CoChat
Sign Up
Cited by 45Mobile Health and mHealth ApplicationsDiabetes Management and ResearchDiabetes Management and Education

The DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index; 27 of the 44 sources its claims cite were checked for support.

Impact of digital health interventions on glycemic control and weight management.

Open access
Veluvali, Arvind, Dehghani Zahedani, Ashkan, Hosseinian, Amir, Aghaeepour, Nima, McLaughlin, Tracey, Woodward, Mark, DiTullio, Alex, Hashemi, Noosheen, Snyder, Michael P.·2025·npj Digital Medicine
DOI 10.1038/s41746-025-01430-7PMC PMC11717909
Open this paper in CoChat — free accountOpen PDF

Abstract

This retrospective cohort study evaluates the impact of an AI-supported continuous glucose monitoring (CGM) mobile app ("January V2") on glycemic control and weight management in 944 users, including healthy individuals and those with prediabetes or type 2 diabetes (T2D). The app, leveraging AI to personalize feedback, tracked users' food intake, activity, and glucose responses over 14 days. Significant improvements in time in range (TIR) were observed, particularly in users with lower baseline TIR. Healthy users' TIR increased from 74.7% to 85.5% (p < 0.0001), while T2D users' TIR improved from 49.7% to 57.4% (p < 0.0004). Higher app engagement correlated with greater TIR improvements. Users also experienced an average weight reduction of 3.3 lbs over 33 days. These findings suggest that AI-enhanced digital health interventions can improve glycemic control and promote weight loss, particularly when users are actively engaged.

Overview

AI snapshot

Written from the paper’s full text.

TL;DR

This retrospective cohort study of 944 users of an AI-supported CGM app (“January V2”) reports improved time in range (TIR), modest weight loss, and reduced hypoglycemic events, with greater improvements among highly engaged “power users.” The authors conclude that flexible digital health interventions may support glycemic control and weight management, while noting the absence of a control group and other real-world limitations.

Key findings

  • Among users with baseline TIR < 90%, healthy users’ TIR increased from 74.7% to 85.5% and T2D users’ TIR from 49.7% to 57.4%; the Results section reports p < 0.0004 for both, while the abstract states p < 0.0001 for healthy users.
  • “Power users” had a TIR increase from 75.5% to 85.6%; comparing the 5-day AI training period with the post-training intervention period, all users’ TIR rose from 80.2% to 85.6% (p < 0.0002) and power users’ TIR from 81.0% to 88.2% (p < 0.0001).
  • Average weight reduction was 3.3 lbs over an average of 33 days; the prediabetes cohort and power users each showed 4.0 lbs loss (p < 0.0001).
  • Hypoglycemic events decreased across all cohorts, particularly in healthy users (0.17 to 0.06 events/day, p < 0.0001); hyperglycemic events decreased only in the prediabetes cohort (1.14 to 0.95 events/day, p = 0.037).

Methods

  • Retrospective cohort study of 944 self-selected users who purchased and used the January V2 app between January 2022 and December 2023; participants were adults aged 18+, completed at least 5 days of CGM use for AI training, and self-reported health status as healthy (n = 785), prediabetes (n = 98), or T2D (n = 61).
  • The intervention integrated CGM (Abbott Freestyle Libre 2), heart-rate monitoring, food logging, and AI-generated personalized recommendations; primary glycemic outcomes were assessed over 14 days, with a 5-day AI training period and a subsequent 9-day post-training intervention period, while weight was assessed over an average of 33 days.
  • Engagement was quantified by average foods logged per day after AI training; “power users” were the top quartile logging ≥3 foods/day. Analyses used paired t-tests and multivariate regression models in Python, with complete-case analysis for missing data.

Limitations

  • The authors state there was no control group, so improvements could reflect placebo or nonspecific effects; they also note selection bias from self-selected paying users, short duration (14 days for glycemic outcomes and 33 days for weight), no data on concurrent weight-loss or diabetes medications/programs, reliance on self-reported food intake and health status, and possible unmeasured confounding.
  • The paper itself notes that the GMI change was statistically significant but small (5.734% to 5.718%, p = 0.042) and that its clinical relevance needs careful consideration; it also reports that the weight–engagement correlation was not significant (Pearson 0.15, p = 0.34).
  • Evident from the text: weight analysis included only 702 of 944 users (74.4%) with complete weight data, and health-condition classification relied on self-report, which the authors suggest may misclassify some users with early insulin resistance.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1038/s41746-025-01430-7

Cites

38 of 38 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

27 of 44 cited sources checked · 10 supported · 0 flagged · accuracy not yet measured

  • Premisecitation

    Traditional methods such as the Diabetes Prevention Program rely on periodic clinical visits, one-on-one coaching, and self-reported data.

    “Traditional methods such as the widely used Diabetes Prevention Program (DPP) often rely on periodic clinical visits, one-on-one coaching, and self-reported data9.”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites [9] Valabhji, J. et al. Early Outcomes From the English National Health Service Diabetes Prevention Programme. Diabetes Care 43, 152–160 (2020). source

      The Intervention section describes recurring face-to-face sessions over at least nine months, supporting periodic contact. But it specifies group-based sessions, not one-on-one coaching. The Data collection section says coaches measured participants’ weight and providers assessed HbA1c, rather than relying on self-reported data; neither section describes the sessions as clinical visits. Page numbers are not available in our copy. (LLM, conf=0.88)

      Experimental — accuracy not yet measured
  • Premisecitation

    The high cost of programs that require coaching limits their reach.

