Grant: Operating Grant

Lung cancer is a leading cause for death among men and women with 5-year survival rate of only 15%. Patients at advanced stages suffer from further poorer prognosis and dire socioeconomic consequences for them, their relatives and the healthcare system. The majority of these patients is diagnosed with non-small cell lung cancer (NSCLC) and receives radiation therapy as their main treatment. However, radiation hypersensitivity, which manifests as inflammatory response known as radiation pneumonitis, is a major limiting factor to treatment success and a main obstacle to applying new promising radiation modalities. This is a potentially fatal condition that damages normal lung tissues, therefore, a key goal of modern radiotherapy research is to predict at the time of treatment planning, the risks of pneumonitis for each individual patient. However, because of the inherent complexity and variability of the biological response to radiation therapy, current physical or biological models separately are insufficient to accurately predict this risk. Therefore, in this proposal we plan to investigate a novel system-based approach that would integrate relevant biological information while controlling for physical variations in the same population using artificial intelligence and bioinformatics techniques. We plan to conduct a prospective study in a cohort of locally advanced NSCLC patients who receive radiotherapy at McGill University Health Centre. The data collected in this study and developed methodology would provide new insights into radiation pneumonitis signaling mechanisms and allow for better predictive models of its onset. The findings can be used clinically to personalize patients' treatment plans, reducing the risk of complications or supporting therapy that is more intensive for those patients likely to benefit. This could potentially improve outcomes, provide greater quality care for patients, and reduce associated healthcare costs.