JMIR Diabetes最新文献

{"title":"DigiBete, a Novel Chatbot to Support Transition to Adult Care of Young People/Young Adults With Type 1 Diabetes Mellitus: Outcomes From a Prospective, Multimethod, Nonrandomized Feasibility and Acceptability Study.","authors":"Veronica Swallow, Janet Horsman, Eliza Mazlan, Fiona Campbell, Reza Zaidi, Madeleine Julian, Jacob Branchflower, Jackie Martin-Kerry, Helen Monks, Astha Soni, Alison Rodriguez, Rob Julian, Paul Dimitri","doi":"10.2196/74032","DOIUrl":"10.2196/74032","url":null,"abstract":"<p><strong>Background: </strong>Transition to adult health care for young people and young adults (YP/YA) with type 1 diabetes mellitus (T1DM) starts around 11 years of age, but transition services may not meet their needs. A combination of self-management support digital health technologies exists, but no supportive chatbots with components to help YP/YA with T1DM were identified.</p><p><strong>Objective: </strong>The aims of this study were to (1) evaluate the novel DigiBete Chatbot, the first user-led, developmentally appropriate, clinically approved transition chatbot for YP/YA with T1DM from four English diabetes services and (2) assess the feasibility of a future trial of the chatbot.</p><p><strong>Methods: </strong>In a prospective, multimethod, nonrandomized feasibility and acceptability study in the UK National Health Service, YP/YA with T1DM from 4 hospital diabetes clinics (2 pretransition and 2 posttransition) were enrolled in a 6-week study to test the DigiBete Chatbot. During the study, YP/YA completed web-based, validated, and standardized questionnaires at baseline, 2 weeks, and 6 weeks to evaluate quality of life and anxiety and depression, along with chatbot usability and acceptability. Qualitative interviews involving YP/YA, parents, and health care professionals explored their views on the chatbot. Data were analyzed using descriptive statistics and framework analysis.</p><p><strong>Results: </strong>Eighteen YP/YA were enrolled. Qualitative interviews were conducted with 4 parents, 24 health care professionals, and 12 YP/YA. Questionnaire outputs and the emergent qualitative themes (living with T1DM, using the chatbot, and refining the chatbot) indicated that the measures are feasible to use and the chatbot is acceptable and functional. In addition, responses indicated that, with refinements that incorporate the feasibility results, the chatbot could beneficially support YP/YA during transition. Users scored the chatbot as \"good\" to \"excellent\" for being engaging, informative, and aesthetically pleasing, and they stated that they would use it again. The results suggest that, with some adaptations based on user feedback, the chatbot was feasible and acceptable among the YP/YA who enjoyed using it. Our reactive conversational agent offers content (messaging and additional multimedia resources) that is relevant for the target population and clinically approved. The DigiBete Chatbot addresses the identified lack of personalized and supported self-management tools available for 11-24 year olds with T1DM and other chronic conditions.</p><p><strong>Conclusions: </strong>These results warrant chatbot refinement and further investigation in a full trial to augment it prior to its wider clinical use. Our research design and methodology could also be transferred to using chatbots for other long-term conditions. On the premise of this feasibility study, the plan is to rebuild the DigiBete Chatbot to meet identified user needs and prefere","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"10 ","pages":"e74032"},"PeriodicalIF":0.0,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144692312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Privacy-Preserving Glycemic Management in Type 1 Diabetes: Development and Validation of a Multiobjective Federated Reinforcement Learning Framework.","authors":"Fatemeh Sarani Rad, Juan Li","doi":"10.2196/72874","DOIUrl":"10.2196/72874","url":null,"abstract":"<p><strong>Background: </strong>Effective diabetes management requires precise glycemic control to prevent both hypoglycemia and hyperglycemia, yet existing machine learning (ML) and reinforcement learning (RL) approaches often fail to balance competing objectives. Traditional RL-based glucose regulation systems primarily focus on single-objective optimization, overlooking factors such as minimizing insulin overuse, reducing glycemic variability, and ensuring patient safety. Furthermore, these approaches typically rely on centralized data processing, which raises privacy concerns due to the sensitive nature of health care data. There is a critical need for a decentralized, privacy-preserving framework that can personalize blood glucose regulation while addressing the multiobjective nature of diabetes management.