Revealing Possibilities

In the Fight Against
Alzheimer's and Dementia

The Problem

Age-related cognitive decline, mild cognitive impairment, and progression to other Alzheimer’s Disease-related dementias affects the well-being of older adults, their families and caregivers.

Sixteen million individuals in the US are living with mild cognitive impairment, a precursor to Alzheimer’s Disease.

The total cost of health care and long-term care-related payments in 2020 for all individuals with dementia was estimated at $305 billion.

There are currently no pharmacologic solutions and no other treatments with strong evidence for the prevention of age-related cognitive decline, mild cognitive impairment, or progression to clinical Alzheimer’s-type dementia.

The Solution

Incite is innovative in four primary respects:

First

Unsupervised, home-based Neurofeedback training for cognitive enhancement, rather than meditation, sleep, or relaxation

Second

The application of deep learning to correctly classify cognition performance that can then be applied to a tablet, by way of the application of transfer learning

Third

The use of transfer learning to make the brainwave characteristics and feedback thresholds individualized across users, and adaptive as a user’s brainwave activity changes over time

Fourth

The integration of machine learning-derived brainwave characteristics to drive the volume of individually selected music

Incite is innovative in five primary respects:

Unsupervised, home-based NFB training for cognitive enhancement, rather than meditation, sleep, or relaxation.

The application of deep learning to correctly classify cognition performance that can then be applied to a tablet, by way of the application of transfer learning.

The use of transfer learning to make the EEG characteristics and feedback thresholds individualized across users, and adaptive as an individual user’s EEG activity changes over time.

The integration of machine learning-derived EEG characteristics into the volume control of music, in which EEG characteristics in addition to behavioral responses adjust the volume of the music.

Gap in Knowledge:

The National Institute on Aging of the National Institutes of Health asked the National Academies of Sciences, Engineering, and Medicine to examine and comment on the state of knowledge about what works in preventing or slowing cognitive decline and dementia.

The Agency for Healthcare Research and Quality (AHRQ) systematic review identified no specific interventions that are supported by sufficient evidence to encourage people to adopt them for the purpose of preventing cognitive decline and dementia. The systematic review did, however, find some degree of support for the benefit of three classes of intervention: cognitive training, blood pressure management, and increased physical activity.

The AHRQ review states additional research is needed to further understand and gain confidence in the effectiveness of these interventions.

Recent research has shown anatomical changes and cognitive performance improvement in older adults using Electroencephalographic (EEG) Neurofeedback (NFB). In one study, healthy elderly people and patients with prodromal Alzheimer’s Disease showed improved visuospatial memory performance after NFB training. Analysis revealed changes in cerebral connectivity over the course of the training.

Another randomized, placebo-controlled study involving seventeen older adults showed that NFB can benefit brain reserve in an aging population.

Few products are available for cognitive improvement and none use advanced machine learning to apply cutting edge computer science to an in-home effective product.

Preliminary Studies:

Work began in 2016 using an Emotive wet electrode headset to study brain waves associated with cognitive function. In 2018, Preveal assembled a team to begin full scale research and in 2019, a study was conducted to determine the feasibility of using a dry electrode headset, wirelessly connected to a laptop, with off-line data processing, to extract EEG features associated with peak working memory. The results were consistent with published EEG analyses during working memory testing using wet electrode headset systems.

In 2019, work began to determine whether a deep learning pipeline could be used to successfully differentiate EEG patterns in which participants were performing mental arithmetic from those at rest with no cognitive load. The validation accuracy was 78.8% for the differentiation of mental arithmetic from resting state.

About Us

The Company
The Team

Preveal Technologies, Inc. is a health technology start-up located in Spokane, Washington. Our focus is the application of in-home neurofeedback for cognitive enhancement and prevention or delay of onset of neurodegenerative diseases. Preliminary research has proven effectiveness of the headset design and the deep machine learning algorithm. Preveal has received a grant from the National Institute on Aging. The grant is through the a2 Collective “to fund promising technology demonstration projects with a clear path to commercialization, translational milestones, or technology transfer at the intersection of artificial intelligence (AI) and healthy aging.” We are seeking investor funding to conduct a feasibility study.

Dr. Robert Hager

President

Dr. Robert Hager is President of Preveal Technologies, an aerospace engineer and entrepreneur. He brought two companies from a vision to successful and thriving organizations and, under contracted by Teledyne Monitor Labs, developed an in-stack analyzer to measure, in real time, concentrations of four pollutants in emitted smoke using machine learning software. He will be responsible for market research, project logistics, and will directly oversee all of the company activities.

Dr. Lonnie Nelson

Neuropsychologist

Dr. Lonnie Nelson is a clinical rehabilitation neuropsychologist and Associate Professor in the Washington State University College of Nursing with over a decade of experience in NFB in both clinical and research contexts. He will advise the team regarding the EEG signal quality and neuropsychological aspects of neuro-integrated game play for cognitive enhancement.

Dr. Hassan Ghasemzadeh

A.I. Expert

Dr. Hassan Ghasemzadeh is an associate professor of biomedical informatics and the director of Embedded Machine Intelligence Lab (EMIIL) at Arizona State University and is an internationally recognized expert in artificial intelligence, including machine learning, deep learning, and transfer learning.

Mr. Will Clegern, MS

R & D Director

Mr. Will Clegern, MS directs the Biomedical Engineering and Design Service Center at Washington State University’s Health Sciences Campus in Spokane, Washington. He will be responsible for the design and construction of the adjustable, wireless, 6-lead dry detector headset and interface of the headset with the tablet to enable neuro-integrated game play.