Journal of Diabetes Science and Technology最新文献

{"title":"Using One-Shot Prompting of Non-Fine-Tuned Commercial Artificial Intelligence to Assess Nutrients from Photographs of Japanese Meals.","authors":"Yuexiang Ji, Kayo Waki, Toshimasa Yamauchi, Masaomi Nangaku, Kazuhiko Ohe","doi":"10.1177/19322968241309889","DOIUrl":"10.1177/19322968241309889","url":null,"abstract":"<p><strong>Background: </strong>Diet interventions often have poor adherence due to burdensome food logging. Approaches using photographs assessed by artificial intelligence (AI) may make food logging easier, if they are adequately accurate.</p><p><strong>Method: </strong>We used OpenAI's GPT-4o model with one-shot prompts and no fine-tuning to assess energy, fat, protein, carbohydrate, fiber, and salt through photographs of 22 meals, comparing assessments to weighed food records for each meal and to assessments of dieticians.</p><p><strong>Results: </strong>The model had poor performance overall. For fiber, though, the model achieved an intraclass correlation coefficient of 0.71 (0.67-0.74 95% CI), well above the dietician performance of 0.57.</p><p><strong>Conclusions: </strong>The simplest use of current AI via one-shot prompting and no fine-tuning accurately assesses fiber content in meals but is inaccurate for other nutritional parameters.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968241309889"},"PeriodicalIF":4.1,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11724398/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142949744","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":"Advancing Monogenic Diabetes Research and Clinical Care by Creating a Data Commons: The Precision Diabetes Consortium (PREDICT).","authors":"Michael E McCullough, Lisa R Letourneau-Freiberg, Rochelle N Naylor, Siri Atma W Greeley, David T Broome, Mustafa Tosur, Raymond J Kreienkamp, Erin Cobry, Neda Rasouli, Toni I Pollin, Miriam S Udler, Liana K Billings, Cyrus Desouza, Carmella Evans-Molina, Suzi Birz, Brian Furner, Michael Watkins, Kaitlyn Ott, Samuel L Volchenboum, Louis H Philipson","doi":"10.1177/19322968241310896","DOIUrl":"10.1177/19322968241310896","url":null,"abstract":"<p><p>Monogenic diabetes mellitus (MDM) is a group of relatively rare disorders caused by pathogenic variants in key genes that result in hyperglycemia. Lack of identified cases, along with absent data standards, and limited collaboration across institutions have hindered research progress. To address this, the UChicago Monogenic Diabetes Registry (UCMDMR) and UChicago Data for the Common Good (D4CG) created a national consortium of MDM research institutions called the PREcision DIabetes ConsorTium (PREDICT). Following the D4CG model, PREDICT has successfully established a multicenter MDM data commons. PREDICT has created a consensus data dictionary that will be utilized to address critical gaps in understanding of these rare types of diabetes. This approach may be useful for other rare conditions that would benefit from access to harmonized pooled data.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968241310896"},"PeriodicalIF":4.1,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11713946/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142949717","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":"Open Ecosystem Through Secure Plug and Play Interoperability: An Overview.","authors":"Christoph Fischer","doi":"10.1177/19322968241310253","DOIUrl":"https://doi.org/10.1177/19322968241310253","url":null,"abstract":"<p><strong>Background: </strong>Interoperability is a critical enabler for integrated Personalized Diabetes Management (iPDM), automated insulin delivery (AID), and the digital transformation of healthcare in general. However, manufacturers still create closed ecosystems (ie, solutions designed to work end-to-end minimizing collaboration with other organizations) with proprietary interfaces because of various interoperability challenges. Therefore, the aim of this article is to provide an overview of how to achieve organizational interoperability in an open ecosystem (ie, solutions designed to integrate different organizations via interoperability standards) for diabetes management.