</p><p><strong>Objective: </strong>This study aimed to develop and validate PRIMO-FRL (Privacy-Preserving Reinforcement Learning for Individualized Multi-Objective Glycemic Management Using Federated Reinforcement Learning), a novel framework that optimizes clinical objectives-maximizing time in range (TIR), reducing hypoglycemia and hyperglycemia, and minimizing glycemic risk-while preserving patient privacy.</p><p><strong>Methods: </strong>We developed PRIMO-FRL, integrating multiobjective reward shaping to dynamically balance glucose stability, insulin efficiency, and risk reduction. The model was trained and tested using simulated data from 30 simulated patients (10 children, 10 adolescents, and 10 adults) generated with the Food and Drug Administration (FDA)-approved UVA/Padova simulator. A comparative analysis was conducted against state-of-the-art RL and ML models, evaluating performance using metrics such as TIR, hypoglycemia (<70 mg/dL), hyperglycemia (>180 mg/dL), and glycemic risk scores.</p><p><strong>Results: </strong>The PRIMO-FRL model achieved a robust overall TIR of 76.54%, with adults demonstrating the highest TIR at 81.48%, followed by children at 77.78% and adolescents at 70.37%. Importantly, the approach eliminated hypoglycemia, with 0.0% spent below 70 mg/dL across all cohorts, significantly outperforming existing methods. Mild hyperglycemia (180-250 mg/dL) was observed in adolescents (29.63%), children (22.22%), and adults (18.52%), with adults exhibiting the best control. Furthermore, the PRIMO-FRL approach consistently reduced glycemic risk scores, demonstrating improved safety and long-term stability in glucose regulation..</p><p><strong>Conclusions: </strong>Our findings highlight the potential of PRIMO-FRL as a transformative, privacy-preserving approach to personalized glycemic management. By integrating federated RL, this framework eliminates hypoglycemia, improves TIR, and preserves data privacy by decentralizing model training. Unlike traditional centralized approaches that require sharing sensitive health data, PRIMO-FRL leverages federated learning to keep patient data local, significantly reducing privacy","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"10 ","pages":"e72874"},"PeriodicalIF":0.0,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12248133/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144565505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Young Adults With Type 1 Diabetes and Their Perspectives on Diabetes-Related Social Media: Qualitative Study.","authors":"Tara Maxwell, Lillian Branka, Noa Asher, Persis Commissariat, Lori Laffel","doi":"10.2196/69243","DOIUrl":"10.2196/69243","url":null,"abstract":"<p><strong>Background: </strong>Young adults with type 1 diabetes (T1D) often struggle with self-management and achieving target glycemic control, and thus, may benefit from additional support during this challenging developmental life stage. They are also some of the highest users of social media (SM), which may have some benefits to young people with T1D.</p><p><strong>Objective: </strong>Given the potential of SM support for people with diabetes, we sought to use qualitative methods to explore the perceptions of diabetes SM posts to influence self-care and emotional state of young adults with T1D.</p><p><strong>Methods: </strong>A series of Instagram (Meta) posts were selected by a multidisciplinary team of T1D experts. Young adults aged 18-25 years with T1D duration of 1 year or more were recruited from the clinic to participate in a 60-minute semistructured videoconferencing interview. First, they were queried about their SM use in general and specific to diabetes. Next, they reviewed 10 posts with the interviewer. For each post, perceptions and reactions were queried. Participants were asked about each post's impact on their emotional state and potential influence on diabetes self-care. Finally, they were asked to comment on what the posts emphasized and how they felt after viewing the posts. Interviews were transcribed and coded using thematic analysis. The participants' diabetes management information was extracted from the electronic health record.