Journal of Diabetes Science and Technology最新文献

{"title":"Use of the Glycemia Risk Index at Hybrid Closed-Loop Initiation to Predict Combined International Glucose Targets at 12 Months: Results From the CIRDIA Study Group.","authors":"Sylvie Picard, Joëlle Dupont, Fabienne Amiot-Chapoutot, Blandine Courbebaisse, Estelle Personeni, Emmanuelle Lecornet-Sokol, François Mougel, Clara Bouché, Françoise Giroud, Sandrine Lablanche, Sophie Borot","doi":"10.1177/19322968251380291","DOIUrl":"https://doi.org/10.1177/19322968251380291","url":null,"abstract":"<p><strong>Background: </strong>Hybrid closed-loop (HCL) therapy helps reaching efficacy and safety glucose targets (ESGT+) in persons with type 1 diabetes (PwT1D). We analyzed here the glycemia risk index (GRI) in PwT1D at HCL initiation (M₀) and at 12 months (M₁₂) and determined whether M₀GRI value and/or M₀GRI zone (A-B-C-D-E) could identify people reaching M₁₂ESGT+.</p><p><strong>Methods: </strong>This was a retrospective study. Consecutive PwT1D who started HCL in a CIRDIA center were included after written consent. Glucose parameters were manually extracted from platforms at M₀ and M₁₂. ESGT+ meant reaching time in range (TIR) > 70% and glucose management indicator < 7% and time below range (TBR)^<70 < 4% and TBR^<54< 1%. Glycemia risk index was calculated and receiver-operating characteristic (ROC) analyses were performed to study the relation between M₀GRI and M₁₂ESGT+/M₁₂ESGT-.</p><p><strong>Results: </strong>M₁₂ data were available for 128 PwT1D. M₀GRI predicted M₁₂ESGT mostly for low and high M₀GRI values. An M₀GRI < 41 had a 90% specificity, a 36% sensitivity, and a 74% positive predictive value for M₁₂ESGT+. Sensitivity increased to 80% but specificity dropped to 56% for M₀GRI < 61 and M₀GRI ≥ 61 had a 78% negative predictive value. All PwT1D with M₀GRI 0 to 20 (zone A) reached M₁₂ESGT+. Then, the percentage of M₁₂ESGT+ people dropped about 25% per M₀GRI zone (A-B-C-D) and to 11% for zone E.</p><p><strong>Conclusions: </strong>M₀GRI was significantly associated with M₁₂ESGT status but mostly when in zones A-B or D-E. Hybrid closed-loop training should focus on PwT1D with M₀GRI ≥ 41 (90% of M₁₂ESGT- persons), but reaching M₁₂ESGT+ is possible with M₀GRI in zones C-D-E (64% of M₁₂ESGT+ persons) and even D-E (20% of M₁₂ESGT+ persons).</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968251380291"},"PeriodicalIF":3.7,"publicationDate":"2025-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145228609","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":"Diabetes Technology in Saudi Arabia: Current Status and Future Directions.","authors":"Mohammed E Al-Sofiani, Abdulhalim M Al-Murashi, Nada A Al-Agil, Azzam O Al-Othman, Shahad Y Al-Faris, Ahmed M Al-Enzi","doi":"10.1177/19322968251370756","DOIUrl":"10.1177/19322968251370756","url":null,"abstract":"<p><strong>Background: </strong>The increasing incidence and prevalence of diabetes have led to a strain on health care systems, necessitating innovation in diabetes care delivery and substantial resource allocation for disease management and treatment of complications. Recently, Saudi Arabia has made significant strides in digital transformation, implementing cutting-edge technologies across various sectors, including the health sector.</p><p><strong>Aims: </strong>To develop a report that examines the current status, identify challenges and opportunities in implementing diabetes technology solutions for diabetes management, and provide a strategic roadmap for enhancing the accessibility to diabetes technology solutions.</p><p><strong>Methods: </strong>The Saudi National Diabetes Center (SNDC) convened a group of experts to develop a comprehensive report that serves a dual purpose. First, it provides a narrative review on insulin pumps and CGMs that are approved by the SFDA and discusses their clinical effectiveness based on local studies. Second, it presents a comprehensive report on the current status and future directions of diabetes technology in Saudi Arabia.</p><p><strong>Results: </strong>Our experts identified six major barriers to the adoption of diabetes technology solutions in Saudi Arabia and proposed 14 strategic initiatives that can help overcome these barriers and transform the current overwhelmed diabetes care model into a more innovative, effective, efficient, safe, accessible, and cost-effective model of care.</p><p><strong>Conclusion: </strong>While Saudi Arabia offers one of the most diverse ranges of diabetes technology solutions globally, major accessibility barriers persist. The SNDC Diabetes Technology Report is the first report developed primarily for policymakers, regulatory bodies, clinicians, academicians, and industry partners to address these accessibility barriers.