The director of Laryngology Research at Mass Eye and Ear discussed how the AI-based DystoniaNet came to be and what challenges impact the diagnosis of dystonia.
“In addition to the absence of a biomarker and test, the diagnosis [of dystonia] is typically impacted by the large variability in the symptomatology of this disorder, the circumstances of the evaluation, the state of the patient, the expertise and experience of the clinician, and other non-neurologic conditions that can mimic the symptoms.”
Kristina Simonyan, MD, PhD, DrMed, has spent much of her time as a clinician attempting to improve a challenging aspect of care for patients with dystonia: diagnosis. Despite a relatively solid understanding of the disease, many individuals with dystonia can often go undiagnosed for quite some time—some up to 10 years—due to the challenges of diagnosing the disorder.
In part to help combat these issues, Simonyan and her colleague Davide Valeriani, PhD, postdoctoral research fellow, Dystonia and Speech Motor Control Laboratory, Mass Eye and Ear and Harvard Medical School, developed an artificial intelligence (AI) based deep learning platform, dubbed DystoniaNet, to use magnetic resonance imaging (MRI) data to better identify these patients. Their recent assessment of DystoniaNet suggests that the platform can accurately identify patients with dystonia within a single second, which may help clinicians severely cut down the time to diagnosis in an otherwise challenging condition.
Simonyan, who is the director of Laryngology Research at Mass Eye and Ear, as well as an associate neuroscientist at Massachusetts General Hospital and associate professor of Otolaryngology-Head and Neck Surgery at Harvard Medical School, spoke with NeurologyLive to provide some background on how this platform came to be, as well as to highlight the challenges faced in the diagnosis of dystonia.