This year, there have been numerous rumors that the Samsung Galaxy Watch 4 may finally feature the noninvasive blood sugar monitoring feature. These supply chain-based rumors suggest that the Apple Watch Series 7 could also feature the blood glucose monitoring functionality.
The latest research available today via a Samsung Patent shows how the company might approach the blood sugar monitoring use case.
The Samsung patent ‘Apparatus and method for estimating Blood Sugar based on Heterogenous spectrums” was approved today (03/23/2021).
Prior literature on monitoring blood sugar via spectroscopy either looked at Near Infra-Red spectroscopy or Raman Spectroscopy. A recent Apple patent also suggested methods to capture wavelengths beyond the 940nm wavelength to track new metrics.
Since invasive blood sugar meters may make users uncomfortable and there is a risk of infection, noninvasive blood sugar meters based on a spectroscopic analysis method capable of measuring a blood sugar level of intercellular liquid under the skin without using a needle have been developed.
- Facense Smartglasses for Health Monitoring can assist with blood pressure, blood sugar, and more.
- Masimo’s approach to noninvasive blood glucose monitoring and its fight with Apple
- Japanese startup to launch first noninvasive wearable glucose monitor
The challenge with existing noninvasive blood sugar meters in development is that they require a plurality of blood-collecting processes to generate calibration to produce the right blood sugar estimation model.
This Samsung research applies a combination of spectroscopy techniques to estimate an individual’s blood sugar correctly.
A first type spectrum may be a Raman spectrum, and a second type spectrum may be a near-infrared (NIR) spectrum.
The first type spectrum-blood sugar profile relationship model may be generated through machine learning based on training first type spectrum data and training blood sugar profile data.
The training blood sugar profile data may be obtained by performing an oral glucose tolerance test (OGTT) on a subject whose training first type spectrum data has been measured.
Using Raman spectroscopy, a spectrum-blood sugar profile relationship model may be generated through machine learning.
The second type spectrum measurer (NIR) may include a light source configured to emit light to the skin of the user and a spectroscope configured to detect absorbed, scattered, or reflected light from the skin of the user and measures the training second type spectrum data based on the detected light.
The processor may generate the individualized blood sugar model through machine learning.
Samsung plans to use heterogenous spectrums to make calibration easier and provide the correct blood glucose estimated value to users.
This recent patent and other recently approved Samsung patents in this area suggest that the big tech companies are in fact doing a tonne of work around using spectrometry for noninvasive blood glucose measurement, and we should not be surprised if the next Galaxy Active Watch 4 incorporates some of these novel technologies to help with noninvasive blood glucose monitoring.
The ability to use machine learning algorithms combined with a new generation of NIR sensors and improved battery technology on wearable devices makes this possible.
We will have to wait and see in a few months if the rumors prove themselves.