The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index; 17 of the 43 sources its claims cite were checked for support.
My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial
Open accessPublished version of a preprint
Abstract
Background: Delivering self-management support to people with type 2 diabetes mellitus is essential to reduce the health system burden and to empower people with the skills, knowledge, and confidence needed to take an active role in managing their own health. Objective: This study aims to evaluate the adoption, use, and effectiveness of the My Diabetes Coach (MDC) program, an app-based interactive embodied conversational agent, Laura, designed to support diabetes self-management in the home setting over 12 months. Methods: This randomized controlled trial evaluated both the implementation and effectiveness of the MDC program. Adults with type 2 diabetes in Australia were recruited and randomized to the intervention arm (MDC) or the control arm (usual care). Program use was tracked over 12 months. Coprimary outcomes included changes in glycated hemoglobin (HbA1c) and health-related quality of life (HRQoL). Data were assessed at baseline and at 6 and 12 months, and analyzed using linear mixed-effects regression models. Results: A total of 187 adults with type 2 diabetes (mean 57 years, SD 10 years; 41.7% women) were recruited and randomly allocated to the intervention (n=93) and control (n=94) arms. MDC program users (92/93 participants) completed 1942 chats with Laura, averaging 243 min (SD 212) per person over 12 months. Compared with baseline, the mean estimated HbA1c decreased in both arms at 12 months (intervention: 0.33% and control: 0.20%), but the net differences between the two arms in change of HbA1c (−0.04%, 95% CI −0.45 to 0.36; P=.83) was not statistically significant. At 12 months, HRQoL utility scores improved in the intervention arm, compared with the control arm (between-arm difference: 0.04, 95% CI 0.00 to 0.07; P=.04). Conclusions: The MDC program was successfully adopted and used by individuals with type 2 diabetes and significantly improved the users’ HRQoL. These findings suggest the potential for wider implementation of technology-enabled conversation-based programs for supporting diabetes self-management. Future studies should focus on strategies to maintain program usage and HbA1c improvement. Trial Registration: Australia New Zealand Clinical Trials Registry (ACTRN) 12614001229662; https://anzctr.org.au/Trial/Registration/TrialReview.aspx?ACTRN=12614001229662
Overview
CoChat Summary
TL;DR
In a 12-month Australian randomized trial of 187 adults with type 2 diabetes, the My Diabetes Coach app-based conversational agent was widely adopted and significantly improved health-related quality of life versus usual care, but did not significantly improve HbA1c. Program use declined over time, and the HbA1c between-arm difference was not statistically significant.
Key findings
- Among 187 randomized adults (93 intervention, 94 control), 92/93 intervention participants completed at least one chat with Laura; they completed 1942 chats total, averaging 243 min (SD 212) per person over 12 months, and 83/93 uploaded glucose data.
- HRQoL (AQoL-8D utility) improved significantly in the intervention arm versus control at 12 months: between-arm difference 0.04 (95% CI 0.00-0.07; P=.04); intervention baseline-to-12-month change 0.04 (95% CI 0.01-0.06; P=.007); per-protocol between-arm difference 0.06 (95% CI 0.02-0.09; P=.003).
- HbA1c decreased in both arms at 12 months (intervention −0.33%, control −0.28%), but the between-arm difference was not significant (−0.04%, 95% CI −0.45 to 0.36; P=.83).
- A dose-response relationship was observed for HRQoL: participants completing >24 chats had greater AQoL-8D improvement than those completing <7 chats (between-arm difference 0.09, 95% CI 0.02-0.17; P=.02), with no significant HbA1c difference (−0.33%, 95% CI −1.11 to 0.44; P=.40).
Methods
- Two-arm, open-label randomized controlled trial in Australia; adults aged ≥18 years with type 2 diabetes, registered with the National Diabetes Service Scheme <10 years, with basic English and an internet-enabled smart device; recruitment June 2016–April 2017; 2x4 block randomization via REDCap to intervention or usual care.
- Intervention: My Diabetes Coach app with embodied conversational agent Laura, modules on glucose monitoring, eating, activity, medication, and foot care, plus printed guide, website, optional Bluetooth glucose meter, and coordinator calls; control received usual care and a quarterly newsletter.
