The study addresses one of the most persistent challenges in gastric cancer immunotherapy. Nivolumab can produce long-lasting responses in some patients, but many others gain little benefit despite receiving the same treatment. Gastric cancer is biologically diverse, meaning that two tumours appearing similar under conventional examination may behave very differently once exposed to immune-based therapy. Clinicians therefore need reliable biomarkers that can distinguish patients more likely to respond from those who may require another strategy. The researchers’ model is intended to provide an additional layer of evidence by extracting predictive information directly from tumour morphology.

At present, the best-known clinical marker for selecting patients for some immunotherapy regimens is the programmed death ligand 1, or PD-L1, combined positive score. The CPS estimates the proportion of tumour cells and immune cells within a tissue sample that express PD-L1, a protein capable of suppressing immune activity. A higher score can indicate a greater likelihood of benefit from drugs such as nivolumab, which block the interaction between PD-1 on immune cells and PD-L1 on tumour or immune cells. Yet PD-L1 is not a perfect predictor. Some patients with low or negative scores respond, while some patients with high scores do not. This limitation has encouraged researchers to look for more comprehensive biological signals.

Digital pathology offers a way to examine those signals at a scale that is difficult to achieve manually. In a typical workflow, a glass pathology slide is scanned to create a whole-slide image containing millions or even billions of pixels. Deep-learning algorithms can then evaluate the architecture of the tumour, the arrangement of malignant cells, the density and distribution of immune cells, connective tissue patterns, necrotic regions and other visual features. Many of these characteristics are subtle, spatially complex or too numerous to be consistently integrated during routine assessment. A model can process them collectively and convert the resulting information into a numerical risk score.

The researchers describe a model developed from digital pathology to forecast outcomes among patients with gastric carcinoma treated with nivolumab. Rather than depending exclusively on a single molecular marker, the system is designed to learn associations between tissue appearance and clinical course. Its output is a risk estimate that could potentially help identify patients more likely to experience a favourable outcome and those at higher risk of limited benefit. The central concept is not that artificial intelligence replaces the pathologist, but that it acts as a computational assistant capable of uncovering patterns hidden within standard diagnostic material.

This distinction is important because digital pathology uses specimens already collected as part of ordinary cancer care. In principle, a predictive model based on routine slides could be easier to implement than a test requiring a new biopsy, specialised sequencing or an expensive laboratory platform. It could also be updated to combine image-derived information with clinical variables, treatment history and established biomarkers such as PD-L1 CPS. Such integration may eventually produce a more nuanced picture of a patient’s likely response than any individual measurement can provide.

However, the promise of an AI-derived score does not automatically make it ready for clinical decisions. Deep-learning systems can learn unwanted features from the data used to train them, including differences in staining protocols, scanner hardware, hospital workflows or patient selection. A model that performs well in one institution may lose accuracy when applied to slides produced elsewhere. Researchers must therefore test these systems across independent cohorts, institutions and populations, while also examining whether the model remains reliable when tissue samples are small, damaged or contain limited tumour material. Transparent reporting and rigorous validation are essential before such tools can influence treatment choices.

The study is particularly significant because nivolumab outcomes are difficult to predict using conventional clinical information alone. Immunotherapy depends on an interaction between the cancer and the patient’s immune system, and that interaction may be reflected in the organisation of cells within the tumour microenvironment. A slide can reveal not only whether immune cells are present, but also where they are located and how they relate to malignant cells. Deep learning may be able to quantify these spatial relationships, potentially identifying an “immune context” linked to treatment sensitivity. The resulting score could complement PD-L1 testing rather than compete with it.

If validated in future studies, the model could support a more precise form of treatment planning for gastric cancer. Patients predicted to have a higher probability of benefit might proceed with nivolumab-based therapy with greater confidence, while those at higher predicted risk could be considered for clinical trials, combination approaches or alternative treatments. Such a system could also help researchers design trials by identifying biologically similar patient groups and investigating why some tumours resist immune checkpoint blockade. Nevertheless, the score should be interpreted as a probability, not a verdict. Treatment decisions would still need to account for overall health, tumour stage, previous therapies, toxicity risks and patient preferences.

The work reflects a broader transformation in oncology, in which pathology images are becoming quantitative sources of biological information rather than static illustrations attached to a diagnosis. By applying deep learning to routine tissue, the researchers aim to move gastric cancer care closer to predictive medicine, where the question is not simply what a tumour looks like, but what it is likely to do when challenged by a specific therapy. The model described by Hong and colleagues does not eliminate the uncertainty surrounding nivolumab, but it offers a potentially scalable route toward reducing it. Its ultimate value will depend on independent validation, clinical integration and proof that the predictions improve outcomes for real patients.

Subject of Research: Deep learning and digital pathology for predicting nivolumab outcomes in gastric carcinoma

Article Title: A deep learning-derived risk score model from digital pathology to forecast nivolumab outcomes in gastric carcinoma

Article References: Hong, Y., Hwang, I., Kim, MJ. et al. A deep learning-derived risk score model from digital pathology to forecast nivolumab outcomes in gastric carcinoma. Br J Cancer (2026). https://doi.org/10.1038/s41416-026-03590-z

Image Credits: AI Generated

DOI: 10.1038/s41416-026-03590-z

Keywords: gastric cancer, gastric carcinoma, nivolumab, immunotherapy, PD-L1, combined positive score, digital pathology, deep learning, artificial intelligence, biomarkers, precision oncology

Non-small cell lung cancer remains the leading cause of cancer mortality worldwide, largely due to late diagnosis and heterogeneous responses to existing therapies. Immune checkpoint inhibitors, targeting proteins such as PD-1 and CTLA-4, have revolutionized treatment paradigms by reactivating cytotoxic T lymphocytes against tumor cells. However, the variability in patient response poses a formidable obstacle in clinical practice, underscoring the urgent need for predictive biomarkers that can preemptively identify which individuals will benefit from these costly and potentially toxic interventions.

