Naiad Lab is a technology company specializing in AI, Machine Learning (ML), and Deep Learning (DL) for healthcare needs. Our products provide AI & ML based solutions to problems affecting healthcare in the modern world.
Naiad Lab provides AI-based cloud services that detect abnormalities in medical tests and automating diagnoses. Specifically, we are active in the electrocardiogram (ECG) space.
Tell us about yourself?
I am a chemical engineer by training, graduate of University of Alberta. Shortly after graduating, I worked as an engineer in two different companies. I was always interested in data analytics, and how AI can shape predictive modelling.
After a terrible vehicle accident, I just decided to leave my current position and only do what I truly love. I ran into many people at the University of Alberta, such as Dr. Pierre Boulanger from computing sciences. We had a common ground and decided to make this our full time jobs.
If you could go back in time a year or two, what piece of advice would you give yourself?
I would say CUT DOWN YOUR SCOPE OF WORK. Really, we tried starting with a larger scope of work, a complex system with multiple components. Not only does this compromise path to market, it kills resources and stretches everyone thin.
Therefore, the best thing we did was to only work on one feature, making that one feature a valuable product and offering. This saves resources, keeps a slim and focused team.
What problem does your business solve?
Naiad Lab provides an automated ECG analysis system for live feedback and preventative model for health and wellness apps. In addition, cutting time for analysis and introducing an automation method.
This makes the end consumer far more informed in a shorter amount of time, adding precision and great experience.
What is the inspiration behind your business?
The main inspiration was seeing how many people were wearing watches and patches that collected ECG and other health markers, but nothing was being done with it. No useful feedback was being provided to users and actionable items.
This limited the use case. We had the intellectual property to train models and create a meaningful feedback system, starting with heart analysis via ECG. This data should not be wasted, but utilized for a far more efficient system.
What is your magic sauce?
The main way we differ is we apply four different algorithms on the collected data, that gets rid of noise, corrects for baseline wander, motion artifacts, and analyses for any diagnosis.
Our algorithms are our secret sauce. The correction for continuous monitoring does not really exist or is very primitive at the moment.
What is the plan for the next 5 years? What do you want to achieve?
From the product side, in addition to the ECG capabilities, we are working on developing algorithms for continuous glucose monitoring (CGM), for guided interpretation and predictive modelling.
We are also in the process of conducting R&D on different minimally evasive neck patches that can be used for continuous monitoring.
This neck patch, coupled with our algorithms, can provide the best health and wellness product to an end consumer. Imagine having a thin patch that can take data in live and provide end users with guided interpretation and action items, plus keeping a close eye on your health.
As a company, we are looking to grow and provide our service to different segments. We’d like to be a huge cloud based service provider to device, health and wellness, EMR and insurance companies across North America.
What is the biggest challenge you’ve faced so far?
Thus far, we have faced many financial challenges. Keeping the past few years of development afloat was a huge challenge. However, we pulled through with the founders contributing capital, and the team working for free for a long time.
It truly showed dedication from everyone. The other main challenge has been understanding on how to deploy your capability. You can have the greatest thing, but a wrong deployment or in the wrong market can kill it.
Like I said, in the beginning we also had a larger scope of work – trying to get many things done! A classic mistake for a start-up.
We just simply re-evaluated our schedule, resources and just kept asking “what is our strength?” In this way of thinking we came to the conclusion of cutting down the product and becoming a B2B focused service provider.
How do people get involved/buy into your vision?
I simply talk about what is out there right now, and what we have. The future potential of deep learning is limitless, with more training sets and experience.
I think it’s still in its infancy. Right now, we have wrapped up a contract with a company to provide our services. Our first integration has begun.
We want angel investors and other investors reaching out to us, we want to finalize our pre-seed round. In addition, we also want to collaborate with device companies that take health measurements to provide our algorithms for use.