</p><p><strong>Results: </strong>There were 26 young adults who completed the study. Their mean (SD) age was 22.6 (SD 2.0) years, T1D duration 12.6 (SD 5.9) years, and glycated hemoglobin (HbA1c) 7.6 (SD 1.2%). In this sample, 65.3 were female and 84.6% White. All were using continuous glucose monitors (CGMs) and 80.7% used insulin pumps, 71.4% of which were hybrid closed loop. All participants used SM at least once daily, but most only sometimes or rarely used SM to access diabetes content and rarely or never posted diabetes content themselves. Major themes arising from the interviews centered on the potential for the young adult to connect emotionally through SM, which could be either positive or negative. Overall, for young adults with T1D, SM served to (1) highlight the existence of a community of people with T1D, (2) be a source of new diabetes information, (3) potentially influence diabetes self-management, (4) potentially influence emotional state, and (5) be appealing to the T1D community when the posts possessed certain characteristics (eg, medical accuracy, aesthetically appealing presentation of content).</p><p><strong>Conclusions: </strong>SM has the potential to help young adults with T1D feel a sense of community, seek and share objective and subjective thoughts and feelings about diabetes, motivate diabetes self-care, and positively affect emotional state. However, it may also have the potential to demotivate self-care and exacerbate negative emotional state with regards to diabe","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"10 ","pages":"e69243"},"PeriodicalIF":0.0,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12272138/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Continuous Glucose Monitoring in Primary Care: Multidisciplinary Pilot Implementation Study.","authors":"Alyssa H Zadel, Katia Chiampas, Katrina Maktaz, John G Keller, Kathy W O'Gara, Leonardo Vargas, Angela Tzortzakis, Micah J Eimer, Emily D Szmuilowicz","doi":"10.2196/69061","DOIUrl":"10.2196/69061","url":null,"abstract":"<p><strong>Background: </strong>Continuous glucose monitoring (CGM) is used to assess glycemic trends and guide therapeutic changes for people with diabetes. We aimed to increase patient access to this tool by equipping primary care physicians (PCPs) to accurately interpret and integrate CGM into their practice via a multidisciplinary team approach.</p><p><strong>Objective: </strong>The primary objective of this study was to evaluate the feasibility and effectiveness of integrating CGM into primary care clinics using a multidisciplinary approach that included a clinical pharmacist (PharmD) and a certified diabetes care and education specialist (CDCES).</p><p><strong>Methods: </strong>Eighteen PCPs received a 1-hour video training module from an endocrinologist teaching a systematic stepwise approach to CGM interpretation. Patient inclusion criteria included type 2 diabetes mellitus, ≥18 years old, hemoglobin A1c (HbA1c) ≥8% or concern for hypoglycemia, and no previous CGM use or an endocrinology visit in the past year. Patients saw physician extenders (CDCES or a PharmD) for professional CGM placement and education on nutrition, medication administration, and physical activity goals based on the PCP's recommendations. The CDCES or PharmD reviewed CGM data with patients and collaborated with PCPs to adjust the care plan, informed by the systematic stepwise approach to CGM interpretation. Patients either converted to personal CGM if desired or had a second professional CGM device placed after ≥1 month from the initial professional CGM placement and obtained a postintervention HbA1c measurement at ≥3 months from the initial HbA1c measurement. The primary outcomes were time in range, HbA1c, and average time from referral to the first CGM device placement. Follow-up continued with the CDCES or PharmD until patients met the study discharge criteria of HbA1c level ≤7%. Paired t tests with 1-sided P values were used to assess changes in glucose metrics from the initial to postintervention measurements. The McNemar test was used to determine the significance of change in patients meeting the goal of ≥70% time in the target range of 70-180 mg/dL.</p><p><strong>Results: </strong>The CGM users (n=46) had a mean (SD) age of 62.39 (14.57) years, and 14/46 participants (30%) were female. The mean (SD) time in range increased by 28.06%, from 43.25% (33.41%) at baseline to 71.31% (25.49%) postintervention (P<.001), due to reduced hyperglycemia. The proportion of CGM users meeting the consensus target of the time in range ≥70% increased from 23.81% to 57.14% (P<.001). Postintervention HbA1c decreased by an average of 2.37%, from 9.68% (1.78%) to 7.31% (1.32%; P<.001).</p><p><strong>Conclusions: </strong>The integration of CGM into primary care clinics to increase patient access is feasible and effective using a multidisciplinary approach.