Mount Sinai's cancer AI startup finds its algorithms can help spot Parkinson's disease as well

A digital pathology spinout that recently launched from Mount Sinai with the goal of supporting breast and prostate cancer diagnoses has made an interesting finding: Its artificial intelligence programs could also spot the early signs of Parkinson’s disease before severe symptoms appear.

PreciseDx originally trained its AI to analyze the form and structure of cells on biopsied tissue slides and detect the early hallmarks of cancer to help predict a person’s risk of developing a tumor or the chances of having one return after treatment.

And when the algorithms were turned on nerve samples taken from the mouth’s salivary glands, they were able to find the characteristic protein clumps known as Lewy bodies, which have been linked to the neurodegenerative disease.

In a collaboration with The Michael J. Fox Foundation for Parkinson's Research, a study showed the AI could be highly accurate, providing false-negative and false-positive results at a rate of 1%, while outperforming human pathologists.

"Objective diagnostic tools, especially early in disease, are critical to drive care decisions and to design trials toward better treatments and cures," Jamie Eberling, the Fox Foundation’s senior vice president of research resources, said in a statement.

Definitively diagnosing Parkinson's disease can be a challenge, as motor control symptoms such as tremors and rigidity can mimic other conditions.

"Traditionally, pathology grading systems look at a few morphology components to make a diagnosis. Unlike any human-powered grading method, PreciseDx's AI Morphology Feature Array can examine thousands of different features and leverage those relationships between them," said John Crary, M.D., a professor in the pathology, neuroscience and AI departments of the Icahn School of Medicine at Mount Sinai.

"This industry-changing study has shown that we need to revitalize the way we think about pathology and lean into using AI to detect diseases more accurately, such as PD,” Crary added.

PreciseDx’s cancer risk stratification methods were developed by Mount Sinai faculty and licensed to the company, which raised $10.75 million in venture capital funding this past January.

The startup’s series A round was led by the Merck Global Health Innovation Fund, with additional backing from Agilent Technologies, IBM Ventures, the Hobart Group and Mount Sinai Health System.

"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, Mount Sinai’s chief commercial innovation officer and president of Mount Sinai Innovation Partners. Lium also holds a seat on PreciseDx’s board of directors.