Precision Oncology in LS-SCLC: AI-Driven Dosimetric and Genomic Biomarkers for Outcome Prediction
Combining chemotherapy, radiation therapy, and immunotherapy has improved survival for patients with small cell lung cancer (SCLC). However, many patients relapse or suffer severe side effects. This project aims to improve how we predict patient outcomes when treated with immunotherapy, improving survival rates while minimizing harm. We will use a combination of clinical information, radiation treatment data and genetic information from tumors to build personalized prediction tools. Using advanced artificial intelligence methods we will identify features that help forecast whether a patient will relapse or develop treatment-related side effects. We will also create "molecular twins," virtual models of individual patients, to simulate how different treatment choices might affect outcomes. Our approach leverages one of the largest real-world datasets of limited-stage SCLC patients linked with genomics and radiation details. The results of this work could significantly advance personalized cancer care and guide the next generation of clinical trials in SCLC.
