Transforming Alzheimer's Screening through AI
We use portable brainwave scanning technologies and Artificial Intelligence to make early Alzheimer's diagnosis a reality.
Website or social media url(s) (optional):
Date You Started Your Project Started
Project Stage: Select the description below that best applies to your approach.
Growth (have moved past the very first activities; working towards the next level of expansion)
1. The Problem: What problem are you helping to solve?
Alzheimer's Disease is the 6th leading cause of death in the United States, costing Americans more than $259 billion dollars annually. Underlying changes in the brain of an Alzheimer's patient may happen years before initial clinical signs are shown, making an Alzheimer's diagnosis always happen too late. There is currently no routine Alzheimer's screening tool since bio-imaging modalities like PET scans are only used after cognitive decline.
2. Your Solution: How are you planning to solve this problem? Share your specific approach.
The Synapto device encompasses the application of machine learning and artificial intelligence in EEG data collected through portable EEG on diseased clinical populations. Brainwaves of patients with Alzheimer's pathology are inherently different, and the use of AI helps us identify these patterns that humans by themselves cannot do. A patient would take a simple 10 minute test where they put on a cap that collects their brainwaves, and the artificial intelligence algorithms in the back-end would output a diagnostic class based on previously collected data in Alzheimer's and healthy patients. We recently conducted a clinical pilot study collaboration with New Castle University in the United Kingdom to evaluate and build the model on 50 patients. Our AI models utilizing a certain EEG biomarker/feature performed higher than literature and better than competitor values at a 86% diagnostic accuracy, 94% sensitivity, 74% specificity, and 0.88 ROC AUC. We're exploring both non-linear functional connectivity biomarkers that evaluate brain functional connectivity architecture as well as linear markers that utilize Fast Fourier Transforms to understand overall neural activity.
3. Personal Journey: What’s the story behind why you decided to start this project?
My (Dhruv) grandfather was diagnosed with Alzheimer’s as I was graduating high school. As traumatic of an experience the initial diagnosis was, he started presenting with very conflicting/complicated symptoms like strokes, hemorrhages, and other deficiencies. We weren’t even sure if he had dementia due to AD anymore. I was extremely frustrated at the whole process and didn’t understand why patients were diagnosed so late. I wanted to do something to shift the status quo. My (Chris) great grandmother passed away from AD. I don’t remember her well, but I remember the frustration our family went through. As I grew up, I learned more about how our family got a late diagnosis for her, and how convoluted it was. I learned how little was known about the disease. I realized that without early diagnosis, we can never make a treatment for AD. I immediately knew I wanted to tackle early diagnosis.
4. Selfie Elevator Pitch: Include 1-minute video that answers the following “I am stepping up to make change because...”
One of the most challenging aspects of the disease is early diagnosis. Changes in the brain may happen up to a decade before clinical signs are presented, and by that time its too late. We're using portable EEG + AI models to make an Alzheimer's screening a routine process in even those who appear cognitively normal. We won the 1st place prize from NIH ($20K), have run several clinical pilot study collaborations to generate 86%+ accuracy, and are now partnering with Georgetown Med for trials.
5. Example: Please walk us through a specific example of what happens when a person or group gets involved with your project.
Our product hasn't been available yet due to FDA regulation, however from our Public Releases, we have gotten contacted countless times from people who want to use the device and are afraid of getting the disease because their family members have had it in the past. Earlier diagnosis offers the patients and caregivers numerous economic and societal benefits. Becoming aware of the disease earlier also enables patients and their caregivers to plan for their future by creating health directives, making financial and legal arrangements, as well as addressing safety issues/counseling on how to deal with behavioral changes associated with progression. Patients become eligible for novel clinical trials, and could potentially slow progression of disease if drugs are started early enough. Physicians are also able to better manage co-morbid conditions, thus overall improving clinical outcomes.
6. The X Factor: What is different about your project compared to other programs or solutions already out there?
Clinicians are trying to use cognitive assessments to routinely screen for Alzheimer's patients in those who appear cognitively normal, however the success has been widely debated: (1) cognitive assessments are qualitative and aren't specific enough to pick up on cognitive impairment due to AD (2) cognitive assessments such as MMSE/MoCa are prone to education, etc... biases. Scientists have reported classification accuracies from 14-21%, much higher than our reported statistics (Q2). There are other EEG companies trying to diagnose AD however none use AI and are specific enough to AD.
7. Impact: How has your project made a difference so far?
We've engaged millions of people through social media and news: millions have liked, viewed, and shared the Freethink documentary along with other releases; Our message and work is spreading internationally! We have spoken to dozens of doctors, and most have given the feedback that they would trust our device if it were FDA cleared. Towards that goal we have had a pre-submission and applied to a breakthrough device designation. Some physicians and clinicians that have said they would adopt this device when FDA cleared, include Dr.David Merrill, MD, PhD, Dr.William Crevier, MD, Dr.Jason Brandt, PhD, and several others. We expect physician adoption to be seamless, as our product can already be successfully reimbursed by insurance companies for the EEG acquisition alone at $400 minimum. We hope to deploy the software + hardware bundle to physicians as soon as it is legally possible.
8. What’s Next: What are your ideas for taking your project to the next level?
We recently completed a clinical study collaboration with New Castle University and are now looking to partner with Georgetown Medical Center to conduct a larger clinical data study to further build the algorithms for our target population. This clinical study will drive algorithm development and form the basis for the clinical trial that will be used to clear the device for market. We're also looking to obtain Breakthrough Device Designation from the FDA and raise capital through NIH STTR funding & venture capital funding to continue drive product development and innovation.
9. Which of the following types of expertise would be most useful for you?
10. Finances: If applicable, have you mobilized any of the following resources so far?
Donations between $100-$1k
Donations between $1k-$5k
Donations over $10k
How did you hear about this challenge?
Ashoka page or contact