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
. 2024 Jan 11;7(1):7.
doi: 10.1038/s41746-023-00985-7.

Multimodal digital phenotyping of diet, physical activity, and glycemia in Hispanic/Latino adults with or at risk of type 2 diabetes

Amruta Pai  1 , Rony Santiago  2 , Namino Glantz  3 , Wendy Bevier  2 , Souptik Barua  4 , Ashutosh Sabharwal  4 , David Kerr  5
Affiliations

Multimodal digital phenotyping of diet, physical activity, and glycemia in Hispanic/Latino adults with or at risk of type 2 diabetes

Amruta Pai et al. NPJ Digit Med. .

Abstract

Digital phenotyping refers to characterizing human bio-behavior through wearables, personal devices, and digital health technologies. Digital phenotyping in populations facing a disproportionate burden of type 2 diabetes (T2D) and health disparities continues to lag compared to other populations. Here, we report our study demonstrating the application of multimodal digital phenotyping, i.e., the simultaneous use of CGM, physical activity monitors, and meal tracking in Hispanic/Latino individuals with or at risk of T2D. For 14 days, 36 Hispanic/Latino adults (28 female, 14 with non-insulin treated T2D) wore a continuous glucose monitor (CGM) and a physical activity monitor (Actigraph) while simultaneously logging meals using the MyFitnessPal app. We model meal events and daily digital biomarkers representing diet, physical activity choices, and corresponding glycemic response. We develop a digital biomarker for meal events that differentiates meal events into normal and elevated categories. We examine the contribution of daily digital biomarkers of elevated meal event count and step count on daily time-in-range 54-140 mg/dL (TIR54-140) and average glucose. After adjusting for step count, a change in elevated meal event count from zero to two decreases TIR54-140 by 4.0% (p = 0.003). An increase in 1000 steps in post-meal step count also reduces the meal event glucose response by 641 min mg/dL (p = 0.0006) and reduces the odds of an elevated meal event by 55% (p < 0.0001). The proposed meal event digital biomarkers may provide an opportunity for non-pharmacologic interventions for Hispanic/Latino adults facing a disproportionate burden of T2D.

PubMed Disclaimer

Conflict of interest statement

A.P., R.S., N.G., A.L., W.B., S.B., and A.S. declare no competing interest(s). D.K. has received research support from Abbott Diabetes Care and Novo Nordisk and is an advisor to Sanofi, Glooko, SNAQ, and Hi.Health.

Figures

Fig. 1
Fig. 1. Research summary.
Overall contributions of multimodal digital phenotyping in Hispanic/Latino adults with or at risk of non-insulin treated T2D.
Fig. 2
Fig. 2. Visualization of a snapshot of the multimodal data.
Digital health devices were used to collect synchronous information on the meal, activity, and glucose excursions in free-living conditions.
Fig. 3
Fig. 3. Meal event annotations.
Various examples of CGM profiles overlayed with meal timings across different participants are shown in (a–d). The red vertical lines correspond to self-reported food log timings. The green lines adjacent to the red lines correspond to corrected timing. The yellow lines correspond to added timings.
Fig. 4
Fig. 4. Mapping between HbA1c and average meal event glucose response.
The scatterplot on the left a displays the robust regression fit between average meal event glucose response and HbA1c. The equation representing the best line-of-fit is reported (solid black line). The scatterplot in b shows the correlation between true and fitted HbA1c values. The dashed black line represents the 45° line.
Fig. 5
Fig. 5. Illustration of steps taken in methods.
The CGM curve and meal logs are analyzed to segment meal events. The meal event measures are the meal event’s glucose response (MGR3hr), post-meal step count, and elevated or normal classification of meal events computed for each meal event. Daily measures of elevated meal count, daily step count, baseline glucose, and duration are then calculated.
Fig. 6
Fig. 6. Association between Daily TIR54–140 and elevated meal event count.
Daily TIR54–140 decreases associated with an increase in elevated meal event count across participants a at risk of T2D, b with prediabetes, c with T2D. The ends of the box represent the lower and upper quartiles. The median (second quartile) is marked by a line inside the box. The data points adjacent to the box plot display the underlying data points where each data point corresponds to a day.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Griffin S. Diabetes precision medicine: plenty of potential, pitfalls and perils but not yet ready for prime time. Diabetologia. 2022;65:1913–1921. doi: 10.1007/s00125-022-05782-7. - DOI - PMC - PubMed
    1. Spruijt-Metz D, Cook L, O’Reilly GA, Page KA, Quinn C. Behavioral contributions to the pathogenesis of type 2 diabetes. Curr. Diabetes Rep. 2014;14:475. doi: 10.1007/s11892-014-0475-3. - DOI - PMC - PubMed
    1. Kerr D, King F, Klonoff DC. Digital health interventions for diabetes: everything to gain and nothing to lose. Diabetes Spectr. 2019;32:226–230. doi: 10.2337/ds18-0085. - DOI - PMC - PubMed
    1. Kerr D, Axelrod C, Hoppe C, Klonoff DC. Diabetes and technology in 2030: a utopian or dystopian future? Diabet. Med. 2018;35:498–503. doi: 10.1111/dme.13586. - DOI - PubMed
    1. Huckvale K, Venkatesh S, Christensen H. Toward clinical digital phenotyping: a timely opportunity to consider purpose, quality, and safety. npj Digit. Med. 2019;2:1–11. doi: 10.1038/s41746-019-0166-1. - DOI - PMC - PubMed