Research summary
In a data-driven world, machine learning is expected to be a key tool for converting big data into tangible benefits. But many datasets are typically needed to train robust and accurate machine learning models. This is a major barrier preventing their use in health care applications. As a result, new data mining and machine learning approaches may not achieve their true potential for diagnosing and treating patients with neurological diseases.
As Canada Research Chair in Medical Image Analysis, Dr. Nils Daniel Forkert is developing a new system for training machine learning models that does not require data-sharing and centralized collection. Instead, the patient data used does not leave the contributing institution, and is used only locally to train machine learning models on-site. By using this approach, Forkert and his research team are enabling many advanced machine learning models to be trained for computer-aided diagnosis, which will have a significant impact on neuroscience research and beyond.