Transforming NSCLC Care Through Multiomics and AI

Published Date : 29/07/2025 

Artificial intelligence (AI) and multiomics are transforming the diagnosis and treatment of localized non-small cell lung cancer (NSCLC). From enhancing imaging and digital pathology to predicting toxicities, these technologies are paving the way for more precise and effective patient care. 

Artificial intelligence (AI) and multiomics are rapidly reshaping the diagnostic and therapeutic landscape in localized non–small cell lung cancer (NSCLC). Although the hype around AI often overshadows its practical limitations, thoughtful integration of digital pathology, radiomics, and multi-parametric modeling is beginning to provide real clinical utility, particularly in the neoadjuvant setting.

In a presentation delivered during the 26th Annual International Lung Cancer Congress, Sandip Patel, MD, discussed the rise of AI-enabled imaging and digital pathology in predicting treatment response, the use of multiomics and machine learning for toxicity prediction and risk stratification, and a cautious but promising vision of AI as an assistive, not autonomous, tool in clinical oncology.

Patel is a professor at the University of California, San Diego (UCSD), medical director of Clinical Research Informatics, leader of Experimental Therapeutics, coleader of the Solid Tumor Therapeutics Program, and deputy director of the Sanford Stem Cell Clinical Center at UCSD Moores Cancer Center.

AI in Imaging and Digital Pathology: Constructive “Hallucinations” and Enhanced Diagnostic Precision

A standout example of AI’s evolving role in lung cancer care is Sybil, an AI model developed at Massachusetts General Hospital (MGH) by Lecia Sequist, MD, MPH, and colleagues. Designed for low-dose CT lung cancer screening, Sybil leverages deep learning to detect patterns that elude even expert radiologists. Importantly, Sybil has demonstrated the phenomenon of “constructive hallucinations,” or instances where the AI flags nodules missed by human readers that later manifest as radiologically visible lesions.

“Everything AI produces is a hallucination; it’s just most things are useful hallucinations,” Patel said. “What’s interesting from the MGH data is that in the lung cancer screening population, there were several nodules that two radiologists felt were low risk or not even there. Sybil said, ‘Oh, there’s something there.’ Then 2 or 3 or 6 months later, a nodule showed up.” These so-called “constructive hallucinations” exemplify the potential of AI to enhance radiologic sensitivity in clinically meaningful ways.

Despite its promise, Sybil, like all AI, suffers from a lack of epistemological grounding. Without a true “gold standard,” AI outputs are fundamentally probabilistic, and clinicians must remain cautious of false positives and negatives. Nevertheless, when used in tandem with human expertise, these AI tools can heighten sensitivity and reveal subtle changes with clinical relevance.

Equally transformative is AI’s role in digital pathology, particularly in evaluating responses to neoadjuvant therapy. Traditional assessment of pathologic response is highly subjective, especially in intermediate cases where complete tumor eradication isn’t observed, Patel explained.

To address this, investigators are integrating computer vision algorithms into digital pathology workflows. One case study from the phase 2 LCMC3 trial (NCT02927301) used AI to standardize the measurement of pathologic response to neoadjuvant atezolizumab (Tecentriq). These models help quantify tumor regression more objectively, aiding in clinical trial end point determination and potentially guiding postoperative decision-making.

Within the same study, led by Sanja Dacic, MD, PhD, of Yale School of Medicine, investigators found that digital major pathologic response, an AI-determined response metric, outperformed subjective human interpretation in predicting intermediate patient outcomes when there was discordance between pathologists. This suggests that digital pathology may soon serve not just as a support tool, but as a central adjudicator in ambiguous response scenarios.

“The ability for an algorithm to assist a pathologist in doing this is something that I think we’re going to see [more] of, and it’s going to be kind of a centralized reviewer,” Patel said.

Predicting Toxicity and Therapeutic Benefit With Multiomics and Radiomics

AI is also proving useful in treatment planning by integrating diverse data streams to predict adverse effects. One area of focus is immune-related pneumonitis, a well-known toxicity in the context of immunotherapy. Here, radiomics, or the extraction of high-dimensional data from standard medical images, is combined with multi-parametric modeling to identify patients at risk before symptoms emerge.

Research by Jarushka Naidoo, MBBCh, a professor of medical oncology and consultant medical oncologist at Beaumont the Royal College of Surgeons in Ireland Cancer Centre in Dublin, exemplifies this. Her multivariate analysis used imaging features, electronic medical record (EMR) variables, and baseline laboratory data to predict pneumonitis risk. Surprisingly, race and neutrophil count emerged as strong predictors, alongside imaging-based metrics. The model’s high negative predictive value (0.93; 95% CI, 0.90-0.96) makes it a valuable tool for ruling out toxicity and avoiding unnecessary treatment interruptions.