The team’s meticulous investigation harnessed advanced flow cytometry and single-cell RNA sequencing to interrogate the functional and phenotypic landscape of T cells circulating in the peripheral blood of NSCLC patients prior to and during ICI treatment. Their analyses revealed that the abundance and activation states of a specific subset of tumor-reactive T cells correlate strongly with therapeutic outcomes. These CTRTs exhibited distinct surface marker signatures indicating an effector memory phenotype coupled with high expression of exhaustion markers, suggesting a poised but dysfunctional state that ICIs can robustly reinvigorate.

Further molecular dissection highlighted key transcriptional programs governing CTRT activation and exhaustion, driven by complex interplay between chronic antigen stimulation and immunosuppressive tumor microenvironmental signals. Notably, enriched expression of genes such as TOX, NR4A, and PDCD1 delineated CTRTs from other T cell populations, underscoring the nuanced balance between immune exhaustion and reinvigoration potential. This duality appears to shape clinical responses and offers a window into patient stratification based on immune dynamics.

Intriguingly, longitudinal monitoring revealed that patients with a higher baseline proportion of these tumor-reactive, yet partially exhausted T cells were far more likely to experience durable clinical benefit from ICIs. Conversely, patients with low CTRT levels or skewed toward terminally differentiated, non-responsive T cells exhibited poorer outcomes, elucidating a critical mechanistic underpinning for therapeutic resistance. This suggests that the mere presence of T cell infiltration within the tumor is insufficient; rather, precise functional states govern anti-tumor efficacy.

The implications of these findings extend beyond biomarker development. This research incites a paradigm shift in how immunologists and oncologists conceptualize T cell dynamics in cancer immunotherapy. It challenges the binary classification of T cells as simply “active” or “exhausted” and prompts a more sophisticated appreciation of phenotypic plasticity within tumor-reactive T cells. Consequently, it opens avenues for combinatorial approaches aimed at modulating these cellular states to heighten ICI responsiveness.

Importantly, the study also highlights the practicality of liquid biopsy approaches leveraging peripheral blood samples to monitor tumor-specific immune activity without invasive tissue biopsies. This noninvasive snapshot of systemic antitumor immunity may enable real-time treatment monitoring and early intervention strategies to enhance patient survival. It heralds a transformative clinical tool that could democratize precision oncology by providing accessible and dynamic biomarkers.

In addition to predicting outcomes, the researchers posit that characterizing CTRTs could inform the design of personalized immunotherapeutic modalities. For instance, adoptive cell transfer therapies might be optimized by selectively expanding tumor-reactive T cells with favorable phenotypic profiles identified through this approach. Moreover, co-targeting pathways implicated in exhaustion and activation could recalibrate the immune response towards a more effective and sustained anti-tumor attack.

Detailed mechanistic explorations into the signaling pathways modulating CTRT fate uncovered roles for metabolic regulators and epigenetic modifiers that tune T cell exhaustion thresholds. These insights align with emerging evidence that metabolic reprogramming is indispensable for T cell function in tumors, suggesting potential adjunct targets to synergize with checkpoint blockade. Exploration of these pathways could yield novel pharmacological agents enhancing immune competence.

The rigorous clinical correlations presented in this paper were bolstered by extensive cohorts spanning multiple NSCLC stages and treatment histories, enhancing the robustness and generalizability of the conclusions. This comprehensive framework integrates immunophenotyping and transcriptomics with patient outcome data, exemplifying a model for future translational immuno-oncology research striving to bridge basic science with real-world clinical impact.

While the study advances our understanding substantially, the authors acknowledge the complexity inherent in tumor-immune interactions and propose future avenues for refining predictive models by incorporating additional immune subsets, tumor mutational burden, and microbiome influences. Multimodal data integration coupled with machine learning techniques may further enhance predictive precision, ultimately facilitating truly individualized immunotherapy.

In conclusion, the identification of circulating tumor-reactive T cell phenotypes as predictors of immune checkpoint inhibitor response delineates a critical biomarker axis with profound clinical relevance. This work represents a milestone in NSCLC immunotherapy, offering a beacon of hope for patients and clinicians grappling with therapeutic uncertainty. By illuminating the subtle immunological intricacies underlying treatment success, this study equips the medical community with vital tools to tailor cancer immunotherapy and improve patient survival in a field marked by remarkable yet variable progress.

As immune-oncology continues to evolve at a rapid pace, integrating these novel biomarkers into clinical workflows promises to enhance the precision and efficacy of therapeutic interventions. The pioneering efforts of Ito, Iida, Hirano, and their team underscore the indispensable value of deep immunophenotyping in conquering cancer’s adaptive resilience, heralding a new era of personalized medicine where immune profiling guides treatment decisions. Their findings, published in the prestigious journal Nature Communications, are likely to catalyze major shifts in research and clinical practice, shining a spotlight on the power of the immune system in combating lethal malignancies.

Subject of Research: The immunophenotypic characterization of circulating tumor-reactive T cells as a predictive biomarker for immune checkpoint inhibitor response in non-small cell lung cancer.

Article Title: Phenotype of circulating tumor-reactive T cells predicts immune checkpoint inhibitor response in non-small cell lung cancer.

Article References:
Ito, K., Iida, K., Hirano, T. et al. Phenotype of circulating tumor-reactive T cells predicts immune checkpoint inhibitor response in non-small cell lung cancer. Nat Commun (2026). https://doi.org/10.1038/s41467-026-69680-x

Image Credits: AI Generated