Cofounder and chief scientific officer, PreciseDx

Gerardo “Jerry” Fernandez, MD

“The disruptive technology is digital pathology combined with artificial intelligence. We’re seeing AI algorithms get deployed in a lot of different contexts, [but] it’s only recently that the ability to scan and digitize histological preparations has become feasible.”

In recent years, as has been the case for many technologies leveraged by the medical field, the COVID pandemic has accelerated the need for more digital and virtual tools for care. For pathologists, such as John F. Crary, MD, PhD, this has allowed for the use of digital pathology images, which has, in turn, opened the door for the incorporation of artificial intelligence (AI) to enter into the fold.

Crary, a professor of pathology, neuroscience, and AI & human health at the Icahn School of Medicine at Mount Sinai, has been working with such technology alongside Gerardo “Jerry” Fernandez, MD, the cofounder and chief scientific officer of PreciseDx, which has developed an AI algorithm that works with its Morphology Feature Array to help in these very situations. In a recent study conducted by Crary and colleagues showed that the algorithm 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, the AI Morphology Feature Array outperformed human pathologists with an accuracy of 0.69 compared with 0.64 in the prediction of clinical PD status.

 Fernandez and Crary offered background on the AI algorithm that’s been developed by Precise Dx and shared their experience with the process improvements that have been brought about by this shift to digital pathologies and AI-assisted diagnosis. Additionally, Crary offered his perspective on the role AI can play in neuropathology in the future.

REFERENCES
1. Signaevsky M, MArami B, Prastawa M, et al. Antemortem detection of Parkinson's disease pathology in peripheral biopsies using artificial intelligence. 

. 2022;10(1):21. doi:10.1186/s40478-022-01318-7
2. PreciseDx's AI-Enabled Digital Pathology Is the First Proven to Detect Early-Stage Parkinson's Disease. News release. PreciseDx. April 20, 2022. Accessed May 4, 2022. https://www.prnewswire.com/news-releases/precisedxs-ai-enabled-digital-pathology-is-the-first-proven-to-detect-early-stage-parkinsons-disease-301528441.html

Videos

The neuropathologist at Mount Sinai and chief science officer of Precise Dx pairing spoke to the role of artificial intelligence in the diagnosis of diseases from peripheral tissue biopsies and its ability to improve neuropathology. [WATCH TIME: 8 minutes]

The Future of Digital Neuropathology and the Role of AI: John F. Crary, MD, PhD; Gerardo Fernandez, MD

“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.

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, 

 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.

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]

Gerardo “Jerry” Fernandez, MD

Articles

The Future of Digital Neuropathology and the Role of AI: John F. Crary, MD, PhD; Gerardo Fernandez, MD

PreciseDx's AI Morphology Feature Array for Detecting Parkinson Disease Pathology: John F. Crary, MD, PhD; Gerardo Fernandez, MD

Latest News