Clinical performance testing of neuropacs in Parkinsonism diagnosis

PROJECT SUMMARY
The growth rate in the number of people diagnosed with Parkinsonism is substantial. Estimates indicate that
from 1990 to 2015 the number of Parkinsonism diagnoses doubled, with more than 6 million people currently
diagnosed. By 2040, there will be 12 to 14 million people diagnosed with Parkinsonism. Parkinson’s disease
(PD), multiple system atrophy Parkinsonian variant (MSAp), and progressive supranuclear palsy (PSP) are
neurodegenerative forms of Parkinsonism, which can be difficult to diagnose as they share similar motor and
non-motor features, and they each have an increased chance of developing dementia. In the first five years of a
PD diagnosis, about 58% of PD patients are misdiagnosed, and of these misdiagnoses about half have either
MSAp or PSP. Since PD, MSAp, and PSP require unique treatment plans and different medications, and clinical
trials testing new medications require the correct diagnosis, there is an urgent need for clinical and clinical trial
ready diagnostic markers. A promising approach to identify different forms of Parkinsonism is diffusion magnetic
resonance imaging (MRI), as there is no contrast drug, the technique is safe, and is already used clinically in
traumatic brain injury and stroke. Using this approach is advantageous because MRI acquisition is compatible
with standard clinical practice when evaluating suspected Parkinsonism in patients and can be performed rapidly
on widely available 3 Tesla MRI systems. Automated Imaging Diagnostics is developing a commercial software
called neuropacs™, a high-throughput brain image processing and AI-powered precision diagnostic tool to assist
in the diagnosis of PD, MSAp, and PSP. Results from our Phase I program have established clear technical
feasibility and the data indicate neuropacs™ is robust in the clinical classification of PD, MSAp, and PSP with
>90% accuracy. Our next goal in this Phase II project is to perform a pre-market field evaluation of neuropacs™.
We will perform a clinical performance study to determine how the addition of neuropacs™ into workflows of
board-certified neurologists affects diagnostic accuracy of PD, MSAp, and PSP. A second major objective is to
validate the accuracy of neuropacs™ for predicting gold-standard pathological diagnosis. This is an important
validation step because other available technologies fail to distinguish patients using pathological markers of
Parkinsonism, including dopamine deficiency and brain atrophy. This Phase II project will further our efforts to
develop a high-precision clinical decision support tool for Parkinsonism and position our company to achieve
FDA biomarker approval and device qualification milestones.

Grant Number: 5R42NS132614-03
NIH Institute/Center: NIH
Principal Investigator: Angelos Barmpoutis