Search PubMed⌕ Search
Home/Archive/PubMed

PubMed · 42685343

User Engagement and Feature Preferences in an AI-Powered mHealth Intervention for Diabetes Prevention: Secondary Analysis of a Randomized Controlled Trial.

Benjamin Lalani·Gabriela Siew·Yllka Valdez·Aliyah Shehadeh·Daniel Zade·Kristin Riekert·Nestoras Mathioudakis·AI-DPP Study Group
View original source ↗Export metadata ↓

Abstract

BACKGROUND: Prediabetes is highly prevalent and increasing globally, yet lifestyle interventions remain underused. AI-driven mobile health (mHealth) tools can help scale diabetes prevention efforts, but the key factors driving their success are not well understood. OBJECTIVE: This post hoc secondary analysis of a randomized controlled trial (RCT) aimed to characterize the most valued features and the role of user engagement in outcomes of a fully automated mHealth intervention for diabetes prevention. METHODS: Data from 151 participants with prediabetes and overweight or obesity who were assigned to an AI-based diabetes prevention program (Sweetch) in a parent RCT (NCT05056376) were analyzed. Engagement (defined as the total number of days the app was used) was categorized into tertiles (low, medium, and high). Baseline characteristics were compared across engagement groups using ANOVA, Kruskal-Wallis, and chi-square tests, and regression models assessed the association between engagement and achievement of diabetes risk reduction outcomes (&#x2265;5% weight loss, &#x2265;4% weight loss with &#x2265;150 min/week of physical activity, or &#x2265;0.2 percentage point reduction in hemoglobin A1c [HbA1c] at 12 months). Perceived usefulness of intervention features was surveyed at 12 months. RESULTS: Median engagement was 98 (IQR 34-232) days. Older age (P<.001) and lower baseline BMI (P=.04) were significantly associated with higher engagement. Compared with low engagement, high engagement was associated with greater odds of achieving the composite diabetes risk reduction outcome (odds ratio [OR] 2.59, 95% CI 1.11-6.01; P=.03), &#x2265;5% weight loss (OR 3.31, 95% CI 1.16-9.42; P=.03), and &#x2265;0.2 percentage point reduction in HbA1c (OR 3.57, 95% CI 1.19-10.75; P=.02). Participants most frequently rated weight tracking, physical activity tracking, and the digital body weight scale as the features that were most helpful for achieving their health goals. CONCLUSIONS: Higher engagement with an AI-driven intervention requiring no human intervention was associated with improved diabetes risk reduction. Contrary to concerns about lower digital literacy, older adults engaged with the intervention more than younger adults. Features related to weight and physical activity tracking were most valued by patients in the program. TRIAL REGISTRATION: ClinicalTrials.gov NCT05056376; https://clinicaltrials.gov/study/NCT05056376.

Explore related subjects

HumansFemaleMaleMiddle AgedTelemedicineAdultDigital HealthDiabetes Mellitus, Type 2Prediabetic StatePatient ParticipationArtificial IntelligenceAgedartificial intelligencediabetes preventiondigital healthlifestyle interventionmobile appobesityoverweightprediabetesreinforcement learninguser engagementJournal ArticleRandomized Controlled TrialResearch Support, N.I.H., Extramural

Keep this discovery

BibTeXRIS

Benjamin Lalani, Gabriela Siew, Yllka Valdez, Aliyah Shehadeh, Daniel Zade, Kristin Riekert, Nestoras Mathioudakis, AI-DPP Study Group. 2026-09-02. User Engagement and Feature Preferences in an AI-Powered mHealth Intervention for Diabetes Prevention: Secondary Analysis of a Randomized Controlled Trial.. https://doi.org/10.2196/92981

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

Adult subjectAged subjectArtificial Intelligence subjectDiabetes Mellitus, Type 2 subjectDigital Health subjectFemale subjectHumans subjectJournal Article subjectMale subjectMiddle Aged subjectObesity subjectOverweight subjectPrediabetes subjectPrediabetic State subjectRandomized controlled trials study

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related citations

PubMed2026

Opposite metabolic and gut responses to oral glutamine in male and female mice with diet-induced obesity.

