Unmet Need
Parkinson’s Disease affects over 6 million people globally, and is one of the fastest growing neurodegenerative diseases in prevalence, disability, and deaths (GBD 2016 Parkinson’s Disease Collaborators). Presently, Parkinson’s diagnosis and prognosis depend on monitoring a patient’s symptoms and occasional imaging of the affected region of the brain. However, Parkinson’s progression varies by patient, and although there is no way to prevent or cure the disease, providing the proper treatment for the diseases stage can significantly relieve symptoms (Cleveland Clinic). Identifying biomarkers and trends in Parkinson’s progression can power clinical studies towards new and better treatments for Parkinson’s as well as inform current therapy options (Parkinson’s Progression Markers Initiative). Therefore, there is a strong need for prognostic tools that can characterize Parkinson’s Disease patients’ outcomes and assist in determining optimal treatment and therapy regimens.
Technology Overview
Johns Hopkins researchers have developed an artificial intelligence method for predicting long term motor performance in patients with Parkinson’s Disease. Using a combination of dopamine system imaging and non-imaging clinical patient measures such as motor function in the first year of diagnosis, researchers are able to predict outcomes which can enable more targeted therapy to delay disease progression.
Stage of Development
Currently in the process of refining the machine learning algorithm.
Publication
K. H. Leung et al., "Using deep-learning to predict outcome of patients with Parkinson’s disease," 2018 IEEE Nuclear Science Symposium and Medical Imaging Conference Proceedings (NSS/MIC), 2018, pp. 1-4, doi: 10.1109/NSSMIC.2018.8824432.