    “the high cost of such programs that require coaching limits their reach13,14”
    Quote in the paperSubstantial claim2 of 2 sources checked
    • cites [13] Kim, S. E. et al. Evaluation of a Digital Diabetes Prevention Program Adapted for Low-Income Patients, 2016–2018. Prev. Chronic Dis. 16, 190156 (2019). source

      The Introduction describes participation barriers for in-person diabetes prevention programs, including scheduling, transportation, and childcare. The Methods describe a digital program with health coaches, but neither passage says that coaching makes programs expensive or that its cost limits their reach; searches for coaching costs and scalability found no such statement. The indexed passages have no page numbers. (LLM, conf=0.75)

      Experimental — accuracy not yet measured
    • cites [14] Karachaliou, F., Simatos, G. & Simatou, A. The challenges in the development of Diabetes Prevention and care models in Low-Income settings. Front. Endocrinol. (Lausanne) 11, 518 (2020). source

      The Models of Care section says patients in low- and middle-income countries have difficulty accessing and affording health care, supporting a general link between cost and access. The Prevention Models section describes a low-cost peer-support program, but neither passage says that coaching-based programs are expensive or that their cost limits their reach. No page numbers are available in our copy. (LLM, conf=0.78)

      Experimental — accuracy not yet measured
  • Premisecitation

    The magnitude of improvements observed, particularly in TIR and weight loss metrics, aligns with outcomes from controlled studies of similar digital health interventions.

    “the magnitude of improvements observed, particularly in TIR and weight loss metrics, align with outcomes from controlled studies of similar digital health interventions19.”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [19] Hall, H. et al. Glucotypes reveal new patterns of glucose dysregulation. PLoS Biol. 16, e2005143 (2018). source

      The Methods describe glucose monitoring during a period of stable lifestyle, not a controlled digital-health intervention. The Introduction reports improved postmeal glucose responses from a separate personalized-nutrition study, but our copy provides no TIR or weight-loss outcomes to compare with the magnitude claimed (searched: TIR, time in range, weight loss, intervention). (LLM, conf=0.78)

      Experimental — accuracy not yet measured
  • Premisecitation

    Research into the use of AI for the delivery of personalized recommendations is sparse.

    “It is notable that research into the use of AI for the delivery of personalized recommendations is sparse33”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [33] Aggarwal, A. et al. Artificial Intelligence–Based Chatbots for Promoting Health Behavioral Changes: Systematic Review. J. Med. Internet Res. 25, e40789 (2023). source

      The Discussion’s “Nascent Application of AI Chatbots” section describes research on AI chatbot interventions for health behavior change as nascent. But the claim extends that assessment to AI-delivered personalized recommendations generally; the Results report that 10 of the 15 reviewed studies used AI techniques to deliver personalized interventions. The source supports a narrower statement about the maturity of this research area, not the broader claim as written (page unavailable). (LLM, conf=0.84)

      Experimental — accuracy not yet measured
  • Findingown data

    Examination of users' time-in-range compared to their weight led to observation of several individuals who self-reported as "healthy" but exhibited lower TIR, which is typically more characteristic of individuals with prediabetes or T2D.

    “Examination of users’ time-in-range compared to their weight led to observation of several individuals who self-reported as “healthy” but nonetheless exhibit lower TIR, which is typically more characteristic of individuals with prediabetes or T2D; a feature noted previously19.”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [19] Hall, H. et al. Glucotypes reveal new patterns of glucose dysregulation. PLoS Biol. 16, e2005143 (2018). source
  • Probably not a substantial claim. 39
  • It may state two separate claims as one. 37
  • The quote only partly states this claim. 1

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Premisecitation

    CGM has been predominantly used by insulin-treated individuals.

    “While CGM has been predominantly used by insulin-treated individuals4,5”
    Quote in the paperNot a substantial claim2 of 2 sources checked
    • cites [4] Poolsup, N., Suksomboon, N. & Kyaw, A. M. Systematic review and meta-analysis of the effectiveness of continuous glucose monitoring (CGM) on glucose control in diabetes. Diabetol. Metab. Syndr. 5, 39 (2013). source
    • cites [5] Perez-Nieves, M. et al. Trends in U.S. Insulin Use and Glucose Monitoring for People with Diabetes: 2009–2018. J. Diabetes Sci. Technol. 16, 1428–1435 (2022). source

      The Results report CGM use among people with type 1 and type 2 diabetes in cohorts described as prevalent insulin users. But because the study does not compare insulin-treated with non-insulin-treated CGM users, it cannot establish that CGM users overall were predominantly insulin-treated. (LLM, conf=0.85)

      Experimental — accuracy not yet measured

  • It may state two separate claims as one.

    Premisecitation

    Recent developments have made CGM more available to individuals with diet-controlled diabetes or no diabetes, placing CGM center-stage in efforts to prevent diabetes through lifestyle modifications.

    “recent developments have made CGM more available to individuals with diet-controlled diabetes or no diabetes, thereby placing CGM center-stage in efforts to prevent diabetes through lifestyle modifications such as healthier food choices and increased physical activity6,7.”
    Quote in the paperNot a substantial claim1 of 2 sources checked
    • cites [6] Liu, C. et al. Impact of patients’ beliefs about insulin on acceptance and adherence to insulin therapy: a qualitative study in primary care. BMC Prim. Care 23, 15 (2022). source

      The Introduction discusses lifestyle factors in type 2 diabetes, and the Methods describe a study of patients using insulin. Neither those passages nor searches for CGM, continuous glucose monitoring, and diabetes prevention address CGM availability to people with diet-controlled diabetes or no diabetes, or its role in lifestyle-based prevention. (LLM, conf=0.76)

      Experimental — accuracy not yet measured
    • cites [7] Klonoff, D. C. et al. Use of Continuous Glucose Monitors by People Without Diabetes: An Idea Whose Time Has Come? J. Diabetes Sci. Technol. 17, 1686–1697 (2023). source

  • It may state two separate claims as one.

