AACR 2026: Lung Cancer Immunotherapy Response Predicted by Pathomics AI Model

SAN DIEGO – A new AI model applied to routine pathology slides accurately predicts outcomes and response to immunotherapy in patients with metastatic non-small cell lung cancer (NSCLC). The study was study presented at the American Association for Cancer Research (AACR) Annual Meeting. 

“Immunotherapy has transformed cancer treatment, but only a subset of patients benefit from it, and predicting who will respond remains challenging,” said Rukhmini Bandyopadhyay, PhD, a postdoctoral fellow at The University of Texas (UT) MD Anderson Cancer Center.  

“This study represents, to our knowledge, the first deep learning-based pathomics biomarker rigorously validated across international real-world cohorts and a Phase III randomized clinical trial, directly addressing one of the most urgent unmet needs in precision oncology: reliable patient selection and stratification for immunotherapy,” he continued. 

Pathomics applies computational and machine learning methods for high-throughput analysis of digital pathology images to extract large-scale data related to cell and tissue architecture linked to disease outcomes. 

Bandyopadhyay and colleagues developed a deep learning survival prediction model called Pathology-driven Immunotherapy Optimization (Path-IO), which can study patterns across tissue to identify patients most likely to benefit from immunotherapy. The model then combines imaging and clinical data to estimate whether a patient may have a higher or lower risk of poor outcomes from immunotherapy. 

The researchers tested the platform in a study that included 797 immune checkpoint inhibitor-treated NSCLC patients from UT MD Anderson, with external validation in 280 additional patients from Mayo Clinic, Gustave Roussy, and the Phase III Lung-MAP S1400I trial in which immunotherapy-naïve patients with lung squamous cell carcinoma, a subtype of NSCLC, were treated with immune checkpoint inhibitors. 

The model reliably stratified patients into higher and lower risk groups. In the UT MD Anderson cohort, patients in the high‑risk group had more than double the risk of death or disease progression compared with patients in the low‑risk group. 

Model performance was evaluated using the concordance index (C-index), which measures how well each biomarker distinguishes between patients with different outcomes. Notably, Path-IO consistently outperformed PD-L1, the U.S. Food and Drug Administration-validated standard-of-care biomarker for guiding immunotherapy use in NSCLC patients, across both discovery and test cohorts.  

PD-L1 alone showed limited prognostic performance, with C-indices of 0.58 for overall survival (OS) and 0.57 for progression-free survival (PFS) in the discovery cohort, declining to 0.50 and 0.51, respectively, in the test cohort. In contrast, Path-IO demonstrated stronger discriminative ability, achieving C-indices of 0.69 for OS and 0.65 for PFS in the discovery cohort and 0.63 for OS and 0.58 for PFS in the test cohort.  

Combining pathology-based predictions with radiomics and clinical data further improved the model’s performance, with the C-index increasing from 0.58 to 0.70 for PFS and from 0.63 to 0.75 for OS.  

Given that the approach was designed to be applied to routine pathology slides, the platform can be incorporated into existing clinical workflows without significant expense compared to other emerging data-based technologies. 

As the study is retrospective, further investigation is needed to go beyond the identification of patients who would benefit from immunotherapy and help predict what type of immunotherapy they can benefit from. Future directions include prospective validation and the integration of paired, more comprehensive molecular profiling to enhance predictive performance.

The post AACR 2026: Lung Cancer Immunotherapy Response Predicted by Pathomics AI Model appeared first on GEN - Genetic Engineering and Biotechnology News.