Development and Validation of a Predictive Model for Immunotherapy Benefit in Extensive-Stage Small Cell Lung Cancer.

Extensive-stage small cell lung cancer (ES-SCLC) is an aggressive form of lung cancer where the disease has spread widely in the body. The standard treatment combines chemotherapy with immunotherapy. Chemotherapy involves administering drugs that are toxic to cells, particularly those that are rapidly dividing, like cancer cells, whereas immunotherapy stimulates the body's own immune system to recognize and kill cancer cells. While this combination has helped some patients live a few months longer, many others do not benefit from it at all. Currently, doctors have no reliable test to predict who will respond well to this treatment. This means some patients undergo costly therapies with potential side effects without receiving any significant benefit.

In this project, we will address this issue by developing a prediction model using machine learning, which is a form of Artificial Intelligence (AI) that finds patterns in complex data. Using retrospectively collected data from our institutional cohort of ES-SCLC patients, we will train the model by integrating transcriptomic information (which refers to the patterns of which specific genes are actively turned on or off within a patient's tumor) with routine clinical variables such as age. The output will be a score estimating an individual patient’s likelihood of benefiting from immunotherapy.

The most crucial step is to thoroughly test this model to ensure it is accurate and reliable for future patients. For this validation, we will use the model on two completely separate groups of patients from large, international clinical trials: the CASPIAN trial and the IMpower133 trial. Applying the tool to these independent datasets will show us if it truly works in different patient populations.

If successful, this tool could help doctors make more personalized treatment decisions. It could identify patients who are very likely to benefit from the immunotherapy, while also sparing those unlikely to respond from unnecessary treatment, allowing them to try other options sooner. Ultimately, this research seeks to ensure that every patient receives the treatment best suited for them, improving care for people with advanced small cell lung cancer.