New Study Shows AI-Powered Diabits App Can Improve Blood Glucose Control

The study, now published in the JMIR academic journal, examines the predictive accuracy of Diabits and the correlation between daily use of the app and blood glucose control

VANCOUVER, British Columbia, Sept. 23, 2020 (GLOBE NEWSWIRE) -- Bio Conscious Technologies Inc. (“Bio Conscious”), a Prevention-as-a-Service™ technology company using machine learning to predict and prevent complications from chronic diseases, is announcing that its latest study assessing the capabilities of its Diabits app, has just been published in the JMIR Academic Journal.

Diabits is an artificial intelligence (AI) powered diabetes management app for people with type I and type II diabetes who use a continuous glucose monitor (CGM) to monitor daily blood sugar fluctuations. Using data from CGMs and user input, Diabits applies machine learning techniques to create personalized patient models and predict the patient’s future glycemic fluctuations.

The study shows that Diabits accurately predicts future glycemic fluctuations 60 minutes into the future, potentially making it easier for patients with diabetes to maintain their blood glucose in a healthy range, and that an improvement in glucose control was observed on days with more frequent use of the Diabits app.

The study used real app users’ data to examine the predictive accuracy of the app and the correlation between daily use of the app and the users’ ability to keep their blood glucose within the healthy range.

Results based on over 6.8 million data points evaluated using Parkes (Consensus) Error Grid showed that:

  • 30-minute Diabits predictions were 86.89% clinically accurate and 99.56% clinically acceptable
  • 60-minute predictions were 70.56% clinically accurate and 97.49% clinically acceptable

The study also analyzed the daily use statistics and corresponding CGM data for the 280 longest-standing Diabits users, and it was established that, under normal use conditions, Average blood glucose for the days that these users used the app was 154.0 mg/dL, with 67.52% of the time spent in the healthy 70-180 mg/dL range

  • For days with 10 or more Diabits sessions, the average blood glucose decreased to 141.6 mg/dL (P < .0005), while the time within a healthy glucose range increased to 74.28% (P < .0005).

“Diabetes is a major public health challenge that affects hundreds of millions of people worldwide, and these patients must consistently monitor their glycemic levels in order to keep them in a healthy range. CGMs provide users with real-time information on their glycemic fluctuations, but we are taking this one step further and providing accurate blood glucose predictions to help patients take preemptive actions to better manage their conditions,” said Amir Hayeri, CEO of Bio Conscious.

Increasing time spent within a healthy glucose range is associated with decreased risk of hypertension, cardiovascular disease, and chronic kidney disease, and other major health complications that people with diabetes face as they age.

“We are very pleased with the results of this study. We are working toward 100% clinically acceptable predictions, but this is not yet achieved due to measurement errors and unknown future events, but we are confident about our methods and excited about the potential of our technology,” added Hayeri.

Read the full study:

About Bio Conscious Technologies Inc.
Bio Conscious Technologies Inc. (“Bio Conscious”) is a Prevention-as-a-Service™ company focused on developing proprietary machine learning technology that analyzes glucose fluctuations in the body and its impact on metabolism. This enables preventive and personalized care for diabetes, hypertension, heart disease, and a wide range of other medical conditions. Bio Conscious is working toward a Novel Therapeutic (De Novo) designation from the FDA for the use of its preventive technology in diabetes. Learn more:

Media Contact:
Brittany Whitmore
Exvera Communications inc.
Phone: 1-415-712-2490