AI in NSCLC: Promise, Progress, and the Path to Responsible Integration

Lung cancer remains the leading cause of cancer-related mortality worldwide, with non-small cell lung cancer (NSCLC) accounting for approximately 85% of all lung cancers[1]. Despite advances in immunotherapy and targeted therapies, overall survival has historically been low. Late diagnosis remains a major driver of poor outcomes, while treatment resistance, tumor heterogeneity, and immunologically “cold” tumor microenvironments further limit the effectiveness of available therapies.

This landscape is beginning to shift with the introduction of low-dose computed tomography (LDCT) screening in high-risk populations. Large screening trials have demonstrated that detecting lung cancer earlier can drastically improve long-term survival, with 20-year survival rates reaching up to 81% among patients diagnosed with early-stage (stage I) disease[2]. While adoption varies across healthcare systems, LDCT screening programs are increasingly being incorporated into clinical guidelines and national screening initiatives.

As screening becomes more widespread, clinicians are increasingly confronted with a new challenge: interpreting large numbers of imaging studies, characterizing pulmonary nodules, and integrating imaging findings with pathology and molecular data to guide treatment decisions.

In this evolving landscape, AI-driven approaches are beginning to support multiple steps in the NSCLC care pathway, from improving the detection and characterization of lung nodules on imaging to enhancing pathology analysis and enabling more precise risk prediction. As AI becomes increasingly integrated into oncology workflows, balancing innovation with rigorous validation and human oversight will be essential to ensuring that these technologies deliver meaningful clinical benefit.

Smarter Imaging and Earlier Detection

As LDCT screening expands, clinicians are increasingly faced with large volumes of imaging data and pulmonary nodules that must be detected, characterized, and monitored over time. In reality, imaging is almost always the first step in the diagnostic pathway, whether lung cancer is detected through screening, incidental findings, or clinical symptoms, further compounding the volume of imaging data that must be interpreted in clinical practice.

CT, PET-CT, and MRI all play a central role in detecting pulmonary nodules, assessing malignancy risk, and guiding decisions about biopsy and further diagnostic evaluation. AI models trained on large imaging datasets are now demonstrating performance that rivals, and in some cases surpasses, experienced radiologists.[2]

Deep learning systems applied to low-dose CT screening have achieved area-under-the-curve (AUROC) values as high as 0.94 for lung cancer detection. AUROC is a statistical measure of how well a model can distinguish between two outcomes (in this case, whether a lung nodule is malignant or benign), with values ranging from 0.5 (no better than chance) to 1.0 (perfect discrimination). In practical terms, stronger model discrimination translates into fewer missed cancers and fewer unnecessary follow-up imaging studies or invasive diagnostic procedures. Some models reduce false positives – benign nodules incorrectly flagged as suspicious – by approximately 11%, while reducing false negatives by 5% compared with conventional radiologist-led screening workflows.[2]

Beyond detection, AI is also beginning to help estimate an individual’s future risk of developing lung cancer (risk stratification), and support decisions about how closely suspicious findings should be monitored over time (longitudinal monitoring).

One example is the Sybil model, a deep learning system designed to analyze low-dose CT scans from lung cancer screening programs. Unlike conventional approaches that focus only on visible nodules, Sybil evaluates patterns across the entire CT scan to estimate a person’s likelihood of developing lung cancer in the coming years, even when no obvious tumor is present.

Using a single CT scan, the model can predict lung cancer risk one to six years into the future. External validation studies report AUROCs between 0.75 and 0.81, suggesting that AI-based forecasting could help personalize screening intervals by identifying individuals who require closer monitoring while allowing others to safely extend the time between scans.[2]

Taken together, these advances have the potential to transform how imaging is used in lung cancer care. By improving early detection, reducing diagnostic uncertainty, and supporting more personalized screening strategies, AI-assisted imaging may help clinicians identify disease earlier while minimizing unnecessary procedures.