- Coprimary outcomes were HbA1c and HRQoL (AQoL-8D) at baseline, 6, and 12 months; linear mixed-effects regression models were used for intention-to-treat, adjusted, and per-protocol analyses in Stata 15.1.
Limitations
- Stated in the paper: participants and their GPs could not be blinded due to the intervention’s nature, so self-report bias and Hawthorne effects may exist; completed assessments were higher in the control arm than the intervention arm; subgroup analyses were underpowered and multiple testing increased false-positive risk.
- Evident from the text: baseline HbA1c was not an inclusion criterion and 52.4% of participants were already in the recommended target range (<7% or 53 mmol/mol), likely limiting detectable HbA1c benefit.
- Evident from the text: program use declined over 12 months (monthly chat users fell from 87% to 15%; glucose recorders from 78% to 23%), and the control arm also reduced HbA1c, which the authors suggest may reflect Hawthorne effects or other self-management.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
8 Valid · 2 Not valid · 13 Not checked · 80 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Our previous studies and others have demonstrated the effectiveness and cost-effectiveness of using technology-enabled programs, including computer-based or telephone-based coaching, in promoting behavior change and self-management among adults with T2DM [7-9].”
§ My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial > Introduction
What the sources say
- Not checked yetcites [7] source
- Partly supportedcites [8] sourceExperimental — accuracy not yet measured
Our copy supports the effectiveness half of the claim: the Discussion (p. Results/Discussion) and Conclusions report that the six-month automated telephone-linked TLC Diabetes program significantly improved glycaemic control (HbA1c ratio 0.91, p = 0.002; Table 3) and mental HRQL in adults with type 2 diabetes, and the Background notes ICT 'has been shown to yield improvements in self-care knowledge and behaviour'. However, the cost-effectiveness element is not demonstrated by this paper: the Discussion describes the program only as '(potentially cost-effective)' support with 'potential for reduced costs', and states that whether the cost of the intervention 'provides acceptable value for money' will be reported elsewhere. Likewise, behaviour change is deferred — 'A subsequent paper will elucidate the changes in behaviour that may have facilitated the improvements observed' — so attributing demonstrated behaviour change and cost-effectiveness to this source overstates it. (LLM, conf=0.80)
- Partly supportedcites [9] sourceExperimental — accuracy not yet measured
Gordon et al. (2014) is a cost-effectiveness analysis of an automated telephone-linked care (TLC Diabetes) program in adults with established Type 2 diabetes, so it does concern a telephone-based technology program and its economic value. However, it does not 'demonstrate' cost-effectiveness: the base case gave a £683 cost saving with a QALY difference (0.004) explicitly 'not considered meaningful', and the Discussion (p. Results/Discussion) states the likelihood of the intervention being cost-effective was 'marginal at 55%'. The behaviour-change/self-management effectiveness element is credited to other works — the Introduction hedges that ICT 'could be an very effective way' and that the technology 'has been previously found to be effective in ... promoting self-care behaviours' for a range of chronic diseases [8–10], while the HbA1c benefit is reported from the parent RCT [4] — and computer-based coaching is not addressed in our copy at all. (LLM, conf=0.78)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Despite the growing number of studies using mobile technologies for diabetes management [10,11,15], the effectiveness of introducing apps to people with T2DM to support their self-management at large scale remains uncertain given the generally poor quality of apps [12,13,32], unmet consumer needs [14], and studies lacking robust designs with long-term evaluations [10,15].”
§ My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial > Discussion
What the sources say
- Not checked yetcites [10] source
- Not checked yetcites [11] source
- Partly supportedcites [15] sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
- Not checked yetcites [12] source
- Supportedcites [13] source
This source is cited for the poor quality of diabetes self-management apps, not for the sentence’s separately cited points about consumer needs or study design. The Discussion’s Principal Findings report that the quality of the reviewed Chinese apps was suboptimal, with poor engagement, low adherence to guidelines, and limited evidence of health benefits. (LLM, conf=0.93)
- Not checked yetcites [32] source
- Not checked yetcites [14] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Although some recent systematic reviews and meta-analyses have indicated a modest effect for app-based interventions to support diabetes self-management [10,11,15], there still remains a great deal of uncertainty about their feasibility, acceptability, and effectiveness in the real world [10,15-17].”
