Digital phenotyping of CGM engagement reveals distinct glycemic outcomes

Bowen Zhang, Tomoki Okuno, Emma Li, Ethan Riggins, Evie L Shen, Joleen Vansomphone, Estelle M Everett, Gregory J Norman, Donald R Miller, Peter D Reaven, Hua Zhou and Jin J Zhou

PLOS Digital Health, 2026, vol. 5, issue 7, 1-20

Abstract: Benefits from continuous glucose monitors (CGMs) may depend on how devices are used over time—not only how often they are used. We linked one year of device-generated CGM wear data from 2,351 U.S. Veterans to electronic health records (EHRs) to characterize real-world usage during the first year after CGM initiation. To compare longitudinal use patterns in the presence of unsynchronized sensor replacement–related gaps and intermittent interruptions, we aligned daily wear streams using a complexity-adjusted, time-adaptive optimal transport (TAOT) distance and applied spectral clustering to identify data-driven usage phenotypes. To estimate the adjusted association between CGM usage phenotypes and clinical outcomes, we used a double/debiased machine learning framework to quantify 12-month changes in time in range (ΔTIR) and mean glucose (ΔMG). We identified three reproducible patterns of CGM usage: Consistent, Fluctuating, and Low engagement. Relative to Consistent wear, Fluctuating usage was associated with worse glycemic change (ΔTIR = −3.56%, 95% CI: −4.76 to −2.36; ΔMG = +7.12 mg/dL, 95% CI: 4.91 to 9.32), and Low engagement showed larger deterioration (ΔTIR = −7.00%, 95% CI: −10.80 to −3.14; ΔMG = +14.09 mg/dL, 95% CI: 6.52 to 21.67). Notably, 73.2% of Fluctuating users still met a common “adherence” threshold (≥80% days worn), indicating that simple coverage metrics can miss clinically relevant instability. The differences in glycemic change (ΔTIR and ΔMG) between the Consistent and Fluctuating groups were most pronounced among subgroups with more intensive diabetes management needs, such as insulin pump or glucagon users, suggesting that sustained CGM usage may be particularly important when clinical management is more complex. Beyond CGM and diabetes, this work provides a generalizable framework for characterizing longitudinal usage patterns of intermittently used digital health technologies and linking derived usage phenotypes to clinical outcomes. The approach can support more precise evaluation, monitoring, and intervention design for a wide range of real-world digital health tools.Author summary: Continuous glucose monitors, or CGM, are widely used in diabetes care, yet evidence linking long-term CGM usage pattern to glycemic control remains limited. In this study, we examined long-term real-world data from more than 2,300 U.S. Veterans who used CGM for up to one year. Rather than summarizing use with a single adherence percentage, we looked at day-to-day patterns of use and how stable or irregular those patterns were over time. We identified three distinct groups: individuals with consistent use, a fluctuating group characterized by irregular engagement with interruptions or insufficient daily wear, and a low-engagement group. Importantly, many people in the fluctuating group would still be considered “adherent” by standard definitions, while they experienced worse glucose outcomes than consistent users, highlighting the limitations of common adherence thresholds. Consistent use was especially beneficial for individuals with more complex diabetes management needs, suggesting that targeted support to sustain stable use may yield greater clinical benefit. Overall, our work highlights the importance of understanding patterns of usage with wearable devices and introduces a general, data-driven framework for linking real-world usage trajectories to clinical outcomes.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001505 (text/html)
https://journals.plos.org/digitalhealth/article/fi ... 01505&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pdig00:0001505

DOI: 10.1371/journal.pdig.0001505

Access Statistics for this article

More articles in PLOS Digital Health from Public Library of Science
Bibliographic data for series maintained by digitalhealth ().