Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 May 26:2:e45450.
doi: 10.2196/45450.

Machine Learning-Based Time in Patterns for Blood Glucose Fluctuation Pattern Recognition in Type 1 Diabetes Management: Development and Validation Study

Nicholas Berin Chan  1 , Weizi Li  1 , Theingi Aung  2 , Eghosa Bazuaye  2 , Rosa M Montero  3
Affiliations

Machine Learning-Based Time in Patterns for Blood Glucose Fluctuation Pattern Recognition in Type 1 Diabetes Management: Development and Validation Study

Nicholas Berin Chan et al. JMIR AI. .

Abstract

Background: Continuous glucose monitoring (CGM) for diabetes combines noninvasive glucose biosensors, continuous monitoring, cloud computing, and analytics to connect and simulate a hospital setting in a person's home. CGM systems inspired analytics methods to measure glycemic variability (GV), but existing GV analytics methods disregard glucose trends and patterns; hence, they fail to capture entire temporal patterns and do not provide granular insights about glucose fluctuations.

Objective: This study aimed to propose a machine learning-based framework for blood glucose fluctuation pattern recognition, which enables a more comprehensive representation of GV profiles that could present detailed fluctuation information, be easily understood by clinicians, and provide insights about patient groups based on time in blood fluctuation patterns.

Methods: Overall, 1.5 million measurements from 126 patients in the United Kingdom with type 1 diabetes mellitus (T1DM) were collected, and prevalent blood fluctuation patterns were extracted using dynamic time warping. The patterns were further validated in 225 patients in the United States with T1DM. Hierarchical clustering was then applied on time in patterns to form 4 clusters of patients. Patient groups were compared using statistical analysis.

Results: In total, 6 patterns depicting distinctive glucose levels and trends were identified and validated, based on which 4 GV profiles of patients with T1DM were found. They were significantly different in terms of glycemic statuses such as diabetes duration (P=.04), glycated hemoglobin level (P<.001), and time in range (P<.001) and thus had different management needs.

Conclusions: The proposed method can analytically extract existing blood fluctuation patterns from CGM data. Thus, time in patterns can capture a rich view of patients' GV profile. Its conceptual resemblance with time in range, along with rich blood fluctuation details, makes it more scalable, accessible, and informative to clinicians.

Keywords: continuous glucose monitoring; diabetes mellitus; glucose fluctuation pattern; glycemic variability; scalable metrics; temporal clustering.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: None declared.

Figures

Figure 1
Figure 1
Analytical framework for glycemic variability (GV) pattern extraction and patient clustering from continuous glucose monitoring (CGM) data. DTW: dynamic time warping; EPR: electronic patient record.
Figure 2
Figure 2
Glycemic variability patterns extracted from dynamic time warping model. Each gray line represents a random sample within the specific pattern and data set, and one is highlighted in color. The dark gray line in each panel depicts the median of glycemic variability patterns extracted. FSL: FreeStyle Libre.
Figure 3
Figure 3
Dendrogram in hierarchical clustering and heat map of time in patterns per patient. The left panel depicts the dendrogram in hierarchical clustering. The 4 colored boxes represent 4 different patient clusters based on glycemic variability (GV) patterns. The right panel is a heat map that depicts the underlying distribution of patterns across all patients. Each row represents a patient and each column represents 1 of the 6 extracted GV patterns. Yellow color represents a relatively rare occurrence, and red color represents a relatively frequent occurrence.
Figure 4
Figure 4
Comparison of recommended time in range (TIR) targets and extracted glycemic variability patterns. Each color in the left panel represents a glycemic variability pattern. The lower and upper bound of each shaded region represent the 20th and 80th percentile of glucose trend for that pattern. The median glucose trend of each pattern is highlighted. The target TIR shown in the right panel is proposed by Battelino et al [28].
Figure 5
Figure 5
The 1-day glucose trend of patients sampled from each cluster. The shaded region represents the target glucose range, and the 6 glycemic variability (GV) patterns over time are highlighted in 6 colors.
Figure 6
Figure 6
Hourly distribution of glycemic variability (GV) patterns across a day for each patient cluster.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

  • CGM Data Analysis 2.0: Functional Data Pattern Recognition and Artificial Intelligence Applications.
    Klonoff DC, Bergenstal RM, Cengiz E, Clements MA, Espes D, Espinoza J, Kerr D, Kovatchev B, Maahs DM, Mader JK, Mathioudakis N, Metwally AA, Shah SN, Sheng B, Snyder MP, Umpierrez G, Shao MM, Scheideman AF, Ayers AT, Ho CN, Healey E. Klonoff DC, et al. J Diabetes Sci Technol. 2025 Aug 14:19322968251353228. doi: 10.1177/19322968251353228. Online ahead of print. J Diabetes Sci Technol. 2025. PMID: 40814224 Free PMC article.

References

    1. IDF Diabetes Atlas 10th edition. International Diabetes Federation. 2021. [2022-09-26]. https://diabetesatlas.org/atlas/tenth-edition/ - PubMed
    1. Global health estimates: Leading causes of death. Cause-specific mortality, 2000–2019. World Health Organization. 2020. [2022-09-26]. https://www.who.int/data/gho/data/themes/mortality-and-global-health-est... .
    1. Juvenile Diabetes Research Foundation Continuous Glucose Monitoring Study Group. Tamborlane WV, Beck RW, Bode BW, Buckingham B, Chase HP, Clemons R, Fiallo-Scharer R, Fox LA, Gilliam LK, Hirsch IB, Huang ES, Kollman C, Kowalski AJ, Laffel L, Lawrence JM, Lee J, Mauras N, O'Grady M, Ruedy KJ, Tansey M, Tsalikian E, Weinzimer S, Wilson DM, Wolpert H, Wysocki T, Xing D. Continuous glucose monitoring and intensive treatment of type 1 diabetes. N Engl J Med. 2008 Oct 02;359(14):1464–76. doi: 10.1056/NEJMoa0805017.NEJMoa0805017 - DOI - PubMed
    1. Reddy N, Verma N, Dungan K. Monitoring technologies- continuous glucose monitoring, mobile technology, biomarkers of glycemic control. Endotext. 2020. Aug 16, [2022-09-26]. https://www.ncbi.nlm.nih.gov/books/NBK279046/
    1. Foster NC, Beck RW, Miller KM, Clements MA, Rickels MR, DiMeglio LA, Maahs DM, Tamborlane WV, Bergenstal R, Smith E, Olson BA, Garg SK. State of type 1 diabetes management and outcomes from the T1D exchange in 2016-2018. Diabetes Technol Ther. 2019 Feb;21(2):66–72. doi: 10.1089/dia.2018.0384. https://europepmc.org/abstract/MED/30657336 - DOI - PMC - PubMed

LinkOut - more resources