The neuropathologist at Mount Sinai and chief science officer of Precise Dx pairing shared background information on the artificial intelligence’s ability to improve the diagnosis of Parkinson disease from peripheral tissue biopsies. [WATCH TIME: 9 minutes]
WATCH TIME: 9 minutes
“One of the major issues with [identifying pathology in peripheral tissue] is that the pathology is very, very hard to find. Screening these slides and finding these peripheral axons is super time-consuming and difficult. I was trained to do it, along with the other neuropathologists on the project, but the entire time I was thinking, ‘There’s got to be a better way to do this. It would be amazing if we could train an AI to do it.’ That’s where this project came from.”
A recently published study conducted by John F. Crary, MD, PhD, professor of Pathology, Neuroscience, and Artificial Intelligence (AI) & Human Health, Icahn School of Medicine, Mount Sinai, and colleagues showed that an AI algorithm, built by the Mount Sinai spinoff company PreciseDx, is capable of accurately detecting Parkinson disease (PD) pathology in biopsy sample image patches with 99% sensitivity and 99% specificity as compared to expert annotated ground truth. All told, PreciseDx's AI Morphology Feature Array outperformed human pathologists with an accuracy of 0.69 compared with 0.64 in the prediction of clinical PD status.1,2
The algorithm is designed to immunohistochemically detect α-synuclein within peripheral nerves of salivary glands. Additionally, it utilizes quantitative feature extraction by assessing morphology features to accurately distinguish Lewy-type synucleinopathy in early-stage PD biopsy specimens.
To find out more about this study and the potential of such technology to improve the diagnosis of PD and similar diseases, NeurologyLive® sat down with Crary, who offered background on the research that led the field to this point, as well as Gerardo “Jerry” Fernandez, MD, cofounder and chief scientific officer, PreciseDx. Fernandez provided information on the AI platform and how the technology is deployed in PD diagnosis.