Artificial intelligence for the prediction of early progression in follicular lymphoma
Why are we doing this study?
Follicular lymphoma is a chronic malignancy: patients often require no immediate treatment and many continue without treatment for long periods. However, some patients experience early disease progression or transformation to a more aggressive cancer, and require treatment. In this study we are trying to improve our ability to predict which patients are at risk of this. A reliable method would be useful for both patients and clinicians as it would help with treatment decisions, and could provide re-assurance that choosing not to treat (known as a ‘Watch & Wait’) is a sensible strategy. In the long term the method might direct earlier or different treatment in patients who are at higher risk of progression or transformation.
What is our aim?
Our aim is to produce an artificial intelligence (AI) based method to predict the risk of early progression or transformation using data gathered from patients at diagnosis and follow-up. The data available for patients in the Haematological Malignancy Research Network is a unique resource that enables this type of study.
What are we going to do?
We think that early progression is likely to be predictable from information about the patient and the diagnosed tumour. The project will begin by building a comprehensive data set containing information on patients and their outcomes, the individual genetic causes and molecular drivers of disease and information from pathology images on the nature of the tumour. We will then train AI methods to predict the risk of progression. If this is successful we will proceed to test the method in new data and trials with patients.