§ My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial > Introduction
What the sources say
- Not checked yetcites [10] source
- Partly supportedcites [15] sourceExperimental — accuracy not yet measured
The Discussion > Limitations section says that real-world effectiveness depends on the quality of user input and that efficacy beyond 12 months remains uncertain. This supports uncertainty about longer-term and real-world effectiveness, but the cited passages do not establish uncertainty about feasibility or acceptability. The Discussion > Conclusion section also reports strong evidence of efficacy for lifestyle modification in type 2 diabetes. (LLM, conf=0.84)
- Not checked yetcites [16] source
- Partly supportedcites [17] sourceExperimental — accuracy not yet measured
In the Discussion sections “Types of Internet-Based Interventions” and “Implications for Future Studies and Clinical Practices” (pages unavailable), the authors call for studies of apps installed on patients’ own phones to establish their effectiveness. They also note possible problems with user-friendliness and satisfaction and call for research on large-scale feasibility, but they do not directly establish uncertainty about the real-world feasibility and acceptability of app-based interventions specifically. (LLM, conf=0.84)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“On the basis of a previous study [30], we estimated that a sample size of 180 participants would provide 80% power at a two-tailed 5% significance level to detect a difference in HbA1c of 0.4% between the 2 arms with three repeated measures based on a previous study.”
§ My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial > Methods > Analytical and Statistical Approaches
What the sources say
- Could not verifycites [30] sourceExperimental — accuracy not yet measured
The Methods (Data synthesis and analyses) describe a meta-analysis, not a power calculation for a 180-person, two-arm study with three repeated measures. The Results (Descriptions of Studies) mention 180 as the size of one included study, and Study Outcomes report a pooled HbA1c difference of −0.40%, but neither passage supports the claimed 80% power estimate. Searches for the sample-size and repeated-measures terms found no such calculation in our copy. (LLM, conf=0.76)
hedgedn = 180- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“previous literature indicates that even a small effect size for HRQoL may bring substantial well-being benefit in the long term [8,27,38].”
§ My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial > Discussion
What the sources say
- Supportedcites [8] source
The Discussion says that even small improvements in health-related quality of life (HRQL) may be clinically significant in the longer term. It also identifies enhanced well-being as an important outcome, supporting the citing sentence’s paraphrase. (LLM, conf=0.90)
- Partly supportedcites [27] sourceExperimental — accuracy not yet measured
The Discussion (page not provided) says AQoL effect sizes as small as 0.13 may indicate important differences and that the measure can detect small changes over time. It does not say those differences produce substantial well-being benefits in the long term. (LLM, conf=0.87)
- Partly supportedcites [38] sourceExperimental — accuracy not yet measured
The Discussion says that a small QOL effect size may be clinically meaningful and that a statistically significant improvement is probably clinically important. It does not establish that the benefit is substantial or persists in the long term; the Results report post-intervention QOL effects, not long-term well-being. (LLM, conf=0.86)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
48 more claims
Create a free account to see all 103 claims and to verify the 26 references still open.
- Probably not a substantial claim. 25
- It may state two separate claims as one. 25
- The quote only partly states this claim. 4
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?
In the citing paper
“Behavior change techniques (BCTs) are an essential component of effective solutions. These involve automated, semi-automated, or human digital feedback [9,10].”