    Premisecitation

    Previous research showed that a structured digital health program integrating CGM and behavioral tracking improved glycemic control and promoted weight loss.

    “This study builds upon our previous research16, where we showed that a structured digital health program integrating CGM and behavioral tracking improved glycemic control and promoted weight loss.”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites [16] Zahedani, A. D. et al. Digital health application integrating wearable data and behavioral patterns improves metabolic health. npj Digit. Med. 6, 216 (2023). source

  • It may state two separate claims as one.

    Premisecitation

    Continuous glucose monitoring provides immediate feedback on glycemic control, enabling timely adjustments to diet, exercise, and medication if patients are medicated.

    “CGM provides users with immediate feedback on their glycemic control, enabling timely adjustments to diet, exercise, and medication, if patients are medicated4.”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [4] Poolsup, N., Suksomboon, N. & Kyaw, A. M. Systematic review and meta-analysis of the effectiveness of continuous glucose monitoring (CGM) on glucose control in diabetes. Diabetol. Metab. Syndr. 5, 39 (2013). source

  • Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.

    Premisecitation

    Weight reduction is often associated with improved insulin sensitivity and reduced risk of diabetes progression.

    “weight reduction is often associated with improved insulin sensitivity and reduced risk of diabetes progression28,29.”
    Quote in the paperNot a substantial claim1 of 2 sources checked
    • cites [28] Rock, C. L. et al. Weight Loss, Glycemic Control, and Cardiovascular Disease Risk Factors in Response to Differential Diet Composition in a Weight Loss Program in Type 2 Diabetes: A Randomized Controlled Trial. Diabetes Care 37, 1573–1580 (2014). source

      The Results report greater weight loss and improved glucose and HbA1c in the intervention groups, supporting a related claim about glycemic control. The paper does not establish improved insulin sensitivity or reduced risk of diabetes progression; its participants already had type 2 diabetes. The cited copy provides section labels but no page numbers. (LLM, conf=0.86)

      Experimental — accuracy not yet measured
    • cites [29] Hamman, R. F. et al. Effect of Weight Loss With Lifestyle Intervention on Risk of Diabetes. Diabetes Care 29, 2102–2107 (2006). source

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Premisecitation

    The results align with existing literature emphasizing the clinical benefits of higher TIR, including reduced complications and improved overall health outcomes for individuals with diabetes.

    “These results align with existing literature that emphasizes the clinical benefits of higher TIR, including reduced complications and improved overall health outcomes for individuals with diabetes19,22–24.”
    Quote in the paperNot a substantial claim3 of 4 sources checked
    • cites [19] Hall, H. et al. Glucotypes reveal new patterns of glucose dysregulation. PLoS Biol. 16, e2005143 (2018). source

      The Introduction (page unavailable) discusses glycemic variability, postprandial glucose peaks, and cardiovascular risk, but does not address whether higher time in range (TIR) reduces complications or improves overall health outcomes in people with diabetes. Searches for TIR, time in range, complications, and health outcomes found no passage establishing the attributed relationship. (LLM, conf=0.72)

      Experimental — accuracy not yet measured
    • cites [22] Lu, J. et al. Association of Time in Range, as Assessed by Continuous Glucose Monitoring, With Diabetic Retinopathy in Type 2 Diabetes. Diabetes Care 41, 2370–2376 (2018). source
    • cites [23] Lu, J. et al. Time in Range in Relation to All-Cause and Cardiovascular Mortality in Patients With Type 2 Diabetes: A Prospective Cohort Study. Diabetes Care 44, 549–555 (2021). source
    • cites [24] Mayeda, L. et al. Glucose time in range and peripheral neuropathy in type 2 diabetes mellitus and chronic kidney disease. BMJ Open Diabetes Res. Care 8, e000991 (2020). source

      The Results section reports that higher time in range (TIR) was associated with lower prevalence of diabetic peripheral neuropathy in participants with type 2 diabetes and chronic kidney disease. The Introduction also reports associations with retinopathy and microalbuminuria. The paper does not establish that raising TIR reduces complications or improves overall health outcomes; its Discussion notes that the cross-sectional design cannot establish a temporal relationship. (LLM, conf=0.87)

      Experimental — accuracy not yet measured

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Premisecitation

    This finding is consistent with previous research highlighting the role of continuous engagement in the effectiveness of digital health interventions.

    “This finding is consistent with previous research that has highlighted the role of continuous engagement in the effectiveness of digital health interventions25–27.”
    Quote in the paperNot a substantial claim3 of 3 sources checked
    • cites [25] Gan, D. Z. Q. et al. Effect of Engagement with Digital Interventions on Mental Health Outcomes: A Systematic Review and Meta-Analysis. Front. Digit. Health 3, 764079 (2021). source

      The Discussion reports that greater engagement with digital mental health interventions is associated with greater improvement in mental health symptoms. It does not establish that engagement must be continuous, and its findings concern mental health interventions rather than digital health interventions generally. (LLM, conf=0.79)

      Experimental — accuracy not yet measured
    • cites [26] Nelson, L. A. et al. Estimating the impact of engagement with digital health interventions on patient outcomes in randomized trials. J. Am. Med Inf. Assoc. 29, 128–136 (2022). source

      The Background and Significance section says users must be willing to engage for digital health interventions to be effective. It does not establish that engagement must be continuous: the Results found insufficient evidence of an association between text-message response rate and outcomes in either trial, and the paper emphasizes identifying how much engagement is needed rather than assuming more is better. Page numbers were not available in our copy. (LLM, conf=0.86)

      Experimental — accuracy not yet measured
    • cites [27] McLaughlin, M. et al. Associations Between Digital Health Intervention Engagement, Physical Activity, and Sedentary Behavior: Systematic Review and Meta-analysis. J. Med Internet Res. 23, e23180 (2021). source

      The Abstract (Conclusions; page unavailable) reports a weak but consistent positive association between engagement with physical-activity digital health interventions and physical-activity outcomes. The Results (Objective 2; page unavailable) find mixed associations for time spent using an intervention. The review therefore supports a role for engagement, but does not establish that continuous engagement improves intervention effectiveness generally. (LLM, conf=0.84)

      Experimental — accuracy not yet measured

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Premisecitation

    For individuals without diabetes, a TIR of 90% or higher has been considered normal.

