Teva and Intel are joining forces on a wearable device and machine-learning platform to improve the understanding and treatment of Huntington’s disease.
The duo plans to deploy the platform, which will enable continuous monitoring and analysis of Huntington’s symptoms, in a substudy in an ongoing Phase II trial of the drug pridopidine in people with Huntington’s, according to a statement. They hope to launch the study in the U.S. and Canada by the end of the year.
The platform comprises a smartphone and smartwatch that will measure patients’ “general functioning and movement,” the companies said in a statement. The data will then be wirelessly transmitted to a cloud-based platform developed by Intel, where it will be analyzed and translated by algorithms into quantifiable scores for motor symptom severity, according to the statement.
There is no cure for Huntington’s, a hereditary condition that causes progressive degeneration of nerve cells in the brain. Treatments focus on managing symptoms. Currently, doctors observe symptoms during patient visits, said Michael Hayden, Teva chief scientific officer and global R&D chief, in the statement. This project aims to provide objective and continuous data on Huntington’s patients and the effects of treatment on them, he said.
“Patients generate data based on their day-to-day experiences that can help in improving disease management--even something as simple as wearing a smart watch can add useful insight,” said Jason Waxman, corporate vice president and general manager of the Datacenter Solutions Group at Intel, in the statement. “The complexity of analyzing these data streams requires a platform for machine learning, to help drive the pharmaceutical industry towards faster, better clinical trials, potentially leading to new treatments for patients.”
Industry players have tapped machine learning in a number of areas, including medical imaging, breast cancer pathology and detection of heart disease. In August, researchers at the Australian National University scored funding for a study tracking early Parkinson’s symptoms to identify possible indicators of progression using machine learning.