</p><p><strong>Methods: </strong>The proposed interoperability design approach called Secure Plug and Play Interoperability (SPPI) supports building and using interoperable system elements in an open ecosystem. Secure Plug and Play Interoperability enables interoperability over the entire system life cycle with its reference architecture, secure interoperability standards, and organizational capabilities. These standards were developed with participation from healthcare providers, regulatory authorities, payers, academia, and manufacturers. Publicly available information provides examples of implementation support and practical usage.</p><p><strong>Results: </strong>Organizational interoperability in an open ecosystem can be achieved through organizational capabilities and a selection of secure interoperability standards. ISO/IEEE 11073, Bluetooth profiles, and HL7 FHIR with test specifications, test tools, software development kits, and quality assurance programs represent a coordinated selection suitable for building an open ecosystem. Practical usage is demonstrated with real-world solutions that build on these standards.</p><p><strong>Conclusions: </strong>Secure Plug and Play Interoperability facilitates the end-to-end integration of devices, digital products, and services from partners in an open ecosystem. Moreover, even a single manufacturer, who provides all system elements of a solution, can use and benefit from SPPI.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968241310253"},"PeriodicalIF":4.1,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11707763/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142949741","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":"Glycemia Risk Index is Associated With Risk of Albuminuria Among Individuals With Type 1 Diabetes.","authors":"Ji Yoon Kim, Jee Hee Yoo, Nam Hoon Kim, Jae Hyeon Kim","doi":"10.1177/19322968241310850","DOIUrl":"https://doi.org/10.1177/19322968241310850","url":null,"abstract":"<p><strong>Background: </strong>The glycemia risk index (GRI) is a novel composite continuous glucose monitoring (CGM) metric composed of hypoglycemia and hyperglycemia components and is weighted toward extremes. This study aimed to investigate the association between GRI and the risk of albuminuria in type 1 diabetes.</p><p><strong>Methods: </strong>The 90-day CGM tracings of 330 individuals with type 1 diabetes were included in the analysis. Glycemia risk index was divided into five risk zones (A-E), and hypoglycemia and hyperglycemia components were divided into quintiles. Albuminuria was defined as a spot urine albumin-to-creatinine ratio ≥30 mg/g. Associations of albuminuria with GRI and its hypoglycemia and hyperglycemia components were estimated.</p><p><strong>Results: </strong>Mean GRI and glycated hemoglobin (HbA1c) were 40.9 ± 21.3 and 7.3 ± 1.0%, respectively, and the overall prevalence of albuminuria was 17.6%. Prevalence of albuminuria differed significantly by GRI zone (<i>P</i> = .023). In logistic regression analysis, the adjusted odds ratio (OR) of albuminuria per increase in the GRI zone was 1.70 (95% confidence interval [CI]: 1.19-2.41) after adjusting for various factors affecting albuminuria. The association remained significant after adjusting for achievement of the recommended target of time in range (70-180 mg/dL; >70%) or HbA1c (<7%). The hyperglycemia component of GRI was also associated with albuminuria, and the association remained significant even after adjusting for HbA1c level itself (adjusted OR 1.44, 95% CI: 1.05-1.98).</p><p><strong>Conclusions: </strong>Glycemia risk index is significantly associated with albuminuria in individuals with type 1 diabetes.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968241310850"},"PeriodicalIF":4.1,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11707761/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142949737","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":"Different Times for Different Metrics: Predicting 90 Days of Intermittently Scanned Continuous Glucose Monitoring Data in Subjects With Type 1 Diabetes on Multiple Daily Injection Therapy. Findings From a Multicentric Real-World Study.","authors":"Alessandro Csermely, Nicolò D Borella, Anna Turazzini, Martina Pilati, Sara S Sheiban, Riccardo C Bonadonna, Roberto Trevisan, Maddalena Trombetta, Giuseppe Lepore","doi":"10.1177/19322968241308564","DOIUrl":"https://doi.org/10.1177/19322968241308564","url":null,"abstract":"<p><strong>Aims: </strong>According to the 2023 International Consensus, glucose metrics derived from two-week-long continuous glucose monitoring (CGM) can be extrapolated up to 90 days before. However, no studies have focused on adults with type 1 diabetes (T1D) on multiple daily injections (MDIs) and with second-generation intermittently scanned CGM (isCGM) sensors in a real-world setting.