    “For individuals without diabetes, a TIR of 90% or higher has been considered normal42.”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [42] Berry, S. et al. Optimised Glucose “Time in Range” Using Continuous Glucose Monitors in 4,805 Non-Diabetic Individuals Is Associated With Favourable Diet and Health: The ZOE PREDICT Studies. Curr. Dev. Nutr. 6, 1108 (2022). source

      The Results report a mean ADA-defined TIR of 91 ± 13% among 4,805 people without diabetes, which is consistent with a value around 90% being typical in this sample. The paper does not establish 90% or higher as a cutoff for what is considered normal; its Methods define TIR by glucose ranges, not by a percentage threshold. (LLM, conf=0.86)

      Experimental — accuracy not yet measured

  • It may state two separate claims as one.

    Premisecitation

    Previous studies of lifestyle interventions for diabetes prevention, such as the Diabetes Prevention Program, have demonstrated sustained benefits over 2.9 to 6 years, with continued protection of 27-43% for up to 15 years.

    “Previous studies of lifestyle interventions for diabetes prevention, such as the Diabetes Prevention Program, have demonstrated sustained benefits over 2.9 to 6 years, with continued protection of 27–43% for up to 15 years38.”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites [38] Knowler, W. C. et al. 10-year follow-up of diabetes incidence and weight loss in the Diabetes Prevention Program Outcomes Study. Lancet 374, 1677–1686 (2009). source

      The Results report a 34% lower diabetes incidence rate in the lifestyle group over the combined DPP and follow-up periods, and the Discussion says the reduction persisted for at least 10 years. The paper reports the original DPP after about 2.8 years and discusses a separate six-year intervention, but it does not establish the claimed 27–43% protection for up to 15 years. (LLM, conf=0.88)

      Experimental — accuracy not yet measured

  • Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.

    Premisecitation

    AI can dramatically reduce the cost of offering personalized recommendations while increasing the level of personalization through integration with wearables.

    “AI can dramatically reduce the cost of offering personalized recommendations34,35 while increasing the level of personalization through integration with wearables36.”
    Quote in the paperNot a substantial claim2 of 3 sources checked
    • cites [34] Prabhod, K. J. The Role of Artificial Intelligence in Reducing Healthcare Costs and Improving Operational Efficiency. Q J. Emerg. Technol. Innov. 9, 47–59 (2024).

      Couldn’t be matched to a paper in Crossref, so it can’t be checked.

    • cites [35] Gual-Montolio, P. et al. Using Artificial Intelligence to Enhance Ongoing Psychological Interventions for Emotional Problems in Real- or Close to Real-Time: A Systematic Review. Int J. Environ. Res Public Health 19, 7737 (2022). source
    • cites [36] Marvasti, T. B. et al. Unlocking tomorrow’s health care: Expanding the clinical scope of wearables by applying artificial intelligence. Can. J. Cardiol. 40, 1934–1945 (2024). source

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Premisecitation

    Most people with prediabetes are unaware that they have this condition.

    “most people with prediabetes are unaware that they have this condition3”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [3] Suh, S. & Kim, J. H. Glycemic variability: how do we measure it and why is it important? Diabetes Metab. J. 39, 273–282 (2015). source

      The Glycemic Variability and Diabetes Complications section discusses impaired glucose tolerance and cardiovascular risk, but not whether people with prediabetes know they have it. Searches for prediabetes awareness and undiagnosed impaired glucose tolerance found no passage addressing the claim. (LLM, conf=0.76)

      Experimental — accuracy not yet measured

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Interpretationcitation

    These findings align with previous research on digital health interventions.

    “These findings align with previous research39,40, underscoring the potential for digital tools in managing chronic conditions and providing a foundation for future innovations in this field.”
    Quote in the paperNot a substantial claim2 of 2 sources checked
    • cites [39] Howarth, A., Quesada, J., Silva, J., Judycki, S. & Mills, P. R. The impact of digital health interventions on health-related outcomes in the workplace: A systematic review. Digit Health 4, 2055207618770861 (2018). source

      The Conclusions (page unavailable) say workplace digital health interventions show promise for improving employee health, supporting the general alignment with previous research and potential for digital tools. The review does not establish their effectiveness for managing chronic conditions specifically; its Discussion cautions that purely digital interventions may be inadequate for more complex health issues. (LLM, conf=0.84)

      Experimental — accuracy not yet measured
    • cites [40] Labinsky, H. et al. Real-world usage of digital health applications (DiGA) in rheumatology: results from a German patient survey. Rheumatol. Int 43, 713–719 (2023). source

  • It may state two separate claims as one.

    Premisecitation

    Sahin examined the use of text messaging in 13 clinical trials and showed that personalized text messaging interventions could improve glycemic control in patients with T2D.

    “Sahin31 examined the use of text messaging in 13 clinical trials and showed that personalized text messaging interventions could improve glycemic control in patients with T2D.”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [31] Sahin, C., Courtney, K. L., Naylor, P. & Rhodes, R. E. Tailored mobile text messaging interventions targeting type 2 diabetes self-management: A systematic review and a meta-analysis. Digit. Health 5, 2055207619845279 (2019). source

  • It may state two separate claims as one.

