Mount Sinai Spin-Off Develops AI Tool to Detect Early-Stage Parkinson's

Cancer risk stratification company PreciseDx, a Mount Sinai Health System spin-off, has developed artificial intelligence-enabled digital pathology technology to detect Parkinson’s disease (PD), and new research conducted in collaboration with the Michael J. Fox Foundation (MJFF) shows it accurately detects the disease before the onset of severe symptoms.

PD is a neurological disorder that can be difficult to diagnose early because the symptoms are subtle and occur gradually, according to the National Institute on Aging. Other conditions also share multiple symptoms with PD, resulting in misdiagnosis or a late diagnosis when symptoms have already become severe. Since the disease is most common in older adults, early symptoms are also occasionally dismissed as the normal effects of aging.

Diagnosis of PD typically relies on a neurologist reviewing a patient’s signs and symptoms, medical history, and a neurological and physical examination. Additional tests and medical imaging can be done to rule out other conditions that share symptoms with PD. Skin biopsies and spinal taps can provide information about a patient’s alpha-synuclein proteins, a type of protein linked to idiopathic PD. A doctor may also prescribe a PD medication to evaluate whether the patient responds to the treatment—significant improvement with this type of medication can be used to confirm a PD diagnosis. Research to pinpoint biomarkers for various neurological diseases, including PD, is ongoing.

PreciseDx has developed Morphology Feature Array (MFA), an AI tool designed to detect PD pathology in image patches from biopsy samples, according to the press release. They then tested the model in a study partially funded by the MJFF, a nonprofit that focuses on improving treatment therapies and finding a cure for PD. In the study, the researchers showed that the AI performed similarly to three neuropathologists. They also noted that the AI has the potential to be more reliable, consistent, and cost-efficient.

"These findings show the potential for technology to aid in diagnosis of Parkinson's disease," said Jamie Eberling, PhD, senior vice president of research resources at MJFF, in the press release. "Objective diagnostic tools, especially early in disease, are critical to drive care decisions and to design trials toward better treatments and cures."

According to the press release, PreciseDx’s MFA will enable new algorithms to be developed and validated for clinical use, which will aid in the creation of new diagnostic tests, allow for accurate diagnosis and prognosis, and improve patient selection for therapy.

"We look forward to working with PreciseDx as it explores the potential of utilizing the AI platform in pathology across multiple diseases, including Parkinson's," said Erik Lium, PhD, president, Mount Sinai Innovation Partners and executive vice president and chief commercial innovation officer, Mount Sinai Health System, in the news release.

The technology is based on intellectual property developed by Mount Sinai faculty and licensed to PreciseDx. The health system, along with some of its faculty, have a financial interest in the company, and Lium represents Mount Sinai on the PreciseDx Board of Directors.