</p>","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"10 ","pages":"e69061"},"PeriodicalIF":0.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12192913/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144327728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Use of AI-Powered Thermography to Detect Early Plantar Thermal Abnormalities in Patients With Diabetes: Cross-Sectional Observational Study.","authors":"Meshari F Alwashmi, Mustafa Alghali, AlAnoud AlMogbel, Abdullah Abdulaziz Alwabel, Abdulaziz S Alhomod, Ibrahim Almaghlouth, Mohamad-Hani Temsah, Amr Jamal","doi":"10.2196/65209","DOIUrl":"10.2196/65209","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Diabetic foot problems are among the most debilitating complications of diabetes mellitus. Diabetes prevalence and complications, notably diabetic foot ulcers (DFUs), continue to rise, challenging health care despite advancements in medicine. Traditional DFU detection methods face scalability issues due to inefficiencies in time and practical application, leading to high recurrence and amputation rates alongside substantial health care costs. Human medical thermography could significantly enhance disease monitoring and detection, including DFUs.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study evaluated the efficacy of artificial intelligence-powered thermography in detecting plantar thermal patterns that differentiate between adult patients with diabetes with no visible foot ulcers and healthy individuals without diabetes.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This cross-sectional observational study included 200 patients-100 healthy and 100 with diabetes without a visible foot ulcer. Initial data were gathered through a questionnaire. Participants were prepared for thermal imaging to capture plantar thermal patterns. All collected data, including thermal images and questionnaire responses, were stored on a password-protected computer to ensure confidentiality and data integrity.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;In this study, participants were categorized into 2 groups: a healthy control group (n=98) with no prior diabetes or peripheral artery disease diagnosis and normal circulatory findings, and a group with diabetes (n=98) comprising patients with diabetes, regardless of peripheral circulatory status. Temperature analysis indicated a wider range in the group with diabetes (18.1-35.6 °C) than in the healthy controls (21.1-35.7 °C), with the former showing significantly higher mean temperatures (mean 29.0 °C, SD 3.0 °C) than controls (mean 28.9 °C, SD 2.8 °C; P&lt;.001). Analysis of both feet revealed significantly greater differences between feet in the group with diabetes and the controls (control: mean 0.47 °C, SD 0.43 °C; group with diabetes: mean 1.78 °C, SD 1.58 °C; P&lt;.001; 95% CI 0.99-1.63). These results identified clinically relevant abnormalities in 10% of the cohort with diabetes, whereas no such findings were observed in the control group. We used a linear regression model to indicate that being diagnosed with diabetes is a significant predictor of abnormal temperature, while age and sex were not found to be significant predictors in this model.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;DFUs pose a significant health risk for patients with diabetes, making early detection crucial. This study highlights the potential of an artificial intelligence-powered computer vision system in identifying early signs of diabetic foot complications by differentiating thermal patterns between patients with diabetes with no visible ulcers and healthy individuals. The findings suggest that the technology could improve early diagnosis and ","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"10 ","pages":"e65209"},"PeriodicalIF":0.0,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12180681/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144289744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Culturally Tailored Physical Activity Intervention for Hispanic Adults Living With Type 2 Diabetes: Pre-Post Pilot Feasibility Study.","authors":"Julio Loya, David O Garcia, Adriana Maldonado, Edgar Villavicencio","doi":"10.2196/62876","DOIUrl":"10.2196/62876","url":null,"abstract":"<p><strong>Background: </strong>Type 2 diabetes mellitus (T2DM) is a metabolic disease that affects over 38 million adults in the United States, who are disproportionately Hispanic.</p><p><strong>Objective: </strong>This study describes the development and implementation of Salud Paso por Paso, a culturally tailored and linguistically appropriate intervention to increase engagement in physical activity (PA) for Hispanic adults living with T2DM.