    Findingown data

    The Glucose Management Indicator at the beginning of the study was 5.734%, and at the end of the study period it slightly decreased to 5.718%.

    “The GMI at the beginning of the study was recorded at 5.734%, while at the end of the study period, it slightly decreased to 5.718%.”
    Quote in the paperSubstantial claim

  • The quote only partly states this claim.

    Findingown data

    The most significant weight loss was observed among power users (4.0 lbs, p < 0.0001).

    “and among power users (4.0 lbs, p < 0.0001)”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Findingown data

    The T2D group showed the highest increases in both protein and fiber intake, suggesting a more significant dietary adjustment in this population.

    “Notably, the T2D group also showed the highest increases in both protein and fiber intake, suggesting a more significant dietary adjustment in this population (Fig. 5).”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Findingown data

    The shift in last meal sleep gap was consistent across cohorts, except for T2D users, who showed no significant change.

    “This shift was consistent across cohorts, except for T2D users, who showed no significant change.”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Findingown data

    The program achieved reduction in carbohydrate and sugar intake while increasing protein and fiber intake per calorie across all groups.

    “A major goal of our program is to reduce carbohydrate and sugar intake while increasing protein and fiber intake per calorie. This was achieved across all groups (Table 1).”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Findingreasoning

    Fat intake per calorie declined in most groups except for those with type 2 diabetes, who exhibited a slight increase.

    “Fat intake per calorie declined in most groups except for those with Type 2 Diabetes, who exhibited a slight increase”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Findingown data

    During the 5-day training period, average TIR for all users was 80.2%; after AI recommendations, average TIR increased to 85.6% (p < 0.0002).

    “During the training period, the average TIR for all users was 80.2%. After the introduction of AI recommendations, the average TIR increased to 85.6% (p < 0.0002).”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Findingown data

    The cohort was 46.3% male and 53.7% female.

    “46.3% were male and 53.7% were female.”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Findingown data

    The cohort was 83% normoglycemic, 10.4% with prediabetes, and 6.5% with diabetes by self-report.

    “The cohort was 83% normoglycemic (“healthy”), 10.4% with prediabetes and 6.5% with diabetes through self reporting.”
    • Also stated in: § Participants · plain
      “The cohort was comprised of healthy (n = 785) and those with prediabetes (n = 98) and type 2 diabetes (T2D) (n = 61) as assessed by users’ self-reporting.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Self-reported health condition, weight, and other demographic data are accurate enough for classifying participants and assessing outcomes.

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Premisecitation

    Type 2 diabetes requires constant monitoring and management due to the mechanism of the disease and its implications on the body's energy expenditure.

    “Type 2 diabetes (T2D) is a condition that requires constant monitoring and management due to the mechanism of the disease and its implications on the body’s energy expenditure2.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [2] Joubert, M. & Reznik, Y. Personal continuous glucose monitoring (CGM) in diabetes management: Review of the literature and implementation for practical use. Diabetes Res Clin. Pr. 96, 294–305 (2012). source

  • It may state two separate claims as one.

    Interpretationown data

    AI-enhanced digital health interventions can improve glycemic control and promote weight loss, particularly when users are actively engaged.

    “These findings suggest that AI-enhanced digital health interventions can improve glycemic control and promote weight loss, particularly when users are actively engaged.”
    • Also stated in: § Discussion · plain
      “The results of this study underscore the potential of digital health interventions, such as the January V2 platform, in improving glycemic control and supporting weight management in individuals with varying stages of metabolic health.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Premisecitation

    Metabolic disease is inversely correlated with income.

    “metabolic disease is inversely correlated with income15.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [15] Allen, K. & McFarland, M. How Are Income and Education Related to the Prevention and Management of Diabetes? J. Aging Health 32, 1063–1074 (2020). source

  • Probably not a substantial claim.

    Interpretationown data

    The lack of significant change in last meal sleep gap among T2D users highlights that this group might have different habits, needs, or challenges when managing meal timing relative to sleep.

    “the lack of significant change among T2D users highlights that this particular group might have different habits, needs, or challenges when it comes to managing meal timing relative to sleep.”
    Quote in the paperSubstantial claim

  • It may state two separate claims as one.

    Interpretationown data

    The average weight reduction of 3.3 lbs over the 33-day period, with the most significant loss in the prediabetes cohort (4.0 lbs), indicates that digital health interventions can be effective in supporting weight management.

    “The average weight reduction of 3.3 lbs over the 33-day period, with the most significant loss observed in the prediabetes cohort (4.0 lbs), indicates that digital health interventions can be effective in supporting weight management.”
    Quote in the paperSubstantial claim

  • It may state two separate claims as one.

    Premisecitation

    For individuals with Type 1 and Type 2 diabetes, optimal TIR is >70%; each additional 5% increase in TIR is associated with clinically significant benefits.

    “For individuals with Type 1 and Type 2 diabetes, optimal TIR is > 70%; each additional 5% increase in TIR is associated with clinically significant benefits for those populations20,21.”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [20] Beck, R. W. et al. The Relationships Between Time in Range, Hyperglycemia Metrics, and HbA1c. J. Diabetes Sci. Technol. 13, 614–626 (2019). source
    • cites [21] Vigersky, R. A. & McMahon, C. The Relationship of Hemoglobin A1C to Time-in-Range in Patients with Diabetes. Diabetes Technol. Ther. 21, 81–85 (2019). source

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Interpretationown data

    The shift in last meal sleep gap in non-T2D groups indicates a broader behavioral trend that could have positive implications for sleep quality and metabolic health.

    “The shift in non-T2D groups indicates a broader behavioral trend that could have positive implications for sleep quality and metabolic health.”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Interpretationown data

    The results underscore the potential of digital health interventions such as the January V2 platform in improving glycemic control and supporting weight management in individuals with varying stages of metabolic health.

