess the organisation of tumour regions and their surrounding microenvironment. A separate gene-driven encoder processes molecular information, while the fusion architecture seeks to establish relationships between visual and genomic representations. By combining these data streams, the model is intended to identify features that may be difficult to recognise when pathology images or molecular profiles are analysed in isolation. The result is a prediction framework aimed at distinguishing patients more likely or less likely to benefit from immunotherapy.

In qualitative and quantitative evaluations, the researchers reported that ViGNet outperformed baseline approaches in response classification, achieving a reported discrimination performance of 82.55% in predicting immunotherapy response. The result suggests that multimodal integration may improve the ability of machine-learning systems to extract clinically relevant signals from complex cancer datasets. At the same time, a performance figure alone does not establish that a model is ready for routine clinical use. Independent validation across hospitals, patient populations and imaging platforms will be necessary, along with prospective studies examining whether AI-supported predictions actually improve treatment decisions and patient outcomes. The reliability of such systems also depends on the quality and representativeness of the data used to train them.

Prof. Lawrence Chan, associate professor in PolyU’s Department of Health Technology and Informatics and leader of the research team, described the AI Virtual Patient Simulation System as a platform combining diagnosis, monitoring and treatment assessment. According to Chan, the system may help identify subtle pathological relationships across multimodal datasets and act as a monitoring “sentinel” by alerting care teams when biomarkers or symptoms become abnormal. Earlier recognition of clinically significant changes could help shorten assessment times and support more precise treatment planning, although the practical value of these alerts will depend on careful clinical validation and integration into existing workflows.

The project was recently showcased at Mobile World Congress 2026 in Barcelona, where it was shortlisted as a finalist for the 2026 Global Mobile Awards in the category of Best Mobile Innovation for Connected Health and Wellbeing. PolyU reports that the work has received support from its Micro Fund and Seed Fund, as well as the Greater Bay Area Innovation and Entrepreneurship Incubation Programme. The project has also been conditionally accepted into the Hong Kong Science and Technology Park’s Incubation Programme and is moving toward commercialisation and industrialisation. If clinical deployment expands, the resulting real-world data could support drug development, clinical trials and treatment optimisation. The research team’s ViGNet study has been published in Medical Image Analysis, adding a peer-reviewed foundation to a broader effort to make personalised, continuously updated cancer intelligence part of future healthcare.

Subject of Research: Artificial intelligence, digital twins, multimodal medical data integration, digital pathology and personalised cancer treatment

Article Title: ViGNet: A clinical data-supported deep learning approach for NSCLC immunotherapy response prediction in digital pathology

Web References: https://www.sciencedirect.com/science/article/pii/S1361841526002239

References: Medical Image Analysis

Image Credits: PolyU

Keywords

Artificial intelligence, virtual patient, digital twin, cancer, non-small cell lung cancer, immunotherapy, digital pathology, medical imaging, genomics, biomarkers, personalised medicine, machine learning, multimodal data, clinical decision support

Breast cancer remains a leading cause of cancer-related mortality worldwide, with metastatic disease posing significant treatment challenges. Traditional monitoring methods—primarily imaging and clinical assessments—often fall short in capturing tumor heterogeneity and fail to provide real-time insights into treatment efficacy. The recent study, spearheaded by Elliott, Fuentes-Antrás, Main, and colleagues, focuses on leveraging epigenetic modifications detectable in ctDNA, primarily methylation patterns, as biomarkers for dynamic tumor surveillance.

Circulating tumor DNA encompasses fragmented genetic material shed by cancer cells into the bloodstream, serving as a liquid biopsy reflective of the tumor’s molecular landscape. Unlike conventional ctDNA analyses that emphasize mutational profiling, this research pivots towards epigenetic alterations—methylation signatures—encoding robust and stable markers of malignancy that can signal subtle changes in tumor burden and aggressiveness.

The investigators began by meticulously identifying methylation hotspots characteristic of metastatic breast cancer cells. Using high-throughput sequencing techniques coupled with sophisticated bioinformatics pipelines, they delineated a panel of methylation sites uniquely altered in cancerous tissue compared to normal DNA. This methylation signature formed the cornerstone of their ctDNA monitoring assay, crafted to sensitively detect tumor-derived DNA amidst the vast background of cell-free DNA from healthy cells.

One of the pivotal aspects of this methylation-based ctDNA approach is its enhanced sensitivity and specificity, which greatly improves early detection of treatment resistance. The study demonstrated that fluctuations in methylation levels correlated tightly with patient responses to CDK4/6 inhibitors—a class of therapeutics that target cyclin-dependent kinases crucial for cell cycle progression in cancer cells. These inhibitors have transformed the landscape of hormone receptor-positive breast cancer therapy but have been hamstrung by variable response rates and the eventual emergence of resistance.