</p><p><strong>Methods: </strong>This real-world, retrospective study included 539 90-day isCGM data from 367 adults with T1D on MDI therapy. For each sensor metric, the coefficients of determination (<i>R</i>²) were computed for sampling periods from 2 to 12 weeks versus the whole 90-day interval. Correlations were considered strong for <i>R</i>² ≥0.88.</p><p><strong>Results: </strong>The two-week sampling period displayed strong correlations for time in range (TIR, 70-180 mg/dl; <i>R</i>² = 0.89) and above range (TAR, >180 mg/dl; <i>R</i>² = 0.88). The four-week sampling period showed additional strong correlations for time in tight range (TITR, 70-140 mg/dl; <i>R</i>² = 0.92), for the coefficient of variation (CV; <i>R</i>² = 0.88), and for the glycemia risk index (GRI; <i>R</i>² = 0.92). The six-week sampling period displayed an additional strong correlation for time below range (TBR, <70 mg/dl; <i>R</i>² = 0.90). After stratification by clinical variables, lower <i>R</i>² values were found for older age quartiles (>40 years), higher CV (>36%), lower sensor use (≤94%), and higher HbA1c (>7.5%).</p><p><strong>Conclusion: </strong>In patients with T1D on MDI, two- to six-week intervals of isCGM use can provide clinically useful estimates of TIR, TAR, TITR, TBR, CV, and GRI, which can be extrapolated to longer (up to 90 days) time intervals. Longer intervals might be needed in case of older age, higher glucose variability, lower sensor use, and higher HbA1c.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968241308564"},"PeriodicalIF":4.1,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11705298/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142949722","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":"Improved Glycemic Control in Insulin-Treated Individuals With Poorly Controlled Type 2 Diabetes Through Combined Structured Education With Real-Time Continuous Glucose Monitoring.","authors":"Jee Hee Yoo, Ji Eun Jun, Soo Heon Kwak, Jae Hyeon Kim","doi":"10.1177/19322968241306136","DOIUrl":"10.1177/19322968241306136","url":null,"abstract":"<p><strong>Background: </strong>We evaluated the efficacy of structured individualized education combined with real-time continuous glucose monitoring (rt-CGM, Dexcom G6) in improving glycemic outcomes in insulin-treated adults with poorly controlled type 2 diabetes (T2D).</p><p><strong>Methods: </strong>This multicenter, 16-week, single-arm study included 66 adults with T2D (multiple daily insulin [MDI]: 33; basal insulin: 33) with a ≥7.8%. Each cohort comprised 15 participants aged ≥60 years. The participants attended four educational sessions. The primary outcome was a change in glycated hemoglobin (HbA_1c) levels between baseline and week 16.</p><p><strong>Results: </strong>Sixty-four individuals were included in this study, with a mean age of 58.3 ± 12.4 years. The mean HbA_1c levels decreased from 9.0% at baseline to 7.1% at 16 weeks in the MDI group (difference: -1.8%, 95% confidence interval [CI] = -2.3 to -1.3) and from 8.8% to 7.0% in the basal insulin group (difference: -1.8%, 95% CI = -2.1 to -1.4). In the total population, the mean time in range 70 to 180 mg/dL increased by 25.2% (6 hours 4 minutes, 95% CI = 20.6 to 29.8), whereas the time in tight range 70 to 140 mg/dL increased by 17.3% (4 hours 10 minutes, 95% CI = 14.0 to 20.7). Both groups maintained a target of <1% of the time below the range of <54 mg/dL. Improvements in HbA_1c and CGM metrics were comparable between individuals aged ≥60 years and those aged <60 years (all <i>P</i>-values for interaction >.1).</p><p><strong>Conclusions: </strong>In adults with poorly controlled insulin-treated T2D, rt-CGM use with structured education significantly improved the HbA_1c and CGM metrics, primarily by reducing hyperglycemia, regardless of age.