    “The results of this study underscore the potential of digital health interventions, such as the January V2 platform, in improving glycemic control and supporting weight management in individuals with varying stages of metabolic health.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.

    Interpretationreasoning

    The slight increase in fat intake in the T2D group is likely due to the substitution of carbohydrate-rich "spiking foods" for foods with higher fat content.

    “likely due to the substitution of carbohydrate rich “spiking foods” for foods with higher fat content.”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Interpretationown data

    Power users exhibited more significant improvements in TIR, suggesting that consistent use of the platform's features is crucial for achieving optimal glycemic control.

    “The “power users” in this study, who demonstrated the highest levels of engagement, exhibited more significant improvements in TIR, suggesting that consistent use of the platform’s features is crucial for achieving optimal glycemic control.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.

    Study design and conductown data

    For other variables of interest, missing data were minimal (<1%) and participants with missing data for a specific outcome were excluded from that particular analysis.

    “For other variables of interest, missing data were minimal (< 1%) and participants with missing data for a specific outcome were excluded from that particular analysis.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.

    Premisecitation

    Continuous use of CGMs in non-insulin users can be burdensome physically and financially and may not provide immediate perceived benefits.

    “continuous use of CGMs in non-insulin users can sometimes be burdensome both physically and financially due to the invasiveness and cost of the devices, and may not provide immediate perceived benefits7.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [7] Klonoff, D. C. et al. Use of Continuous Glucose Monitors by People Without Diabetes: An Idea Whose Time Has Come? J. Diabetes Sci. Technol. 17, 1686–1697 (2023). source

  • It may state two separate claims as one.

    Premisecitation

    The Diabetes Prevention Program is hampered by high user burden and lack of engagement.

    “Despite this success, DPP is hampered by a high user burden and lack of engagement.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [12] Ronn, K. The challenge holding back the diabetes prevention program. MedicalEconomics (2022). Available from: https://www.medicaleconomics.com/view/the-challenge-holding-back-the-diabetes-prevention-program

  • It may state two separate claims as one.

    Interpretationown data

    The minor reduction in GMI indicates a small improvement in average blood glucose levels and potentially better glucose management.

    “This minor reduction indicates a small improvement in average blood glucose levels and, by extension, potentially better glucose management by the end of the study.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Study design and conductown data

    Of 944 participants, 702 users (74.4%) had complete weight data and were included in the weight analysis.

    “Of the 944 participants, 702 users (74.4%) had complete weight data (logged their body weight more than once) and were included in the weight analysis.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Study design and conductown data

    There was considerable variation in the number of days between users' first and last weight logs.

    “there was considerable variation, with some users logging for shorter or longer periods.”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Premisecitation

    The National Diabetes Prevention Program is clinically proven to reduce the risk of developing type 2 diabetes by 58%, and among those 60 years or older, by 71%.

    “the National Diabetes Prevention Program is clinically proven to reduce the risk of developing T2D by 58%, and, among those 60 years or older, by 71%10.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [10] Fowler, S. Diabetes Prevention Program (V9) [Dataset]. NIDDK Central Repository (2024).

      Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  • It may state two separate claims as one.

    Interpretationown data

    The decrease from 0.17 to 0.06 events per day suggests that the January V2 platform helps users manage their blood glucose levels and may stabilize them.

    “The decrease from 0.17 to 0.06 events per day suggests that the January V2 platform helps users manage their blood glucose levels and may stabilize them.”
    Quote in the paperSubstantial claim

  • It may state two separate claims as one.

    Interpretationown data

    The lack of significant changes in hyperglycemic events, except in the prediabetes cohort, suggests that the platform is effective in preventing low blood glucose levels but may be less impactful in preventing spikes in certain populations.

    “the lack of significant changes in hyperglycemic events, except in the prediabetes cohort, suggests that while the platform is effective in preventing low blood glucose levels, it may be less impactful in preventing spikes in certain populations.”
    Quote in the paperSubstantial claim

  • It may state two separate claims as one.

    Interpretationreasoning

    Participants may not accurately remember or report their dietary habits or health conditions, which could affect the accuracy of the findings.

    “Participants may not accurately remember or report their dietary habits or health conditions, which could affect the accuracy of the findings.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim.

    Interpretationreasoning

    Some observed improvements may be partially attributable to external factors rather than solely to the intervention.

    “It is possible that some observed improvements may be partially attributable to these external factors rather than solely to the intervention.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Study design and conductnone given

    Missing data were addressed through a complete case analysis approach.

    “Missing data were addressed through a complete case analysis approach.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Study design and conductown data

    The study adjusted for known confounders like age, sex, and baseline health status.

    “While we adjusted for known confounders like age, sex, and baseline health status”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Interpretationown data

    Digital health interventions (January V2) can effectively improve glycemic control (TIR) and support weight loss, particularly in individuals with lower baseline health metrics.

    “This study provides evidence that digital health interventions can effectively improve glycemic control and support weight loss, particularly in individuals with lower baseline health metrics.”
    • Also stated in: § Discussion · boosted
      “Overall, this study demonstrates that digital health interventions can lead to significant improvements in TIR, weight, and glycemic stability, particularly among users with lower baseline metrics.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Self-reported health condition, weight, and other demographic data are accurate enough for classifying participants and assessing outcomes.
    • Rests on an assumption: Improvements in TIR, weight, and glycemic stability observed in this retrospective cohort are attributable to the digital health intervention rather than to secular trends, regression to the mean, or other unmeasured confounders.
    • Rests on an assumption: Findings from this self-selected cohort of January V2 users generalize to broader populations and healthcare settings.

  • Probably not a substantial claim.

    Study design and conductnone given

    Participants who did not complete the minimum required days were excluded from the analysis.