From Long-term Weight Loss in a Primary Care-Anchored eHealth Lifestyle Coaching Program: Randomized Controlled Trial (2022) · cites this paper as [10]
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.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial > Abstract > Results
“the mean estimated HbA1c decreased in both arms at 12 months (intervention: 0.33% and control: 0.20%)”
§ My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial > Results > Program Effectiveness
“control arm: −0.28%, 95% CI −0.57 to 0.00; P=.05”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“Of the 697 individuals with T2DM who expressed interest in participating in the study, 187 were recruited, including 62 (33%) from Victoria, 21 (16.5%) from New South Wales, and 21 (16.5%) from Queensland”
§ My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial > Results > Participant Flow and Baseline Characteristics
Reported 16.5 · recomputed 11.229947
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“| | | Secondary high school or lower | 29 (30.8) | 25 (26.9) | 54 (18.8) | |”
§ My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial > Results > Participant Flow and Baseline Characteristics
Reported 18.8 · recomputed 28.877005
Citations
Cites
Harris, P. A., Taylor, R., Thielke, R., Payne, J., Gonzalez, N., & Conde, J. G. (2009) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2008.08.010 · Cited by 51,384 · cited 2×
“During the screening telephone calls, the research team contacted participants and recorded sociodemographic characteristics (age, sex, education, employment, and language capability), clinical characteristics (duration of NDSS registration and stabilization of the health condition), and app use variables in the REDca…”
MethodThe Hospital Anxiety and Depression Scale
Zigmond, A. S., & Snaith, R. P. (1983) · Acta Psychiatrica Scandinavica · doi:10.1111/j.1600-0447.1983.tb09716.x · Cited by 47,139 · cited 7×
“AQoL-8D: Assessment of Quality of Life-8 Dimensions CONSORT: Consolidated Standards of Reporting Trials GP: general practitioner HADS: Hospital Anxiety and Depression Scale HbA1c: glycated hemoglobin HRQoL: health-related quality of life J Med Internet Res 2020 | vol. 22 | iss.”
MethodInfluentialEvaluating the public health impact of health promotion interventions: the RE-AIM framework.
Glasgow, R. E., Vogt, T. M., & Boles, S. M. (1999) · American Journal of Public Health · doi:10.2105/ajph.89.9.1322 · Cited by 7,217 · cited 1×
“We used the Reach, Effectiveness, Adoption, Implementation, and Maintenance framework to evaluate the impact of the MDC intervention, which covered the 5 dimensions in terms of reach, effectiveness, adoption, implementation, and maintenance [25].”
MethodCurran, G. M., Bauer, M., Mittman, B., Pyne, J. M., & Stetler, C. (2012) · Medical Care · doi:10.1097/mlr.0b013e3182408812 · Cited by 4,058 · cited 1×
“We undertook a hybrid effectiveness-implementation study [18] with a randomized controlled design.”
MethodHealth behavior : theory, research, and practice
Glanz, K., Rimer, B. K., & Viswanath, K. (2015) · Cited by 2,218
Self-Management: A Comprehensive Approach to Management of Chronic Conditions
Grady, P. A., & Gough, L. L. (2014) · American Journal of Public Health · doi:10.2105/ajph.2014.302041 · Cited by 923 · cited 1×
“The conversational scripts and algorithms guiding each individual’s progress were designed by applying behavior change theories and techniques, including the transtheoretical model [21], social cognitive theory [22], gamification [23], and other concepts derived from chronic disease self-management [24].”
MethodIntention-to-Treat Analysis: Implications for Quantitative and Qualitative Research
NEWELL, D. J. (1992) · International Journal of Epidemiology · doi:10.1093/ije/21.5.837 · Cited by 715 · cited 2×
“The main effectiveness analysis followed the intention-to-treat principle [31].”
BackgroundMethodThe problem areas in diabetes scale: an evaluation of its clinical utility
Welch, G. W., Jacobson, A. M., & Polonsky, W. H. (1997) · Diabetes Care · doi:10.2337/diacare.20.5.760 · Cited by 664 · cited 1×
“distress, assessed by the Problem Areas in Diabetes scale [29]; and clinical measurement of body weight.”
MethodGamification: What It Is and Why It Matters to Digital Health Behavior Change Developers
Cugelman, B. (2013) · JMIR Serious Games · doi:10.2196/games.3139 · Cited by 531 · cited 1×
“The conversational scripts and algorithms guiding each individual’s progress were designed by applying behavior change theories and techniques, including the transtheoretical model [21], social cognitive theory [22], gamification [23], and other concepts derived from chronic disease self-management [24].”