By longitudinally tracking patients undergoing CDK4/6 inhibitor therapy, the research team observed that increasing ctDNA methylation levels presaged radiographic evidence of disease progression by several weeks to months. This early warning system presents a critical window for clinicians to adjust treatment strategies proactively, thereby potentially delaying or preventing overt clinical deterioration.

Furthermore, the methylation profiles revealed heterogeneity in tumor evolution and clonal dynamics under therapeutic pressure. Subclonal populations exhibiting distinct methylation patterns emerged in some patients, underscoring the plasticity of metastatic cancer and elucidating mechanisms of acquired drug resistance. These insights open avenues for combination treatments that can address not only dominant clones but also emerging resistant lineages.

Technical rigor was paramount throughout the study. The authors employed ultra-sensitive methylation-specific PCR and next-generation sequencing methodologies optimized for minimal DNA input, a necessity given the low abundance of ctDNA in plasma. Rigorous validation with matched tumor biopsies confirmed that the methylation alterations detected in ctDNA faithfully recapitulated the tumor’s epigenetic landscape, affirming the biological relevance of the assay.

Beyond its application in monitoring, methylation-based ctDNA profiling holds promise as a diagnostic and prognostic tool. Early-stage breast cancer patients could potentially benefit from non-invasive screening methods, while methylation signatures might stratify patients according to risk and inform adjuvant therapy choices. The versatility and robustness of methylation marks, which often resist degradation compared to genetic mutations, add a valuable dimension to precision oncology.

Importantly, the study addresses some of the critical limitations plaguing current liquid biopsy technologies. Mutational ctDNA assays can be confounded by clonal hematopoiesis—age-related mutations in blood cells—resulting in false positives. Methylation patterns, being tissue- and tumor-specific, offer a way to circumvent this issue, increasing diagnostic accuracy and patient safety.

The clinical implications of these findings extend to the realm of healthcare economics and patient quality of life. Frequent imaging procedures are costly and expose patients to ionizing radiation. A blood-based methylation ctDNA test could reduce dependence on imaging, enabling more frequent, less invasive monitoring that captures real-time tumor biology. This paradigm shift aligns with patient-centric care models and has the potential to enhance survival outcomes through timely therapeutic interventions.

Looking forward, the integration of methylation-based ctDNA assays with other omics data—such as transcriptomics and proteomics—could forge powerful multi-modal platforms to decode tumor behavior comprehensively. Machine learning algorithms can harness these rich datasets to predict treatment responses and tailor therapies more precisely than current standards allow.

While the current study focuses on metastatic breast cancer, the principles underlying methylation ctDNA monitoring are broadly applicable across cancer types. Similar epigenetic aberrations define many malignancies, suggesting that this technology could be adapted as a universal biomarker platform, transforming oncology diagnostics on a global scale.

In sum, the innovative work by Elliott and colleagues epitomizes the confluence of molecular biology, clinical oncology, and technological ingenuity. It lays a robust foundation for next-generation cancer monitoring tools that not only track but anticipate tumor evolution, enabling clinicians to outsmart cancer’s relentless adaptability.

This research underscores the critical importance of methylation signatures in cancer biology and their transformative potential for personalized medicine. As these findings ripple through the scientific community, they inspire a renewed commitment to integrating liquid biopsy technologies into routine cancer care, marking a pivotal milestone in the quest to defeat metastatic breast cancer.

The methylation-based ctDNA monitoring strategy delineated by the authors represents a beacon of hope for patients and oncologists alike, merging molecular precision with clinical pragmatism. With ongoing validation studies and increasing accessibility of sequencing platforms, this approach could soon become a mainstay in oncology clinics worldwide.

Cancer’s heterogeneity and capacity for resistance have long stymied effective management, but with tools such as methylation ctDNA assays, the tide may well be turning. This promising technique exemplifies how deep molecular insights can yield tangible clinical benefits, bridging the gap between bench research and bedside application.

As the field of liquid biopsies evolves, methylation-based monitoring reinforces the paradigm that cancer treatment must be dynamic, adaptive, and personalized. It invites a future where the molecular whispers of tumors guide patient-specific therapeutic journeys, transforming metastatic breast cancer from a lethal diagnosis to a manageable chronic condition.

Subject of Research: Metastatic breast cancer monitoring using methylation-based circulating tumor DNA analysis during CDK4/6 inhibitor therapy

Article Title: Methylation-based ctDNA monitoring in metastatic breast cancer during CDK4/6 inhibitor therapy

Article References:
Elliott, M.J., Fuentes-Antrás, J., Main, S.C. et al. Methylation-based ctDNA monitoring in metastatic breast cancer during CDK4/6 inhibitor therapy. Nat Commun (2026). https://doi.org/10.1038/s41467-026-73126-9

Image Credits: AI Generated