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968241306136"},"PeriodicalIF":4.1,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11699545/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142927220","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 Cross-sectional Relationship Between Use of Automatic Insulin Delivery Systems and Eating Styles Among Older Adults With Type 1 Diabetes: An Exploratory Analysis.","authors":"Anna R Kahkoska, Jessica Sprinkles, Nikhita Gopisetty, Gabriella Ercolino, Angela Fruik, Rashmi Muthukkumar, Xiaorui Qu, Elizabeth J Mayer-Davis, Angelica Cristello Sarteau","doi":"10.1177/19322968241296842","DOIUrl":"10.1177/19322968241296842","url":null,"abstract":"<p><strong>Background: </strong>The number of older adults with type 1 diabetes (T1D) is increasing. Use of automated insulin delivery (AID) may influence nutrition and eating behaviors. We explored how three eating styles (restrained, external, emotional) differ between older adults with T1D who use and do not use AID.</p><p><strong>Methods: </strong>We administered a one-time electronic survey from September to November 2023 to adults ≥65 years with T1D receiving care through a university-affiliated hospital system. Clinical and demographic information was collected from medical records. Eating styles were characterized with the Dutch Eating Behavior Questionnaire.</p><p><strong>Results: </strong>Our sample (<i>n</i> = 77, 95% non-Hispanic white) had mean (SD) age: 71.8 (4.1) years, diabetes duration: 33 (18) years, hemoglobin A1c (HbA1c): 6.83 (1.12%), and body mass index (BMI): 27.3 (4.7) kg/m². Respondents reported variable eating styles, with the highest median scores for external and restrained eating and lower scores for emotional eating. Older adults using AID systems had higher median scores for emotional and external eating, and more varied restrained eating scores compared to those not using AID systems. Weak correlations were found between eating styles and HbA1c (restrained: <i>r</i> = -0.14; external: <i>r</i> = 0.08; emotional: <i>r</i> = 0.15), as well as between restrained (<i>r</i> = 0.09) and external (<i>r</i> = 0.04) eating with BMI, with a small correlation between emotional eating and BMI (<i>r</i> = 0.27).</p><p><strong>Conclusions: </strong>Eating styles may vary between older adult AID users and non-users. To our knowledge, this is the first study to characterize eating styles in this population, though generalizability is limited by a non-diverse and small sample with high technology use overall (eg, continuous glucose monitoring, insulin pumps).</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"5-10"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11571612/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142621230","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":"Comparative System Accuracy of Blood Glucose Monitoring Systems-Advocacy for a New Accuracy Assessment Metric.","authors":"Matthes Kenning, Anselm Puchert, Eckhard Salzsieder","doi":"10.1177/19322968241289958","DOIUrl":"10.1177/19322968241289958","url":null,"abstract":"","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"270-271"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11571641/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142466690","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 Observational Crossover Study of People Using Real-Time Continuous Glucose Monitors Versus Self-Monitoring of Blood Glucose: Real-World Evidence Using Electronic Medical Record Data From More Than 12,000 People With Type 1 Diabetes.","authors":"Nudrat Noor, Gregory Norman, Rona Sonabend, Lily Chao, Manmohan Kamboj, Lauren Golden, M Tracy Bekx, Susan Hseih, Carol Levy, Janine Sanchez, Robert Rapaport, Osagie Ebekozien","doi":"10.1177/19322968231178017","DOIUrl":"10.1177/19322968231178017","url":null,"abstract":"<p><strong>Background: </strong>We used real-world electronic health record (EHR) data to examine HbA1c levels among children and adults with type 1 diabetes (T1D) who are classified as continuous glucose monitor (CGM) users after T1D diagnosis and switch to self-monitoring of blood glucose (SMBG) during follow-up, versus people who opt for SMBG after T1D diagnosis and switch to CGM during follow-up visits.</p><p><strong>Methods: </strong>We conducted an observational, case-crossover study using electronic medical record (EMR) data from the T1D Exchange Quality Improvement Collaborative. The primary outcome in this study was HbA1c. Baseline HbA1c levels were taken at the index date, corresponding to initial device classification, and compared with HbA1c value recorded at the clinic visit following device switch.