</p><p><strong>Methods: </strong>Participants were enrolled in a 6-week pre-post pilot test of a culturally tailored intervention that included sessions covering different aspects of PA and T2DM. Participants were recruited at a local free clinic. Nonparametric paired-sample Wilcoxon signed-rank tests were used to examine differences between pre- and postintervention measures.</p><p><strong>Results: </strong>Twenty-one participants were recruited, and 19 (90.5%) completed the intervention. Participants significantly increased average hours spent in moderate PA, by 3.16 hours (from 4.73, SD 3.79 minutes to 9.63, SD 6.39 minutes; Z=-3.52; P<.001), average steps per week (from 23,006.38, SD 14,357.13 steps to 43,000.81, SD 30,237.17 steps; Z=-2.79; P=.005), and minutes per week of PA (from 105.94, SD 72.23 minutes to 224.19, SD 167.85 minutes; Z=-3.36; P<.001).</p><p><strong>Conclusions: </strong>Developing effective culturally tailored interventions that can ameliorate the deleterious effects of T2DM in Hispanic adults is an important strategy to promote health equity. The Salud Paso por Paso intervention is an effective way to promote PA in Hispanic adults living with T2DM.</p>","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"10 ","pages":"e62876"},"PeriodicalIF":0.0,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12173091/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144267882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating Digital Health Solutions in Diabetes and the Role of Patient-Reported Outcomes: Targeted Literature Review.","authors":"Paco Cerletti, Michael Joubert, Nick Oliver, Saira Ghafur, Pasquale Varriale, Ophélie Wilczynski, Marlene Gyldmark","doi":"10.2196/52909","DOIUrl":"10.2196/52909","url":null,"abstract":"<p><strong>Background: </strong>Digital health solutions (DHS) are technologies with the potential to improve patient outcomes as well as change the way care is delivered. The value of DHS for people with diabetes is not well understood, nor is it clear how to quantify this value.</p><p><strong>Objective: </strong>We aimed to summarize current literature on the use of patient-reported outcome measures (PROMs) in diabetes as well as in selected guidelines for Health Technology Assessment (HTA) of DHS to highlight gaps, needs, and opportunities for the use of PROMs to evaluate DHS.</p><p><strong>Methods: </strong>We searched PubMed and ClinicalTrials.gov to establish which PROMs were most used in diabetes clinical trials and research between 1995 and May 2024. HTA guidelines on DHS evaluation from France, Germany, and the United Kingdom were also assessed to identify PROMs for DHS evaluation in general.</p><p><strong>Results: </strong>A total of 46 diabetes-specific PROMs and 16 nondiabetes-specific PROMs were identified. The most used diabetes-specific PROMs were (1) Diabetes Distress Scale, (2) Problem Areas in Diabetes, (3) Diabetes Empowerment Scale, (4) Diabetes Quality of Life, and (5) Diabetes Treatment Satisfaction Questionnaire. The most used nondiabetes-specific PROMs were Beck Depression Inventory, Sickness Impact Profile, EuroQol 5-Dimension, and Short Form 36-Item Health Survey. In HTA guidelines, the most prominent domain was health-related quality of life, for whose assessment there are well-established measures (Short Form 36-Item Health Survey and EuroQol 5-Dimension).</p><p><strong>Conclusions: </strong>Of the many PROMs used in diabetes care, few are currently used to evaluate DHS, and certain domains of value in diabetes are not mentioned in HTA guidelines. A common, comprehensive DHS-specific HTA framework could facilitate and accelerate the evaluation of DHS.</p>","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"10 ","pages":"e52909"},"PeriodicalIF":0.0,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12158397/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144227592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correlation Between Technology and Improved Outcomes in Youth With Type 1 Diabetes Mellitus: Prospective Study Examining Outcomes for Patients With Depression and Those With Public Insurance.","authors":"Natacha D Emerson, Christopher Ferber, Nicholas J Jackson, Joshua Li, Eric Tsay, Dennis Styne, Michael Gottschalk, Steven D Mittelman, Anna-Barbara Moscicki","doi":"10.2196/70380","DOIUrl":"10.2196/70380","url":null,"abstract":"<p><strong>Background: </strong>Adherence to type 1 diabetes mellitus (T1DM) treatment regimens decreases during adolescence. While comorbid depression and health insurance disparities are individually known to potentiate this risk, technological devices for T1DM appear to be protective.