Transforming Pathology

Once a suspicious lesion is identified through imaging, diagnosis relies on tissue analysis. Biopsy samples are examined to determine tumor histology and to perform molecular testing for clinically relevant mutations. Increasingly, AI is being used to assist pathologists in this complex and time-intensive process.[3][2]

Deep learning models applied to digital pathology slides can distinguish between major NSCLC subtypes, including adenocarcinoma and squamous cell carcinoma, with approximately 95 % accuracy, comparable to expert human interpretation. These models are trained on large collections of high-resolution digital scans of entire pathology slides (whole-slide images), allowing them to learn and recognize subtle differences in tumor cell morphology and tissue architecture that characterize different lung cancer subtypes.[3]

Beyond tumor classification, AI models are beginning to predict molecular alterations directly from routine hematoxylin and eosin (H&E) slides, the standard strains used in pathology to visualize cell cultures and tissue architecture under a microscope. Because H&E staining is performed for nearly all biopsy samples, these slides represent one of the most widely available sources of diagnostic information in cancer care.

One example is the EAGLE model, a deep learning system trained to analyze digital H&E pathology slides and identify visual patterns associated with specific genetic mutations. In NSCLC, the model has been used to predict the presence of EGFR mutations, which play an important role in determining eligibility for targeted therapies.

Studies report AUROCs ranging from 0.85 to 0.89 for EGFR mutation prediction. While molecular testing remains the gold standard for confirming these mutations, AI-based approaches may help identify which cases are most likely to harbor EGFR alterations, allowing clinicians to prioritize testing for this biomarker. In real-world evaluations, the implementation of EAGLE has reduced reflex molecular testing by 43% while maintaining high sensitivity, enabling faster results, and lowering diagnostic costs without compromising reliability.[3]

AI has similarly improved the consistency of PD-L1 immunohistochemistry scoring, achieving correlation values of 0.94 compared with pathologists. This improved reproducibility is particularly important because PD-L1 expression plays a critical role in determining eligibility for immunotherapy.[3]

Importantly, these technologies are not intended to replace pathologists. Instead, they function as precision tools that enhance diagnostic consistency, reduce variability, and support more efficient pathology workflows.

Beyond Staging: Risk Stratification and Survival Prediction

Traditional staging in NSCLC relies heavily on the TNM system, which categorizes disease based on tumor size, lymph node involvement, and metastasis. While TNM staging remains essential for clinical decision-making, it does not fully capture biological heterogeneity of lung tumors.

AI-driven models are now integrating imaging, pathology, and molecular data to generate more nuanced predictions of disease progression and survival.

For example, CT-based models that analyze imaging features have achieved AUROCs of approximately 0.70 for predicting survival outcomes, compared with roughly 0.60 for models based only on traditional clinical variables such as stage and patient characteristics. Pathomics models, which extract quantitative features from digital pathology slides, have reported five-year survival prediction AUROCs between 0.64 and 0.85.[4]

One particularly promising development is the use of federated learning, an approach that allows models to be trained across multiple institutions without sharing sensitive patient data. The FedCPI model achieved an AUC of 0.9255 and an accuracy of 89.09 % for predicting early-stage disease progression at one center, outperforming both traditional TNM staging and clinical logistic regression models.[4]

For patients and clinicians alike, improved risk prediction could support more personalized treatment decisions and better informed discussions about prognosis.

Improving Workflows and Efficiency

Beyond diagnostic accuracy, AI is also improving efficiency across oncology workflows.

In radiotherapy planning, AI-assisted segmentation and treatment planning can significantly reduce preparation times for image-guided radiotherapy. In pathology laboratories, AI-assisted screening tools can streamline diagnostic workflows and reduce unnecessary molecular testing, in some cases by as much as 43 %.

