Know Labs, Inc. announced interim results from its most recent clinical research study. The study assessed the accuracy of Know Labs? proprietary radiofrequency (RF) dielectric sensor in non-invasively measuring blood glucose in participants with prediabetes and Type 2 diabetes using venous blood as a comparative reference ?

resulting in an overall Mean Absolute Relative Difference (MARD) of 11.1%. Study Design: This is Know Labs? first clinical research protocol involving people with diabetes and using venous blood as comparative reference.

The proprietary RF sensor employed in the study measures glucose levels using dielectric spectroscopy by rapidly scanning a large range of RF frequencies and recording voltage values detected at each frequency to quantify, with trade-secret machine learning (ML) algorithms, real-time continuous blood glucose levels. The sensor continuously scanned participants' forearms during 21, three-hour sessions involving a 75g Oral Glucose Tolerance Test. Venous blood samples were collected using a peripheral intravenous catheter every five minutes and analyzed using an FDA-cleared blood glucose hospital meter as a reference device.

Data was prepossessed using smoothing techniques and an 80/20 split was performed to create model training and test datasets, respectively. Know Labs trained a Light Gradient Boosting Machine model on data consisting of 520 paired RF and reference blood glucose values, then tested on 130 held-out paired values. Results: On the held-out test dataset, blood glucose was estimated with a MARD of 11.1 ± 2.1% relative to venous blood.

Similar accuracy was observed in normoglycemic (11.0 ± 2.7%) and hyperglycemic (11.5 ± 3.1%) ranges. In previously published studies, most of the data collected was within the normoglycemic range (70 to 180 mg/dL) and glucose values from a popular CGM were used as comparative reference. By including participants with Type 2 diabetes, this study significantly increased the number of data points outside the normoglycemic range, specifically within the hyperglycemic range (>180 mg/dL).

Demonstrating similar accuracy across both ranges is an important milestone in Know Labs? technology development roadmap. While many devices typically underperform outside the normoglycemic range, these results suggest that the novel RF sensor, paired with trade-secret ML algorithms, holds considerable promise for the non-invasive measurement of blood glucose.

Last week, Know Labs announced the KnowU, its wearable, non-invasive CGM that incorporates the sensor the Company plans to submit to the FDA for clearance. Know Labs will exhibit the KnowU device at the ATTD Tech Fair (Booth #30) throughout the conference and during a dedicated session presentation on Thursday, March 7 from 4:30-4:40 p.m. CET. Know Labs will also sponsor an invitation-only luncheon hosted by Children With Diabetes (CWD), where prominent thought leaders in the diabetes management field will discuss the latest in non-invasive glucose monitoring innovation.

These early results are part of a larger, now completed clinical trial with up to 100 participants focused on a population with diabetes and prediabetes, conducted September 2023 through February 2024. During 2024, Know Labs will also deploy the KnowU in large-scale, external clinical trials while making refinements to the device and its algorithms. These new studies will help determine the technology?s performance throughout continuous wear, in more real-world environments, and within more expansive glycemic ranges, including the hypoglycemic range (<70 mg/dL).