</p><p><strong>Objective: </strong>We examined whether technology use impacted the association between depression and poorer health outcomes in T1DM. Given established insurance-based disparities based on technology access, we also studied whether the protective effects of T1DM technology differed among publicly and privately insured youth.</p><p><strong>Methods: </strong>Data were prospectively collected from pediatric patients with T1DM across 3 California medical centers. We used linear and negative binomial regression analyses to examine whether technology use was related to diabetes outcomes and whether this differed based on depression status (technology-by-depression interaction) and health insurance type (technology-by-insurance interaction).</p><p><strong>Results: </strong>Across 1573 patients aged 12 to 25 years (mean age 15.9, SD 2.9 years; n=1050, 66.4%, non-Hispanic White; n=745, 47.0% female), those with a depression diagnosis had higher hemoglobin A1c (HbA1c; mean 9.1%, SD 2.1% vs 10.1%, SD 2.2%) and more frequent diabetic ketoacidosis (DKA) events per year (mean 0.10, SD 0.36 vs 0.24, SD 0.66) than those without (P=.003). Patients using both a continuous glucose monitor (CGM) and pump had lower HbA1c levels and fewer DKA events per year (mean HbA1c 8.2%, SE 0.1%; mean DKA events per year 0.05, SE 0.01) than those using one device (mean HbA1c 9.0%, SE 0.1%; mean DKA events 0.08, SE 0.1%) or none (mean HbA1c 10.0%, SE 0.1%; mean DKA events 0.19, SE 0.1%; P<.001). While youth with public insurance had significantly higher HbA1c levels than those with commercial insurance (mean 9.3%, SD 2.1% vs 9.0%, SD 2.0%, P<.001), those using a CGM had no reliable decrease in HbA1c compared to their commercially insured peers (P=.35).</p><p><strong>Conclusions: </strong>Technology use in pediatric T1DM appears protective for both youth with a history of depression and those who are publicly insured. These data underscore the importance of universal access to technology to mitigate disparities based on comorbid mental health issues and differential access to care.</p>","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"10 ","pages":"e70380"},"PeriodicalIF":0.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12151526/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144217492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimating the Risk of Lower Extremity Complications in Adults Newly Diagnosed With Diabetic Polyneuropathy: Retrospective Cohort Study.","authors":"Alyce S Adams, Catherine Lee, Gabriel Escobar, Elizabeth A Bayliss, Brian Callaghan, Michael Horberg, Julie A Schmittdiel, Connie Trinacty, Lisa K Gilliam, Eileen Kim, Nima S Hejazi, Lin Ma, Romain Neugebauer","doi":"10.2196/60141","DOIUrl":"10.2196/60141","url":null,"abstract":"<p><strong>Background: </strong>Diabetes-related lower extremity complications, such as foot ulceration and amputation, are on the rise, currently affecting nearly 131 million people worldwide. Methods for early detection of individuals at high risk remain elusive. While data-driven diabetic polyneuropathy algorithms exist, high-performing, clinically useful tools to assess risk are needed to improve clinical care.</p><p><strong>Objective: </strong>This study aimed to develop an electronic medical record-based machine learning algorithm that would predict lower extremity complications.</p><p><strong>Methods: </strong>We conducted a retrospective longitudinal cohort study to predict the risk of lower extremity complications within 24 months of an initial diagnosis of diabetic polyneuropathy. From an initial cohort of 468,162 individuals with at least 1 diagnosis of diabetic polyneuropathy at one of 2 multispecialty health care systems (based in northern California and Colorado) between April 2012 and December 2016, we created an analytic cohort of 48,209 adults with continuous enrollment, who were newly diagnosed with no evidence of end-of-life care. The outcome was any lower extremity complication, including foot ulceration, osteomyelitis, gangrene, or lower extremity amputation. We randomly split the data into training (38,569/48209; 80%) and testing (9,640/48209; 20%) datasets. In the training dataset, we used super Learner (SL), an ensemble learning method that employs cross-validation and combines multiple candidate risk predictors, into a single risk predictor. We evaluated the performance of the SL risk predictor in the testing dataset using the receiver operating characteristic curve and a calibration plot.