Federated learning frameworks further enable hospitals to collaborate on model development without directly exchanging sensitive patient data, improving model generalizability while maintaining patient privacy. These efficiency gains are particularly valuable in busy oncology centers where timely diagnosis and treatment decisions are critical.[5][2]

The Limitations We Cannot Ignore

Despite its promise, AI in NSCLC faces several important challenges.

Data bias remains a major concern. Many models are trained using datasets from single institutions or relatively homogeneous populations. When applied to new patient groups or imaging systems, model performance can decline by 5 to 10 AUROC points due to differences in scanners, patient demographics, or clinical practices.

Explainability also remains an ongoing challenge. Many AI systems operate as “black boxes,” generating predictions without transparent reasoning. Tools such as saliency maps attempt to visualize model decisions, but these methods sometimes highlight irrelevant artifacts rather than biologically meaningful features.

Finally, clinical integration presents practical hurdles. Regulatory approval, workflow compatibility, and clinician trust all influence whether AI tools are adopted in routine practice. Demonstrating consistent value will be essential before widespread implementation becomes feasible.[5][2]

The Path Forward

For AI to deliver equitable and reliable impact in NSCLC care, rigorous validation standards will be essential.

Models must undergo external validation, calibration testing, and decision curve analysis to ensure reliability across diverse clinical settings. Fairness audits are also necessary to ensure that performance remains consistent across patient populations.

Improved explainability methods, including deletion curves and concept-based analyses, may help increase transparency and clinician confidence. Most importantly, prospective clinical studies will be required to demonstrate real-world benefit.

AI is unlikely to replace physicians; but when deployed responsibly, it can augment clinical judgment, reduce diagnostic variability, and support more personalized care at scale.

At Helix BioPharma, we believe that integrating advanced analytics with strong validation frameworks and human expertise is essential to unlocking AI’s potential in lung cancer care. By combining innovation with scientific rigor, the goal is to help advance smarter, safer, and more equitable approaches to NSCLC diagnosis and treatment.

References:

1. https://pmc.ncbi.nlm.nih.gov/articles/PMC10308181/

2. https://pubs.rsna.org/doi/10.1148/radiol.231988

3. Li Y, Chen D, Wu X, Yang W, Chen Y. A narrative review of artificial intelligence-assisted histopathologic diagnosis and decision-making for non-small cell lung cancer: achievements and limitations. J Thorac Dis . 2021;13(12):7006-7020. doi:10.21037/jtd-21-806

4. Huang Z, Feng B, Chen Y, et al. Risk stratification for early-stage NSCLC progression: a federated learning framework with large-small model synergy. Front Oncol . 2025;15:1719433. Published 2025 Dec 16. doi:10.3389/fonc.2025.1719433

5. https://jmai.amegroups.org/article/view/9284/html

Jacek Antas

Chief Executive Officer


Jacek Antas is a shareholder of the Company, has spent more than 25 years in the financial services industry holding various positions in sales and consulting.

Mr. Antas obtained a master’s degree from the Warsaw School of Economics and has served as a board member of various
companies throughout his career.

This will close in 0 seconds

James B. Murphy

Chief Financial Officer


Mr. Murphy is a certified public accountant with over thirty years of experience in finance and operations management. He is currently a consultant with Danforth Advisors LLC (“Danforth”), a leading provider of outsourced strategic and operational specialists across functions in the life sciences industry. While at Danforth, Mr. Murphy has served over fifteen private and publicly held life sciences companies as CFO and CFO Advisor, helping them secure over USD 0.5 billion in financing and successfully execute pivotal asset transactions. Mr. Murphy functions as a consultant to Helix pursuant to a consulting agreement between the Company and Danforth.