Obesity is often associated with sex-dependent metabolic complications, to which altered intestinal barrier function and gut microbiota contribute. Glutamine supplementation has previously shown beneficial effects on gut barrier function and glycemic control. We thus aimed to characterize, in male and female mice, the effects of oral glutamine supplementation during high-fat-diet-induced obesity. Male and female C57BL/6 mice received a standard (SD) or high-fat diet (HFD; 60 % kcal from fat) for 14&#xa0;weeks (W14). From W12 onward, mice received glutamine in drinking water (2&#xa0;g/kg/day) or no supplementation. Body composition, glucose tolerance, insulin sensitivity, intestinal permeability, colonic inflammatory response, cecal microbiota and inflammatory/endocrine adipose response were assessed. In both male and female mice, glutamine supplementation failed to improve body weight and body composition. However, glutamine reduced glucose intolerance in HFD-fed males (AUC reduced by 14.57 %) that was associated with a partial restoration of plasma resistin and insulin and a trend toward limiting adipose inflammatory response. In males, glutamine did not affect gut microbiota composition and colonic response. Conversely, in HFD-fed females, glutamine supplementation led to gut microbiota changes (increase in Bacteroidota and Pseudomonadota phyla; increase in Muribaculaceae and Tannerellaceae families), increased colonic inflammatory markers (Il1b, Tlr4, Myd88, Irf3), increased inflammatory response in subcutaneous adipose tissue and increased HOMA-IR. Finally, HFD-fed mice exhibited sex-specific responses to glutamine supplementation with protective effects in males and harmful effects in females that need to be further deeply explored.

Animals↗
PubMed2026

Maternal obesity in rats results in male-specific increases in genome-wide DNA methylation in postnatal offspring liver.

Male-specific peripubertal DNA demethylation in the liver has been reported in mice. Here, we investigated whether it also occurs in rats, the influence of maternal obesity and whether DNA demethylation changes contribute to observed sex-specific effects of maternal obesity in offspring. Female rats were fed a high-fat, high-sugar 'cafeteria' (Caf) diet before mating with standard chow-fed males. The offspring liver methylome and transcriptome were examined. Body weight was higher in Caf-fed dams prior to mating, during gestation and at parturition. Male and female offspring from Caf-fed dams had lower birth weights but higher adult weights and adiposity than offspring from chow-fed dams. A comparison of DNA methylation in 3-week-old weaner males versus female siblings from chow-fed dams did not reveal the male-specific DNA demethylation that was previously reported in mice. However, strong maternal diet effects in male weaner offspring methylation were observed. A comparison of female weaners from chow- versus Caf-fed dams showed a range of differences, with 39% of differentially methylated regions (DMRs) having higher methylation in Caf offspring and 61% of DMRs having higher methylation in chow offspring. In stark contrast, 99% of maternal-diet-induced DMRs in male weaner offspring had higher methylation in offspring from Caf-fed dams. This suggests that maternal obesity induces widespread hypermethylation in the male offspring liver at weaning. However, a comparison with RNA sequencing data revealed limited transcriptional changes at this developmental stage or in adult offspring. While these data highlight how environmentally sensitive DNA methylation is in the male rodent perinatal period, these methylation changes may not be a major contributor to sex differences in developmentally programmed liver disease.

Animals↗
PubMed2026

Male accessory gland proteins in Grapholita molesta: Identification and reproductive functional validation of four accessory gland-specific lipases.

Accessory gland proteins (Acps), synthesized in the male accessory glands (AGs), are transferred to females via spermatophores during mating and elicit diverse post-mating physiological and behavioral responses. However, Acps have not been comprehensively characterized in Grapholita molesta, a cosmopolitan orchard pest. Here, using data-independent acquisition mass spectrometry, we describe an integrated proteomic approach combining comparative AG analyses (virgin vs. newly mated) with spermatophore profiling to identify Acps in G. molesta. According to the established screening criteria, we identified 83 confirmed Acps, which were classified into nine categories. Tissue-specific expression patterns of 20 randomly selected Acp genes were evaluated, revealing that these genes were specifically or highly expressed in male AGs. Among the 83 confirmed Acps, four Acps harbored the PLN02872 superfamily domain and were classified into the canonical lipase family. Notably, their transcripts were all highly expressed in the AGs during the pre-maturation stage. These four Acps were selected for preliminary validation of their male reproductive functions. RNAi-mediated knockdown of three out of four lipase genes in G. molesta males significantly decreased the fertility of mated females, with phenotypes including a significant reduction in egg production and egg hatching rate. This study provides a comprehensive catalog of high-confidence Acps, lays a foundation for subsequent in-depth functional characterization of these reproductive proteins, and offers promising molecular targets for the development of novel genetic regulation-based integrated pest management strategies.

Animals↗