    “Participants who did not complete the minimum required days were excluded from the analysis.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Study design and conductreasoning

    No formal power analysis was conducted because the study was observational and retrospective.

    “Given the observational nature of this retrospective study, no formal power analysis was conducted.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim.

    Study design and conductown data

    To control for potential confounders such as age, sex, baseline health status, and engagement level, multivariate regression analyses were conducted, adjusting for these confounders.

    “To control for potential confounders, such as age, sex, baseline health status, and engagement level, we conducted multivariate regression analyses where appropriate.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Study design and conductreasoning

    User retention rates were high due to the short duration of the study period.

    “User retention rates were high due to the short duration of the study period.”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Study design and conductown data

    The study did not collect data on participants' concurrent use of weight loss or diabetes medications, nor their participation in other glycemic control or weight management programs.

    “Fourth, we did not collect data on participants’ concurrent use of weight loss or diabetes medications, nor their participation in other glycemic control or weight management programs.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper may give no reason why it holds.

    Study design and conductnone given

    The large sample size is sufficient to detect significant changes in the primary outcomes.

    “However, the large sample size is sufficient to detect significant changes in the primary outcomes.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim. It may state two separate claims as one.

    Study design and conductnone given

    Participants were self-selected users who opted to use the app, and data were collected retrospectively from the app's database.

    “Participants were self-selected users who opted to use the app, and data were collected retrospectively from the app’s database.”
    Quote in the paperSubstantial claim

  • It may state two separate claims as one.

    Premisecitation

    For individuals with Type 1 and Type 2 diabetes, optimal TIR is >70%, and each additional 5% increase in TIR is associated with clinically significant benefits.

    “For individuals with Type 1 and Type 2 diabetes, optimal TIR is > 70%; each additional 5% increase in TIR is associated with clinically significant benefits for those populations20,21.”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [20] Beck, R. W. et al. The Relationships Between Time in Range, Hyperglycemia Metrics, and HbA1c. J. Diabetes Sci. Technol. 13, 614–626 (2019). source
    • cites [21] Vigersky, R. A. & McMahon, C. The Relationship of Hemoglobin A1C to Time-in-Range in Patients with Diabetes. Diabetes Technol. Ther. 21, 81–85 (2019). source

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Study design and conductown data

    The sample size of 944 participants was determined by the number of users who met the inclusion criteria during the study period.

    “The sample size of 944 participants was determined by the number of users who met the inclusion criteria during the study period (see below).”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.

    Study design and conductown data

    The Food Detect algorithm has not been formally validated in a separate study, but internal testing suggests a reasonable level of accuracy in identifying meal events based on physiological signals.

    “While the precise accuracy of the Food Detect algorithm has not been formally validated in a separate study, internal testing suggests a reasonable level of accuracy in identifying meal events based on physiological signals.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.

    Study design and conductnone given

    The study was conducted in accordance with the principles outlined in the Declaration of Helsinki and adhered to all applicable data protection and privacy laws.

    “Nonetheless, the study was conducted in accordance with the principles outlined in the Declaration of Helsinki and adhered to all applicable data protection and privacy laws.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Study design and conductreasoning

    The reliance on self-reported data, such as food intake and health status, introduces the potential for recall bias.

    “Fifth, the reliance on self-reported data, such as food intake and health status, introduces the potential for recall bias.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim. The authors may not put it forward as true. The paper’s conclusions may not depend on it.

    Interpretationreasoning

    This raises the question of whether these are missed diagnoses given the correlation of higher body weight with insulin resistance.

    “raising the question of whether these are missed diagnoses given the correlation of higher body weight with insulin resistance.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim.

    Interpretationreasoning

    The lack of significant change in last meal sleep gap among T2D users may indicate the need for more tailored interventions to address their specific challenges.

    “the lack of significant change in this metric among T2D users may indicate the need for more tailored interventions to address their specific challenges.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Study design and conductnone given

    Diagnostic criteria for health conditions were based on self-reported medical history.

    “Diagnostic criteria for health conditions were based on self-reported medical history.”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Interpretationreasoning

    The increase in protein and fiber intake, along with the reduction in carbohydrate and sugar consumption, particularly in the T2D cohort, suggests that users were able to make meaningful adjustments to their diet, likely contributing to their weight loss and improved glycemic control.

    “the increase in protein and fiber intake, along with the reduction in carbohydrate and sugar consumption, particularly in the T2D cohort, suggests that users were able to make meaningful adjustments to their diet, likely contributing to their weight loss and improved glycemic control.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Interpretationreasoning

    Other factors such as socioeconomic status, education level, or access to healthcare could play a role.

    “other factors such as socioeconomic status, education level, or access to healthcare could play a role.”
    Quote in the paperNot a substantial claim

  • It may state two separate claims as one.

    Study design and conductreasoning

    The dataset complies with the HHS Safe Harbor method for de-identification under the HIPAA Privacy Rule, as it excludes all identifiers and cannot be linked back to individuals.

    “This dataset complies with the HHS Safe Harbor method for de-identification under the HIPAA Privacy Rule, as it excludes all identifiers and cannot be linked back to individuals.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Premisecitation

    Radhakrishnan examined 10 studies and showed that, after accounting for cost and resource utilization, the efficacy of tailored interventions may not exceed that of standard interventions in the improvement of disease self-management.

    “Radhakrishnan32 examined 10 studies and showed that, after accounting for cost and resource utilization, the efficacy of tailored interventions may not exceed that of standard interventions in the improvement of disease self-management.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [32] Radhakrishnan, K. The efficacy of tailored interventions for self‐management outcomes of type 2 diabetes, hypertension or heart disease: a systematic review. J. Adv. Nurs. 68, 496–510 (2012). source

  • Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.

