In a collaboration with The Michael J. Fox Foundation, de novo study finds PreciseDx’s technology can accurately diagnose Parkinson’s disease in living patients prior to severe onset of symptoms
PreciseDx, recently spun out from the Mount Sinai Health System in New York, NY, is the only Cancer Risk Stratification company to provide patient-specific risk information through the analysis of morphology features. The company today announced its AI-enabled digital pathology technology can accurately diagnose Parkinson’s disease (PD) in living patients prior to severe onset of symptoms.
Diagnosing Parkinson’s disease is challenging at all stages due to variable symptoms, comorbidities, and mimicking conditions, with definitive diagnosis only coming postmortem. This groundbreaking study found that PreciseDx’s AI-enabled technology is able to facilitate a conclusive diagnosis of Parkinson’s, providing critical information for earlier treatment.
“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 The Michael J. Fox Foundation for Parkinson’s Research (MJFF). “Objective diagnostic tools, especially early in disease, are critical to drive care decisions and to design trials toward better treatments and cures.”
MJFF partially funded the AI analysis and sponsored the study that provided the data (the Systemic Synuclein Sampling Study).
The PreciseDx study applied the company’s AI algorithms (Morphology Feature Array™) for the IHC detection of α-synuclein within peripheral nerves of salivary glands [i.e., peripheral Lewy-type synucleinopathy (LTS)], along with quantitative feature extraction using morphology features to accurately distinguish LTS in early-stage Parkinson’s disease biopsy specimens based upon expert pathologist annotation of the training samples. Following training, the algorithmic test was validated using a separate set of confirmed biopsy specimens.
PreciseDx’s AI Morphology Feature Array was able to detect Parkinson’s pathology in image patches from biopsy samples with 99% sensitivity and 99% specificity as compared to expert annotated ground truth. The AI edged out the human pathologist with an accuracy of 0.69 versus 0.64 in the prediction of clinical Parkinson’s disease status.
PreciseDx’s MFA approach to feature extraction and analysis enables new algorithms to be developed and validated against clinical endpoints. This is extremely valuable to create new diagnostic tests, accurate and reproducible diagnosis, prognosis, patient selection of therapy for a wide range of 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 (MFA) can examine thousands of different features and leverage those relationships between them,” said John F. Crary, MD-PhD, a Professor in the Departments of Pathology, Neuroscience, and Artificial Intelligence & Human Health at 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. This enlightens the industry to a direct case study into how computational pathology can truly advance medicine in terms of accurately identifying and detecting diseases.”
“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.
The cancer risk stratification technology is based on intellectual property developed by Mount Sinai faculty and licensed to PreciseDx. Mount Sinai and Mount Sinai faculty have a financial interest in PreciseDx. Mount Sinai also has representation on the PreciseDx Board of Directors, which includes Dr. Lium.
To view the full study, visit: https://pubmed.ncbi.nlm.nih.gov/35164870/
For more such updates and perspectives around Digital Innovation, IoT, Data Infrastructure, AI & Cybersecurity, go to AI-Techpark.com.
