The study, dubbed ‘Technical Feasibility of a Novel Sensor for Non-Invasive Blood Glucose Monitoring Compared to Dexcom G6’, was designed to determine the stability of hardware and software infrastructure, and validate the accuracy of its Bio-RFID sensor
US-based medical device company Know Labs has announced positive results for its non-invasive glucose monitoring sensor from its recent technical feasibility study.
The company conducted a series of internal studies from December last year through February this year to confirm the technical feasibility of its Bio-RFID sensor technology.
The technical feasibility study was designed to determine the stability of hardware and software infrastructure and to collect additional data to establish the accuracy of the sensor.
It measured blood glucose concentration (BGC) in five healthy participants, using its Bio-RFID sensor technology, compared with the Dexcom G6 as a reference device.
Know Labs chief product officer Steve Kent said: “We have successfully completed our foundational studies, we have a stable sensor that delivers repeatable results, and we have developed software infrastructure to manage and interpret large, novel datasets.
“As you increase sample size, it is expected that there are changes in accuracy, resulting from variability in testing conditions, biological diversity, and other factors.
“This is the goal of expanded data collection, and we will continue to share results as we collect more high-resolution data, from more participants, across more testing scenarios.”
Bio-RFID technology leverages electromagnetic energy in the form of radio waves to non-invasively capture molecular signatures and convert them into physiological information.
Across the five participants, 46 tests were conducted using 92 samples, and 4.7 million data points were collected per sample, which makes up around 430 million data points for all samples.
Know Labs collected the data using sweeps across the 500MHz to 1500 MHz range at 0.1MHz intervals, collecting values at 10,001 frequencies per sweep, on a continuous basis.
The company used data from the Bio-RFID sensor was used to train a neural network (NN) model to predict BGC readings of the Dexcom G6 reference device, as a proxy for BGC.
The study performed with 46% of predictions within the US Food and Drug Administration’s (FDA) recommended limit for accuracy for new blood glucose monitors, said the medical device company.
Know Labs CEO and chairman Ron Erickson said: “Today’s methods of testing BGC come with several disadvantages, from the pain of finger pricks and inserting probes for continuous monitors to the high cost and environmental waste these methods produce.
“This study demonstrates our progress toward getting the first FDA-cleared non-invasive glucose monitoring device in the hands of the nearly 40 million people living with diabetes in the US.
“We’ve achieved so much over the last several months. We’ve refined data collection methods and increased our participant population, with our dataset growing from 3 in our exploratory study to 92 in this study, a 30-fold increase in the sample size.”