</p><p><strong>Results: </strong>Of all patients classified in the SMBG group, 7,706 switched to CGM use within the 5-year study time frame, and 5,123 of all initial CGM users switched to SMBG within the study time frame and were included in this analysis. At baseline, median (interquartile range [IQR]) HbA1c for SMBG use was 8.1 (2.4), whereas postcrossover to CGM use, there was a decline in median (IQR) levels to 7.7 (1.9) (<i>P</i> < .001). For baseline CGM users, median (IQR) HbA1c levels were 7.9 (2.0), and postcrossover to SMBG, median (IQR) HbA1c levels increased to 8.0 (2.9) (<i>P</i> < .001).</p><p><strong>Conclusion: </strong>We found that people who switched to CGM use had significantly improved HbA1c levels compared to those who switched to glucose monitoring with SMBG.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"63-71"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11688696/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9560287","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":"Delivering Biopsychosocial Health Care Within Routine Care: Spotlight-AQ Pivotal Multicenter Randomized Controlled Trial Results.","authors":"Ryan Charles Kelly, Hermione Price, Peter Phiri, Michael Cummings, Amar Ali, Mayank Patel, Ethan Barnard, Yufan Liu, Oscar Mendez, Katharine Barnard-Kelly","doi":"10.1177/19322968231183436","DOIUrl":"10.1177/19322968231183436","url":null,"abstract":"<p><strong>Background: </strong>Annual national diabetes audit data consistently shows most people with diabetes do not consistently achieve blood glucose targets for optimal health, despite the large range of treatment options available.</p><p><strong>Aim: </strong>To explore the efficacy of a novel clinical intervention to address physical and mental health needs within routine diabetes consultations across health care settings.</p><p><strong>Methods: </strong>A multicenter, parallel group, individually randomized trial comparing consultation duration in adults diagnosed with T1D or T2D for ≥6 months using the Spotlight-AQ platform versus usual care. Secondary outcomes were HbA1c, depression, diabetes distress, anxiety, functional health status, and healthcare professional burnout. Machine learning models were utilized to analyze the data collected from the Spotlight-AQ platform to validate the reliability of question-concern association; as well as to identify key features that distinguish people with type 1 and type 2 diabetes, as well as important features that distinguish different levels of HbA1c.</p><p><strong>Results: </strong><i>n</i> = 98 adults with T1D or T2D; any HbA1c and receiving any diabetes treatment participated (<i>n =</i> 49 intervention). Consultation duration for intervention participants was reduced in intervention consultations by 0.5 to 4.1 minutes (3%-14%) versus no change in the control group (-0.9 to +1.28 minutes). HbA1c improved in the intervention group by 6 mmol/mol (range 0-30) versus control group 3 mmol/mol (range 0-8). Moderate improvements in psychosocial outcomes were seen in the intervention group for functional health status; reduced anxiety, depression, and diabetes distress and improved well-being. None were statistically significant. HCPs reported improved communication and greater focus on patient priorities in consultations. Artificial Intelligence examination highlighted therapy and psychological burden were most important in predicting HbA1c levels. The Natural Language Processing semantic analysis confirmed the mapping relationship between questions and their corresponding concerns. Machine learning model revealed type 1 and type 2 patients have different concerns regarding psychological burden and knowledge. Moreover, the machine learning model emphasized that individuals with varying levels of HbA1c exhibit diverse levels of psychological burden and therapy-related concerns.</p><p><strong>Conclusion: </strong>Spotlight-AQ was associated with shorter, more useful consultations; with improved HbA1c and moderate benefits on psychosocial outcomes. Results reflect the importance of a biopsychosocial approach to routine care visits. Spotlight-AQ is viable across health care settings for improved outcomes.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"91-97"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11688703/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9668277","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}