This is particularly important in the neoadjuvant setting, where radiologic findings such as nodal “flares” can mislead clinicians. What might appear to be progressive disease may represent immune cell infiltration rather than tumor growth. Radiomics could help differentiate these phenomena, guiding oncologists on whether to continue or halt immunotherapy prior to surgery.

“This is a red herring. These are immune cells ready to attack the tumor and this patient needs to continue therapy. This is an area that I think radiomics can really help us in discerning which patients are going to benefit vs not,” Patel explained.

Moreover, radiomic features could eventually help discern which patients derive the most benefit from novel agents like datopotamab deruxtecan (Datroway). For instance, AI-assisted image analysis has been used to evaluate whether TROP2 expression is predictive of therapeutic response via whole slide imaging and quantitative immunohistochemistry scoring. Work led by Marina Garassino, MD, of the University of Chicago Medicine, in this space suggests that combining AI with digital pathology may help match antibody-drug conjugates with biologically appropriate candidates, improving outcomes and avoiding overtreatment.

The Limits of Large Language Models and the Promise of Human-AI Collaboration

Although imaging and pathology applications are gaining traction, there’s growing skepticism about AI models purporting to “replace” oncologists. Much of this concern stems from flawed comparisons between AI and human performance in artificial test scenarios. A case in point: Microsoft’s claim of achieving “medical superintelligence” by having an AI outperform physicians on The New England Journal of Medicine case vignettes. These studies typically favor the AI by removing the contextual ambiguity that real-life clinicians face, such as missing data, unclear symptom onset, and differential diagnoses.

“Anytime you see an article about AI beating anyone, I want you to ask a couple questions,” Patel said.

In contrast, tools like ASCO’s retrieval-augmented generation–based guidelines assistant represent a more grounded application. These systems combine large language model architecture with curated clinical guidelines, enhancing the reliability of AI-generated recommendations. Similarly, models like the ScoutAI tool ingest structured clinical data and professional meeting content rather than open internet sources, creating a more trustworthy information substrate for oncologists.

Ambient AI for documentation is another area with immediate clinical utility. These systems transcribe and summarize clinical conversations in real-time, reducing the burden of electronic charting, improving documentation accuracy, and freeing physicians to focus on patient care. Early adopters have reported significant reductions in “pajama time” and enhanced patient interactions, Patel said.

However, AI’s reliability is still influenced by how it’s prompted and how many iterative queries are made. Large language models can “degenerate” over time in chained prompts, leading to increasingly inaccurate responses—a phenomenon evident in older models that hallucinated PubMed IDs or recommended contraindicated drug combinations when pushed with edge-case scenarios, Patel noted.

Looking Ahead at Integration, Not Replacement

AI is unlikely to replace oncologists anytime soon, but it is poised to augment them in profound ways. From standardizing pathologic response measurements to refining imaging interpretations and predicting toxicities, AI offers practical tools that address some of oncology’s most nuanced challenges.

In localized NSCLC, particularly in the neoadjuvant space, these tools are already beginning to influence trial design, regulatory end points, and even patient selection. As multiomics and machine learning models become more integrated into routine workflows, the field must ensure that their implementation is guided by rigorous validation, clinician oversight, and, most importantly, patient benefit.

The promise of AI in NSCLC lies not in sensational headlines, but in practical, iterative progress. By embracing the technology’s strengths, while remaining vigilant to its limitations, oncologists can unlock new avenues of precision medicine that truly move the needle for patients. 

Frequently Asked Questions (FAQS): 

Q: What is Sybil, and how does it help in lung cancer screening?

A: Sybil is an AI model developed at Massachusetts General Hospital that uses deep learning to detect lung cancer nodules from low-dose CT scans. It can identify nodules that might be missed by human radiologists, enhancing early detection and surveillance.

Q: How does AI assist in digital pathology for NSCLC?

A: AI algorithms help standardize the measurement of pathologic response to neoadjuvant therapy, making tumor regression assessments more objective and reliable. This aids in clinical trial end point determination and postoperative decision-making.

Q: What role does radiomics play in predicting treatment toxicities?

A: Radiomics extracts high-dimensional data from medical images to predict adverse effects like immune-related pneumonitis. By combining imaging features with other clinical data, AI models can identify patients at risk before symptoms appear.

Q: Can AI replace oncologists in the near future?

A: While AI has significant potential, it is unlikely to replace oncologists soon. Instead, AI is more likely to augment their work by providing tools that enhance diagnostic precision, treatment planning, and patient care.

Q: What are the ethical considerations in using AI in oncology?

A: Ethical considerations include ensuring AI models are transparent, unbiased, and validated. Clinicians must also remain cautious of AI’s limitations and maintain oversight to ensure patient safety and benefit. 

More Related Topics :