Researchers at Emory University's Winship Cancer Institute have developed an AI-based biomarker that utilizes routine CT scans to predict how patients with non-small cell lung cancer (NSCLC) will respond to immunotherapy. The study, published in Science Advances, identifies "quantitative vessel tortuosity" (QVT)—the degree of twisting in tumor-associated blood vessels—as a key indicator. AI analysis of over 500 patient scans revealed that less twisted vasculature correlates with better responses to immune checkpoint inhibitors (ICIs). This non-invasive method could guide treatment decisions and reduce unnecessary costs, as ICIs can exceed $200,000 annually per patient. The research was led by Dr. Mohammadhadi Khorrami and Dr. Anant Madabhushi, with contributions from Case Western Reserve University and other institutions.