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]
WATCH TIME: 8 minutes
“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.1,2
In a conversation with NeurologyLive® 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.