This will close in 0 seconds

Thomas Mehrling

Medical Adviser


Thomas Mehrling (PhD in Pharmacology and MD) has over 20 years’ experience in multinational Pharma companies developing novel oncology compounds from preclinical research through to registration. Prior to entering the industry, he spent 13 years as an MD at the University Hospital in Frankfurt, working on preclinical and translational projects. He served as Director of European Oncology at Mundipharma International (2003–2013), building the company’s first European oncology business from the ground up out of Cambridge, UK, and completing the clinical development, registration and launch of two major products in Europe, DepoCyte® and Levact® (Ribomustin® and Treanda®). In 2013, he led the establishment of the Mundipharma Group’s start-up, Mundipharma EDO, developing anti-cancer therapeutics for solid tumours out of Basel, Switzerland.

This will close in 0 seconds

Kim Gaspar

Director Quality Assurance


Kim is the Director of Quality Assurance at Helix BioPharma Corp. An experienced quality assurance professional with expertise in Canadian, US, and EU regulations, she has been involved in all aspects of Phase I/II biopharmaceutical product development over the years, including regulatory submissions, QC laboratory compliance, tech transfer and third-party oversight of CMC activities, clinical QA, and bioanalytical data analysis. Kim joined Helix in 2000, transitioning into QA in 2003. She holds a B.Sc in Biochemistry and a Ph.D in Veterinary Physiological Sciences, both from the University of Saskatchewan.

This will close in 0 seconds

Brenda Lee

Director Clinical Operations


Brenda is the Clinical Operations Director at Helix Biopharma Corp. A clinical research operations professional with 25 years of experience managing clinical trials, ranging from early Phase I to late Phase IIIb/IV studies, she brings experience in clinical study protocol writing and development, trial start-up and vendor management, and a proven track record in planning and managing clinical trials to quality standards, timelines and budget. Brenda joined Helix Biopharma Corp. in 2018, working to advance the clinical program of L-DOS47. She holds B.Sc and M.Sc. degrees from the University of Toronto, specializing in Nutritional Sciences and Human Biology.

This will close in 0 seconds

Jerzy Leszczynski

Director


Jerzy Leszczynski is a shareholder of the Company, has spent more than 35 years developing businesses and has served in the capacity of board member of various real estate development companies. Mr. Leszczynski obtained his Master of Science in Chemistry from the Warsaw Institute of Technology.

This will close in 0 seconds

Janusz Grabski

Director, Chair of Audit Committee


Janusz (John) Grabski is a lawyer specialized in corporate and real estate law with over twenty years of experience.

This will close in 0 seconds

Malgorzata Laube

Director


Malgorzata Laube has over 19 years of experience in nuclear medicine. In her last role with Alberta Health Services, she was the Department Supervisor, Nuclear Medicine at Royal Alexandra Hospital. Ms. Laube obtained a MSc degree in Environmental Engineering from the Warsaw University of Technology and is based in Edmonton, Alberta, Canada.

This will close in 0 seconds

Jacek Antas

Chairman of the Board


Jacek Antas is a shareholder of the Company, has spent more than 25 years in the financial services industry holding various positions in sales and consulting.

Mr. Antas obtained a master’s degree from the Warsaw School of Economics and has served as a board member of various
companies throughout his career.

This will close in 0 seconds

Jonathan Davis

Advisor, ADC Discovery


Jonathan Davis received his Ph.D. from University of California, San Francisco, where he studied protein structure and function using NMR. After a post-doc at Harvard Medical School exploring RNA selection and structure in the labs of Jack Szostak and Gerhard Wagner, he went to work at EMD Serono, where his work involved improving antibody-based therapeutics, inventing a platform technology for generating heterodimeric Fcs as a basis for multifunctional molecules, and developing a novel scaffold based on an artificially-designed protein from David Baker’s lab. In 2008 he took a job at Bristol-Myers Squibb in Waltham/Cambridge MA, working on antibody discovery and platform development in a wide range of therapeutic areas, with a particular focus on multispecific therapeutics. He moved to Madison, WI in 2019 to take on the role of VP of Innovation and Strategy at Invenra, a biotech focused on bispecific antibodies, and where he is currently head of the Scientific Advisory Board. In early 2024 he left the corporate world to found Creative Antibodies, a consulting firm that helps guide companies to successful antibody discovery and development projects, from mAbs to multispecifics, ADCs, and other formats. Outside of science, Jonathan is a conservatory trained cellist, plays numerous other instruments, and founded the UCSF Orchestra (now Symphony Parnassus) in San Francisco, where he was Music Director for six years.

