Authors :
Saumil Tripathi
Volume/Issue :
Volume 11 - 2026, Issue 9 - September
Google Scholar :
https://tinyurl.com/57rjy4v2
DOI :
https://doi.org/10.38124/ijisrt/26sep1349
Note : A published paper may take 4-5
working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and
ResearchGate.
Abstract :
Continuous glucose monitors (CGMs) have changed how people with diabetes interact with their glucose data. Instead of relying on occasional finger-stick measurements, people can now see glucose values throughout the day and night. Over time, this creates an enormous amount of information about how the body responds to meals, exercise, medication, sleep, stress, and everyday life. The challenge is no longer simply collecting glucose data. For many people, the harder part is figuring out what all of that data actually means. This project addresses that problem through a Flask-based web application designed to analyze continuous glucose monitoring data, particularly exports from systems such as Dexcom. The application takes a glucose data file, cleans and organizes the readings, calculates relevant metrics, identifies recurring patterns, analyzes glucose behavior by time of day, compares glucose changes with recorded events, and presents the results through a visual web interface. An artificial intelligence layer is also used to translate the findings into simpler language and generate topics and questions that users can discuss with healthcare professionals. The goal is not to diagnose diabetesrelated conditions or replace a physician. Instead, the application acts as an interpretation layer between raw CGM data and the person trying to understand it. By turning thousands of individual readings into recognizable trends, the application can reduce some of the manual work involved in reviewing glucose data and help make conversations between patients and healthcare providers more focused. More broadly, the project shows how software engineering, data analysis, web development, and generative artificial intelligence can work together to address a real-world healthcare problem. It also demonstrates an important idea in health technology: software does not always need to make medical decisions to be useful. Sometimes its most valuable job is simply making existing information easier for people to understand.
References :
- Centers for Disease Control and Prevention. National Diabetes Statistics Report: Estimates of Diabetes and Its Burden in the United States. 2026.
- Dexcom. What Can I Find on the Trends Tab of My Dexcom G7 App? 2026.
- Battelino, T., Danne, T., Bergenstal, R. M., et al. “Clinical Targets for Continuous Glucose Monitoring Data Interpretation: Recommendations From the International Consensus on Time in Range.” Diabetes Care, 2019.
- American Diabetes Association. “Glycemic Goals and Hypoglycemia: Standards of Care in Diabetes.” Diabetes Care.
- Systematic review of qualitative studies. “Patient Experiences of Continuous Glucose Monitoring and Sensor-Augmented Insulin Pump Therapy for Diabetes.” 2023.
- American Diabetes Association. “Section 7: Diabetes Technology — Standards of Care in Diabetes 2026.”
- National Institute of Diabetes and Digestive and Kidney Diseases. “Diabetes Distress and Depression.”
- American Diabetes Association. “Diabetes Technology: Improve Diabetes Outcomes with ADA Tools.”
- American Diabetes Association. Standards of Care in Diabetes 2026.
- Recent research on diabetes distress, CGM metrics, and psychosocial outcomes in people with diabetes.
Continuous glucose monitors (CGMs) have changed how people with diabetes interact with their glucose data. Instead of relying on occasional finger-stick measurements, people can now see glucose values throughout the day and night. Over time, this creates an enormous amount of information about how the body responds to meals, exercise, medication, sleep, stress, and everyday life. The challenge is no longer simply collecting glucose data. For many people, the harder part is figuring out what all of that data actually means. This project addresses that problem through a Flask-based web application designed to analyze continuous glucose monitoring data, particularly exports from systems such as Dexcom. The application takes a glucose data file, cleans and organizes the readings, calculates relevant metrics, identifies recurring patterns, analyzes glucose behavior by time of day, compares glucose changes with recorded events, and presents the results through a visual web interface. An artificial intelligence layer is also used to translate the findings into simpler language and generate topics and questions that users can discuss with healthcare professionals. The goal is not to diagnose diabetesrelated conditions or replace a physician. Instead, the application acts as an interpretation layer between raw CGM data and the person trying to understand it. By turning thousands of individual readings into recognizable trends, the application can reduce some of the manual work involved in reviewing glucose data and help make conversations between patients and healthcare providers more focused. More broadly, the project shows how software engineering, data analysis, web development, and generative artificial intelligence can work together to address a real-world healthcare problem. It also demonstrates an important idea in health technology: software does not always need to make medical decisions to be useful. Sometimes its most valuable job is simply making existing information easier for people to understand.