MethodRichardson, J., Iezzi, A., Khan, M. A., & Maxwell, A. (2014) · The Patient - Patient-Centered Outcomes Research · doi:10.1007/s40271-013-0036-x · Cited by 504
Research works printed but not linked: 1
- Crosby, R, 2013, Health Behavior Theory for Public Health: Principles, Foundations, and Applications, 163
Cited by
Jakob, R., Harperink, S., Rudolf, A. M., Fleisch, E., Haug, S., Mair, J. L., Salamanca-Sanabria, A., & Kowatsch, T. (2022) · Journal of Medical Internet Research · doi:10.2196/35371 · Cited by 446
“Intervention-related factors that positively influenced adherence to diabetes apps included automated and passive data collection within the app [31,34], customized reminders [31], game-based elements [32], and human-like app characteristics [32].”
BackgroundMethodInfluentialRoles, Users, Benefits, and Limitations of Chatbots in Health Care: Rapid Review
Laymouna, M., Ma, Y., Lessard, D., Schuster, T., Engler, K., & Lebouché, B. (2024) · Journal of Medical Internet Research · doi:10.2196/56930 · Cited by 305
“In addition, 11 chatbots were each studied twice (Todaki [90,102], GAMBOT [97,133], Laura [98,121], Vik [108,186], Termbot [151,195], ChatPal [158,168], a chatbot in a virtual ward [180,194], Corowa-kun [181,197], Dokbot [189,192], BotMaria [193,205], and COUCH [236,237]).”
Roles, Users, Benefits, and Limitations of Chatbots in Health Care: Rapid Review (Preprint)
Laymouna, M., Ma, Y., Lessard, D., Schuster, T., Engler, K., & Lebouché, B. (2024) · doi:10.2196/preprints.56930 · Cited by 302
Kurniawan, M. H., Handiyani, H., Nuraini, T., Hariyati, R. T. S., & Sutrisno, S. (2024) · Annals of Medicine · doi:10.1080/07853890.2024.2302980 · Cited by 177
Moschonis, G., Siopis, G., Jung, J., Eweka, E., Willems, R., Kwasnicka, D., Asare, B. Y.-A., Kodithuwakku, V., Verhaeghe, N., Vedanthan, R., et al. (2023) · The Lancet Digital Health · doi:10.1016/s2589-7500(22)00233-3 · Cited by 149
Self-citation
Metadata
- Authors
- Gong, E., Baptista, S., Russell, A., Scuffham, P., Riddell, M., Speight, J., Bird, D., Williams, E., Lotfaliany, M., & Oldenburg, B.
- Affiliations
- The University of Melbourne (AU)
- The University of Queensland (AU)
- Griffith University (AU)
- UNSW Sydney (AU)
- Deakin University (AU)
- University of Surrey (GB)
- Corresponding author
- Gong, Enying
- ORCID
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2020-11-05
- Volume
- 22
- Issue
- 11
- Pages
- e20322
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC7677021
- OpenAlex
- W3047309370
- Semantic Scholar
- 151f52813ed0cbc637d4de4d3413e5fff92cf323
- Cited by
- 159
- References
- 36
- Citations by year
- 2026: 32 · 2025: 36 · 2024: 29 · 2023: 26 · 2022: 22 · 2021: 14
- FWCI
- 16.18
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Journal of Medical Internet Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Minerva Access (University of Melbourne) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- Griffith Research Online (submittedVersion, other-oa)
- Funders
- Bupa Foundation
- Diabetes Australia
- Deakin University
- Roche Diabetes Care
- Diabetes Victoria
- Medical Research Council
- National Health and Medical Research Council (1170937)
- Topics
- Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
- Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Management and Education
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Keywords
- type 2 diabetes, diabetes self-management, mobile health apps, chatbots, HbA1c, health-related quality of life, implementation effectiveness, digital health interventions, health behavior change
- MeSH terms
- Aged, Aged, 80 and over, Communication, Diabetes Mellitus, Type 2, Female, Glycated Hemoglobin, Humans, Male, Middle Aged, Mobile Applications
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial. https://app.cochat.ai/papers/10.2196/20322
- The paper
- Gong, E., Baptista, S., Russell, A., Scuffham, P., Riddell, M., Speight, J., Bird, D., Williams, E., Lotfaliany, M., & Oldenburg, B. (2020). My Diabetes Coach, a Mobile App–Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial. Journal of Medical Internet Research. https://doi.org/10.2196/20322
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
