Onc.AI Announces Presentation of Breakthrough-Designated AI Model Evaluated in Clinical Trial Data at AACR 2025 CHICAGO -- (BUSINESS WIRE) -- Onc.AI, a digital health company at the forefront of developing advanced AI-driven clinical management solutions for oncology, has announced that findings from a collaboration with global biopharmaceutical company GSK will be presented at the 2025 American Association for Cancer Research (AACR) Annual Meeting. The study focused on Onc.AI’s FDA breakthrough-designated Serial CTRS (CT Response Score) model, which was evaluated in GSK’s GARNET Phase I clinical trial, specifically Cohort E. This trial involved patients with advanced non-small cell lung cancer (NSCLC) treated with dostarlimab, GSK’s anti-PD-1 checkpoint inhibitor. The results, set to be highlighted in a poster presentation during the Predictive Biomarkers 2 session (.poster #21, April 27, 2025, 2-5pm), demonstrate that the Serial CTRS biomarker significantly enhances the prediction of overall survival (OS) compared to traditional surrogates such as the RECIST 1.1 response criteria and tumor volume change assessments. This breakthrough was confirmed through an independent and blinded retrospective validation study conducted by GSK. Specifically, Serial CTRS was able to distinguish patients with intermediate versus high probabilities of 12-month OS (hazard ratio: 2.91, 95% confidence interval: 1.16–7.31), outperforming RECIST 1.1 (hazard ratio: 1.34, 95% confidence interval: 0.57–3.13) and tumor volume change assessments (hazard ratio: 1.00, 95% confidence interval: 0.43–2.34). This superior predictive performance underscores Onc.AI’s mission to establish Serial CTRS as a new standard for automated, AI-based imaging endpoints in the early assessment of treatment response. The model seamlessly integrates into standard imaging workflows, making it applicable across various therapeutic regimens. "This significant milestone for Serial CTRS follows our recent FDA breakthrough designation," said Akshay Nanduri, CEO of Onc.AI. "The successful validation study and our ongoing collaboration with GSK highlight the robustness and advanced capabilities of our model. These achievements are made possible by leveraging cutting-edge deep learning techniques and our extensive data harmonization methods, which ensure the highest quality and diversity in our training, testing, and validation processes." Onc.AI’s deep learning platform relies on high-quality data from thousands of patients sourced from dozens of healthcare systems and hundreds of clinics across the United States and international cancer centers. This broad and diverse dataset is crucial for the model's accuracy and reliability. George R. Simon, MD, FACP, FCCP, Vice President of Oncology at OhioHealth, commented, "Having previously headed several Phase I clinics at top cancer centers, I am convinced that Onc.AI’s Serial CTRS could revolutionize the clinical development process for pharmaceuticals, from Phase I to Phase III trials. Its potential impact on improving patient outcomes and enhancing treatment decision-making is substantial." Onc.AI is a digital health company that develops AI-driven oncology clinical management solutions by applying advanced deep learning to routine diagnostic images. The company's platform is designed for use at the point of care by medical oncologists and is also utilized by major pharmaceutical companies to expedite oncology drug development. Onc.AI is supported by leading institutional investors, including Sandbox/Blue Venture Fund, Action Potential Venture Capital, MassMutual Alternative Investments, Accomplice, Digitalis, KdT, and Life Extension Ventures. Additionally, the company receives backing from the National Cancer Institute SBIR program (1R44CA291456-01A1). For more information, visit: www.onc.ai.