If you have diabetes, or have suspected you do, you will have done the thing of poking your finger and smearing blood on a toothpick until your finger goes numb. Fingerstick blood glucose monitoring is the de facto standard, but the AI company Scanbo wants to do away with all that by replacing the droplet with some ready-to-use diagnostic tools and a big help in data analysis.
The company has developed a prototype device that combines one of three leads ECG measurement it is a Photoplethysmgram (PPG). The 60-second measurement is powered by a set of algorithms that can provide some very promising measurements. For starters, the device is monitoring blood glucose non-invasively, but the company’s founder says it can also take blood pressure measurements.
I spoke with the company’s founder and CEO, Ashissh Raichura, as part of Ploonge’s virtual coverage at CES, where he told me a little more about the technology. He also gave me a demonstration, first testing his own blood with a conventional fingerstick blood glucose monitor, and then with the company’s own prototype. The measurements were 6.2 and 6.3 mmol/L, respectively, which puts the two devices within a few percent of each other’s accuracy.
“We use the three electrodes for ECG data and an additional measurement for PPG. We measure for 60 seconds and then take the raw data and analyze it using the machine learning convolutional neural network and the deep neural network. We combine all this data, take the three machine learning algorithms, see the result and analyze the glucose,” Raichura told me, as he prepared to demonstrate the device to me. “We want to market our product and will seek US FDA approval from Health Canada.”
I was surprised to learn that it is possible to take non-invasive blood glucose measurements – most so-called non-invasive methods use a deploy or one filament sensor wire to get readings, but the method that Scanbo uses has been studied and covered in medical journals.. It appears that the FDA has yet to approve any products that take this approach, so the company is certainly facing a lengthy medical approval process to get its products to market.
The company also claims that it is capable of taking blood pressure measurements, the kind you can take at home or in the doctor’s office with a blood pressure cuff.
“When we take their EKG data, we convert it into what’s called the short wave transmission length,” sums up Raichura on how the company is able to get the blood pressure metrics. “Based on that, we also calculated your non-invasive blood pressure without a cuff. This is another piece of algorithm that we have patent pending.”
With all this technology in the pocket, the company has an interesting choice to make; Will you start making your own hardware devices or is there an opportunity to license the algorithms and technology to other manufacturers that already have PPG and ECG enabled devices on the market?
“We have two patents pending, purely on the hardware, how we designed it, how we amalgamate the electrodes and all the sensors in a way that we can get all the parameters at once,” explains Raichura, suggesting how the company is trying to measure all the things at once. “If you look at all the traditionally available devices, you measure one thing at a time, not all at once. You take your blood pressure once, your ECG another. One after another, all in sequential processes. In our case, we’re asking you to put four fingers on the device so we can capture all the data and use algorithms to report different aspects of your health.”
Scanbo sees its technology as a domestic alternative to some of the existing clinical techniques and technologies today.
“As a company, we are a combination of AI and medical technology,” says Raichura, noting that the market is starting to take notice. “With this product, we are just getting started now. Medtronic, Samsung, LG and others are already talking to us and we’re seeing if we can collaborate with them, and we’re exploring some strategic partnerships that can help us take us to different markets globally. We see the needs of 400 million people worldwide with type 2 diabetes, and most populations cannot afford glucometers – let alone continuous blood glucose meters. We are very, very profitable, and we can reduce the cost to as low as $20 a month. There’s no biowaste, you don’t need disposables, you don’t need strips or anything, just the machine learning algorithm and a rechargeable battery device.”
The company is about to use its prototype and clinical results as leverage to raise a seed round and begin the regulatory approval process and eventually make a product available to the public.