This will close in 0 seconds

Davide Guggi

Advisor, CMC


Davide graduated as a pharmacist and received his PhD in Pharmaceutical Technology and Biotechnology from the University of Vienna. He has over 20 years of experience in the pharmaceutical industry, principally in the field of oncology. At the beginning of his career, Davide led oncology business units and commercial departments at Mundipharma and Gilead across Austria and Eastern Europe. Since over 10 years he has been working as a CMC expert, covering operational and regulatory CMC functions on behalf of over 20 different small- and medium-sized biotech companies across the world. He has served as CMC Director and CSO/CTO for several years, developing both small molecules and biologics (mABs, Fab, ADCs and Radio-immuno-conjugates) from early discovery to NDA/BLA in the US, EU and Canada, with a focus on First-in-Human and Phase I/II studies in oncology indications.

This will close in 0 seconds

This will close in 0 seconds

Tumor Defense Breaker™, L-DOS47


L‑DOS47 is a first‑in‑class, clinical-stage antibody‑enzyme conjugate designed to deliver a game-changing assist to anti-cancer immunity and today’s leading cancer immunotherapies for the treatment of prevalent, hard-to-treat solid tumors. The compound precisely targets CEACAM6, a cell-surface protein overexpressed in non‑small cell lung cancer (NSCLC) and other aggressive tumors, where it delivers an enzymatic payload that raises the extracellular pH of the acidic tumor microenvironment (TME). By neutralizing tumor acidity, L-DOS47 restores immune cell infiltration and activity, helps turn immunologically “cold” tumors “hot”, and enhances the therapeutic reach of immune checkpoint inhibitors. With patented composition-of-matter coverage through 2036 and demonstrated synergy with PD-1 inhibitor, pembrolizumab, L-DOS47 is poised to significantly increase the efficacy of immune checkpoint blockade and unlock broader and more durable responses in NSCLC and other aggressive solid tumors.

This will close in 0 seconds

LEUMUNA™


LEUMUNA™ is an oral immune checkpoint modulator designed to activate the donor immune system to recognize and fight relapsing leukemia in patients who have undergone allogeneic stem cell transplantation (allo-SCT). Although a life-saving procedure, up to 30% of patients who undergo allo-SCT see their cancer return, facing a median survival of just four months. LEUMUNA aims to offer these patients a new lease on life, by activating an immune cascade and inciting graft-versus-leukemia (GvL) effect, potentially offering long-term remission. Backed by strong preclinical data and a promising safety record from trials with its precursor compound, ulodesine, LEUMUNA offers a patient‑friendly, oral approach to a difficult-to-treat condition, with patent protection through 2041 and an Orphan Drug Designation granted by the US FDA.

This will close in 0 seconds

GEMCEDA™


GEMCEDA is a first-in-class oral prodrug of gemcitabine that opens up the possibility for convenient at-home administration, metronomic dosing and seamless integration into combination regimens with immune checkpoint inhibitors. To date, gemcitabine is only administered intravenously because oral forms have shown poor bioavailability of about 10%. GEMCEDA was developed as a prodrug to enable new uses of gemcitabine by combining it with cedazuridine, an enzyme inhibitor that helps boost its bioavailability to 90%. This remarkable innovation allows for greater flexibility in dosing schedules, fewer clinic visits, and a better quality of life, while achieving bioavailability on par with intravenous gemcitabine. Supported by a well‑established safety profile, scalable manufacturing, and patent coverage to 2043, GEMCEDA reimagines how chemotherapy can fit into patients’ lives.

This will close in 0 seconds