</p><p><strong>Results: </strong>Of the 48,209 individuals in the cohort, 2327 developed a lower extremity complication during follow-up. The SL risk estimator exhibited good discrimination (AUC=0.845, 95% CI 0.826-0.863) and calibration. A modified version of our SL algorithm, simplified to facilitate real-world adoption, had only slightly reduced discrimination (AUC=0.817, 95%CI 0.797-0.837). The modified version slightly outperformed the naïve logistic regression model (AUC=0.804, 95% CI 0.783-0.825) in terms of precision gained relative to the frequency of alerts and number of patients that needed to be evaluated.</p><p><strong>Conclusions: </strong>We have built a machine learning-based risk estimator with the potential to improve clinical detection of diabetic patients at high risk for lower extremity complications at the time of an initial diabetic polyneuropathy diagnosis. The algorithm exhibited good discriminant validity and calibration using only data from the electronic medical record. Additional research will be needed to identify optimal contexts and strategies for maximizing algorithmic fairness in both interpretation and deployment.</p>","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"10 ","pages":"e60141"},"PeriodicalIF":0.0,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12140504/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144183103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Exergames Program for Adolescents With Type 1 Diabetes: Qualitative Study of Acceptability.","authors":"Selene S Mak, Laura M Nally, Juanita Montoya, Rebecca Marrero, Melissa DeJonckheere, Kevin L Joiner, Soohyun Nam, Garrett I Ash","doi":"10.2196/65665","DOIUrl":"10.2196/65665","url":null,"abstract":"<p><strong>Background: </strong>Numerous barriers to moderate to vigorous physical activity exist for youths with type 1 diabetes (T1D). The virtual exercise games for youth with T1D (ExerT1D) intervention implement synchronous support of moderate to vigorous physical activity including T1D peers and role models.</p><p><strong>Objective: </strong>This study aims to understand the acceptability of this intervention to participants.</p><p><strong>Methods: </strong>We conducted postprogram, semistructured, televideo interviews with participating youths to elicit perspectives on the acceptability of the intervention and experience with the program. Two coders independently reviewed and analyzed each transcript using a coding scheme developed inductively by senior researchers. Discrepancies were resolved by team discussion, and multiple codes were grouped together to produce 4 main thematic areas.</p><p><strong>Results: </strong>All 15 participants provided interviews (aged 14-19 years; 2 nonbinary, 6 females; median hemoglobin A_1c level of 7.8% (IQR 7.4%-11.2%), 5 with a hemoglobin A_1c level of ≥10%). Qualitative data revealed four themes: (1) motivation to engage in physical activity (PA)-improving their physical capabilities and stabilizing glucose levels were cited as motivation for PA and challenges of living with T1D were cited as PA barriers; (2) experience with and motivation to manage diabetes while engaging in PA-participants provided details of accommodating the inherent uncertainty or limitations of PA with diabetes and sometimes preparing for PA involved psychological and motivational adjustments while some relayed feelings of avoidance; (3) peer support encouraged engagement with the intervention-participants appreciated the peer aspects of components of ExerT1D and participants' reflections of the facilitated group experience highlight many benefits of a small-group virtual program; and (4) improvements in PA and diabetes self-management efficacy-all participants credited the program with improving or at least raising awareness of T1D management skills.</p><p><strong>Conclusions: </strong>Our virtual PA intervention using an active video game and discussion component provided adolescents with T1D the confidence and peer support to engage in PA, improved awareness of diabetes-specific tasks to prepare for exercise, and improved understanding of the effect of PA on glucose levels. Engaging youths with a virtual video game intervention is a viable approach to overcome barriers to PA for adolescents with T1D.</p><p><strong>Trial registration: </strong>ClinicalTrials.gov NCT05163912; https://clinicaltrials.gov/ct2/show/NCT05163912.</p>","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":" ","pages":"e65665"},"PeriodicalIF":0.0,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12159555/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144058247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}