Predictive A1c Based on CGM Data Using CGM Data (A1c)

The Prediction of A1c Based on CGM Data Through Applying Machine Learning Approaches

Introduction. The hemoglobin A1C (HbA1c) reflects the average blood glucose level for last two to three months. Recent advancements in the sensor technology facilitate the daily monitoring of the blood glucose using CGM devices. The future prediction of the HbA1C based on the CGM data holds a critical significance in maintaining long term health of diabetes patients. A higher than normal value of the HbA1c greatly increases the likelihood of diabetes related cardiovascular disease.

Goal. The aim this study is to predict the HbA1c in advance by utilizing the CGM data through applying machine learning techniques. The outcomes of this research will assist in improving the health of diabetic patients.

Methods. This is a retrospective analysis. The investigators will de-identify and analyze 120 patients with T1D who using CGM sensor for last three months. Past 15 days of CGM data will be analyzed and different glucose variability features such as time in range (TIR), coefficient of variation (CV), mean amplitude of glycemic excursion (MAGE), mean of daily differences (MODD), continuous overall net glycemic action (CONGA) will be extracted. A machine learning model will calculate (predict) HbA1c in 2-3 months advance based on these 15 days of CGM data. To evaluate the performance of the proposed prediction model, predicted HbA1c will be compared with the real HbA1c.

Study Overview

• Status: Completed
• Conditions: Diabetes Mellitus, Type 1
• Intervention / Treatment: Device: Flash Glucose Monitoring; Other: A1c; Other: Predictive A1c

Detailed Description

This is a retrospective analysis. The investigators will de-identify and analyze 120 patients with T1D using Continuous Glucose Monitoring (CGM) system for last three months. Past 15 days of CGM data will be analyzed and different glucose variability features such as time in range (TIR), coefficient of variation (CV), mean amplitude of glycemic excursion (MAGE), mean of daily differences (MODD), continuous overall net glycemic action (CONGA) will be extracted. A machine learning model will be developed to predict HbA1c in 2-3 months advance based on these 15 days of CGM data. The model is using linear regression, penalized regression (Ridge regression, Lasso regression and Elastic net regression) in combination gradient boosting to calculate predictive A1c

• Study Type: Observational
• Enrollment (Actual): 60

Contacts and Locations

Study Locations

• Qatar
  • Qa
    • Doha, Qa, Qatar, 26999
      • Sidra Medicine

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 2 years to 18 years (Child, Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

Patients with Type 1 Diabetes and Flash glucose monitoring

Description

Inclusion Criteria:

• Type 1 Diabetes
• Flash glucose Monitoring system

Exclusion Criteria:

• Less than 70% od CGM data in the last 90 days.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The difference of Predictive A1c level from CGM data with Real A1c level from EMR	Difference (%) between Predicted A1c and laboratory A1c from the Electronic Medical Record	3 months

Collaborators and Investigators

• Sponsor: Sidra Medical and Research Center
• Investigators: Principal Investigator: Marwa Qaraqe, PhD, Hamad Bin Khalifa University, Doha; Principal Investigator: Hasan Abbas, PhD, TAMUQ, Doha

Publications and helpful links

General Publications

• Alberti KG, Zimmet PZ. Definition, diagnosis and classification of diabetes mellitus and its complications. Part 1: diagnosis and classification of diabetes mellitus provisional report of a WHO consultation. Diabet Med. 1998 Jul;15(7):539-53. doi: 10.1002/(SICI)1096-9136(199807)15:73.0.CO;2-S.
• Ball MJ, Lillis J. E-health: transforming the physician/patient relationship. Int J Med Inform. 2001 Apr;61(1):1-10. doi: 10.1016/s1386-5056(00)00130-1.
• Ogurtsova K, da Rocha Fernandes JD, Huang Y, Linnenkamp U, Guariguata L, Cho NH, Cavan D, Shaw JE, Makaroff LE. IDF Diabetes Atlas: Global estimates for the prevalence of diabetes for 2015 and 2040. Diabetes Res Clin Pract. 2017 Jun;128:40-50. doi: 10.1016/j.diabres.2017.03.024. Epub 2017 Mar 31.
• Rohlfing CL, Wiedmeyer HM, Little RR, England JD, Tennill A, Goldstein DE. Defining the relationship between plasma glucose and HbA(1c): analysis of glucose profiles and HbA(1c) in the Diabetes Control and Complications Trial. Diabetes Care. 2002 Feb;25(2):275-8. doi: 10.2337/diacare.25.2.275.

Study record dates

Study Major Dates

• Study Start (Actual): June 1, 2020
• Primary Completion (Actual): August 31, 2020
• Study Completion (Actual): December 30, 2020

Study Registration Dates

• First Submitted: March 27, 2019
• First Submitted That Met QC Criteria: March 28, 2019
• First Posted (Actual): April 1, 2019

Study Record Updates

• Last Update Posted (Actual): September 28, 2021
• Last Update Submitted That Met QC Criteria: September 26, 2021
• Last Verified: September 1, 2021

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Glucose Metabolism Disorders; Metabolic Diseases; Immune System Diseases; Autoimmune Diseases; Endocrine System Diseases; Diabetes Mellitus; Diabetes Mellitus, Type 1
• Other Study ID Numbers: 2019003271

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No