    Interpretationown data

    The slight increase in the last meal sleep gap across most cohorts, except for T2D users, may suggest a positive shift towards better dietary habits, such as earlier meal times, which can contribute to better glycemic control during sleep.

    “The slight increase in the last meal sleep gap across most cohorts, except for T2D users, may suggest a positive shift towards better dietary habits, such as earlier meal times, which can contribute to better glycemic control during sleep.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim. It may state two separate claims as one.

    Interpretationcitation

    These users may have higher levels of motivation, health literacy, or self-efficacy compared to the general population, potentially leading to better engagement and outcomes.

    “These users may have higher levels of motivation, health literacy, or self-efficacy compared to the general population, potentially leading to better engagement and outcomes37.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [37] Ryan, R. M. & Deci, E. L. Intrinsic and extrinsic motivations: Classic definitions and new directions. Contemp. Educ. Psychol. 25, 54–67 (2000). source

  • Probably not a substantial claim. The paper’s conclusions may not depend on it.

    Study design and conductnone given

    Weight was self-reported.

    “Weight was self reported.”
    Quote in the paperNot a substantial claim
68 of 68

  • The paper relies on this without support.

    AI can estimate glucose levels based on historical data and behavioral patterns, reducing the need for constant monitoring.

    “By harnessing predictive algorithms and data modeling, AI can estimate glucose levels based on historical data and behavioral patterns, reducing the need for constant monitoring.”

  • The paper relies on this without support.

    Flexible programs that allow users to engage at their own pace, without rigid schedules or frequent device use, are likely to see better adherence.

    “Furthermore, flexible programs that allow users to engage at their own pace, without feeling constrained by rigid schedules or frequent device use, are likely to see better adherence.”

  • The paper relies on this without support.

    In healthy individuals, glucose levels below 70 mg/dL are not necessarily dangerous and can be part of normal physiology.

    “However, in healthy individuals, glucose levels below 70 mg/dL are not necessarily dangerous and can be part of normal physiology.”

  • The paper relies on this without support.

    The 5-day training period and the subsequent 9-day intervention period are comparable except for the introduction of AI recommendations, so changes between them can be attributed to the AI feature.

    “To estimate the isolated effect of the AI feature beyond the benefits of food tracking, physical activity, sleep tracking, and CGM, we compared glycemic metrics between the 5-day training period (pre-AI recommendations) and the subsequent 9-day intervention period (post-AI recommendations).”

  • The paper relies on this without support.

    Self-reported health condition, weight, and other demographic data are accurate enough for classifying participants and assessing outcomes.

    “The cohort was 83% normoglycemic (“healthy”), 10.4% with prediabetes and 6.5% with diabetes through self reporting.”
    “Weight was self reported.”
    “Diagnostic criteria for health conditions were based on self-reported medical history.”

  • The paper relies on this without support.

    Improvements in TIR, weight, and glycemic stability observed in this retrospective cohort are attributable to the digital health intervention rather than to secular trends, regression to the mean, or other unmeasured confounders.

    “This study provides evidence that digital health interventions can effectively improve glycemic control and support weight loss, particularly in individuals with lower baseline health metrics.”
    “Overall, this study demonstrates that digital health interventions can lead to significant improvements in TIR, weight, and glycemic stability, particularly among users with lower baseline metrics.”

  • The paper relies on this without support.

    Findings from this self-selected cohort of January V2 users generalize to broader populations and healthcare settings.

    “The broader implications of this study suggest that digital health platforms like January V2 have the potential to play a crucial role in the future of chronic disease management.”
    “This study provides evidence that digital health interventions can effectively improve glycemic control and support weight loss, particularly in individuals with lower baseline health metrics.”
7 of 7

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • AI-based DPP studies reported to date have been single-group or other nonrandomized designs.

    “The AI-based DPP studies reported to date have been single-group or other nonrandomized designs.12,20,21”

    From An AI-Powered Lifestyle Intervention vs Human Coaching in the Diabetes Prevention Program: A Randomized Clinical Trial (2025) · cites this paper as [21]

    The Discussion (page unavailable) says this AI-enabled digital health study had no control group, supporting its classification as nonrandomized. The Introduction discusses the Diabetes Prevention Program separately; the paper does not establish that its intervention was an AI-based DPP or that all AI-based DPP studies reported to date used nonrandomized designs. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

  • Healthy group did not have the largest reduction in fat intake

    Minor

    The figure caption calls the healthy group's 11.6% reduction in relative fat intake the largest, but also states that the prediabetes group's reduction was larger, at 13.0%.

1 of 1

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 1

  1. Prabhod, K. J. The Role of Artificial Intelligence in Reducing Healthcare Costs and Improving Operational Efficiency. Q J. Emerg. Technol. Innov. 9, 47–59 (2024).

Cited by

Sorted by citations

Related

Metadata

Authors
Veluvali, A., Dehghani Zahedani, A., Hosseinian, A., Aghaeepour, N., McLaughlin, T., Woodward, M., DiTullio, A., Hashemi, N., & Snyder, M. P.
Corresponding author
Snyder, Michael P.
ORCID
Venue
npj Digital Medicine
Publisher
Springer Science and Business Media LLC
Published
2025-01-09
Volume
8
Issue
1
Pages
20-20
ISSN
2398-6352 (ISSN-L)
DOI
10.1038/s41746-025-01430-7
PMC
PMC11717909
OpenAlex
W4406221555
Cited by
45
References
38
Citations by year
2026: 24 · 2025: 21
FWCI
33.35
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
  • Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Management and Research
  • Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Management and Education
Keywords
continuous glucose monitoring, mobile health apps, artificial intelligence, glycemic control, time in range, weight loss, prediabetes, type 2 diabetes, app engagement, personalized feedback, dietary monitoring, physical activity monitoring

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review