Know Labs Publishes Study on Non-Invasive Diabetes Screening Device
Know Labs, Inc. (NYSE:KNW), a leading developer of non-invasive medical diagnostic technology, today announced the publication of its peer-reviewed study in Diabetes Technology & Therapeutics Journal titled, “A Glycemic Status Classification Model Using a Radiofrequency Noninvasive Blood Glucose Monitor.” Diabetes Technology & Therapeutics is a leading, peer-reviewed journal covering all aspects of diagnosing and managing diabetes with cutting-edge devices, drugs, drug delivery systems, and software.
The published clinical research results demonstrate that Know Labs’ proprietary non-invasive radiofrequency (RF) dielectric sensor and trade-secret machine learning (ML) algorithms correctly classified an individual’s glycemic status as hyperglycemic, normoglycemic, or hypoglycemic with 93.37% accuracy compared to venous blood glucose values–serving as an early proof-of-concept for a novel, non-invasive diabetes screening device.
Today, more than 500 million people worldwide are living with diabetes, with 75% residing in low and middle-income countries and an estimated 240 million people worldwide remaining undiagnosed. Expanding the potential application of the recently announced KnowU™ beyond non-invasive continuous blood glucose monitoring, the non-invasive screening device could support underserved global populations by facilitating early identification and intervention—potentially reducing diabetes-related hospitalizations and increasing access globally.
“Early diagnosis and intervention for diabetes are critical to both improving patient outcomes and enabling healthcare systems to allocate resources more economically and efficiently,” said Ron Erickson, CEO and Chairman at Know Labs. “This proof-of-concept for the use of our novel RF sensor as a glycemic status screening tool indicates the device’s potential to help funnel previously undiagnosed patients more effectively into the healthcare system.”
Study Design
The study included 31 participants aged 18-65 with prediabetes or Type 2 diabetes. Know Labs’ RF sensor continuously scanned participants' forearmsfor up to two, three-hour sessions each during a 75g Oral Glucose Tolerance Test, and a third session in which water was given instead of liquid glucose to act as a control. Concurrently, venous blood draws were taken every five minutes and measured with an FDA-cleared glucose hospital meter system to create 2,637 paired observations. Data was preprocessed using smoothing techniques and an 80/20 split was performed to create model training and test datasets, respectively. Know Labs trained a Time Series Forest ML model to estimate reference venous blood glucose values on 80% of the data consisting of 2,109 paired RF device and venous blood glucose values randomly selected from the total dataset and then tested on the remaining, held-out 20% (528 paired values).
| 1 |
|
|
Results
The findings show that from the total test dataset of 528 paired values, the model correctly classified glycemic status 93.37% of the time as hyperglycemic, normoglycemic, or hypoglycemic. The model achieved sensitivities of 96.63% and 85.51% for normoglycemic and hyperglycemic classes, respectively. Specificities were 84.51% and 96.92%. More data is required in the hypoglycemic range to evaluate sensitivity and specificity in that glycemic class. Importantly, none of the hyperglycemic values were categorized as hypoglycemia, and none of the hypoglycemic values were categorized as hyperglycemia.
The results support the accuracy of Know Lab’s proprietary non-invasive RF dielectric sensor and ML techniques for glycemic status classification. Further research is needed to enrich the dataset for categorical screening and improve the accuracy and sensitivity of each glycemic status.
Efforts led by President, International, Chris Somogyi, will aim to expand this application beyond proof-of-concept alongside potential strategic partners for a Rest of the World (RoW) product that exploits Know Labs’ proprietary RF technology for use as a screening device. This will occur in parallel, as the Company maintains its core focus on bringing the first FDA-cleared non-invasive continuous glucose monitor to the marketplace.