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968251370756"},"PeriodicalIF":3.7,"publicationDate":"2025-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12477185/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145182139","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":"Virtual Reality for Balance in Individuals With Diabetes: A Systematic Review of Assessment and Intervention Strategies.","authors":"Kai Cheng, Fatimah Alkhameys, Hannes Devos, Patricia Kluding, John Miles, Chun-Kai Huang","doi":"10.1177/19322968251375370","DOIUrl":"10.1177/19322968251375370","url":null,"abstract":"<p><strong>Background: </strong>Diabetes mellitus (DM) and its complications have wide-ranging effects on numerous aspects of health, particularly as they affect individual's static and dynamic balance. Balance assessments and interventions have emerged as key components of rehabilitation strategies for individuals with DM. As part of the growing incorporation of virtual reality (VR) technology into rehabilitative, this systematic review aims to synthesize the current evidence on VR-based assessment and interventions for balance in individuals with DM.</p><p><strong>Methods: </strong>A comprehensive search of electronic database including PubMed, Embase, CINAHL, Cochrane, and PEDro was conducted from the inception through April 2024. Studies applying VR technology either as balance assessments or interventions among individuals with DM were made potentially eligible for inclusion.</p><p><strong>Results: </strong>A total of 12 studies were included according to the inclusion criteria, which included 345 individuals with DM. Four studies utilized VR for balance assessment, revealing that individuals with DM exhibited impaired balance compared with healthy controls. Eight studies applied VR tools for balance training. Despite variations in statistical significance, all studies reported enhanced balance after VR interventions.</p><p><strong>Conclusion: </strong>This systematic review summarizes VR as an innovative and interactive approach, demonstrating its applicability and usefulness in both balance assessment and intervention among individuals with DM.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968251375370"},"PeriodicalIF":3.7,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12463877/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145137646","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":"Developing a Simple Non-Laboratory-Based Machine Learning Tool for Prediabetes Screening in a Target Population: A Proof-of-Concept Study.","authors":"Tanja Fredensborg Holm, Thomas Kronborg, Morten Hasselstrøm Jensen, Stine Hangaard","doi":"10.1177/19322968251376380","DOIUrl":"10.1177/19322968251376380","url":null,"abstract":"<p><strong>Background: </strong>Progression from prediabetes to type 2 diabetes (T2D) can be delayed with early detection and intervention. Current detection methods, relying on costly blood glucose tests, limit widespread screening. Machine learning models offer the potential for non-laboratory-based tools. However, existing prediabetes detection models lack validation in their intended target populations. Thus, this study aimed to develop and validate a non-laboratory-based machine learning tool for prediabetes detection in a specific target population.</p><p><strong>Methods: </strong>Based on 501 adults from a prediabetes screening project, a decision tree model was developed. Twelve potential non-laboratory-based features were extracted. The target variable was categorized into prediabetes (hemoglobin A1c [HbA_1c] ≥39 mmol/mol and <48 mmol/mol) and normoglycemia (HbA_1c <39 mmol/mol). The data set was divided into 70% for training and 30% for validation, and forward feature selection was used to identify the most relevant features.</p><p><strong>Results: </strong>Out of 501 participants, 88 were identified with prediabetes. The mean age and body mass index (BMI) were approximately 50 years and 27 in both the training and validation sets. Forward selection identified age and waist circumference as the most important features to include in the model. The model achieved an area under the receiver operating characteristic curve (ROC AUC) of 0.8297 and 0.7961 on the training and validation sets.</p><p><strong>Conclusion: </strong>A machine learning screening tool using age and waist circumference was developed with promising results. Its simplicity, by only requiring two non-laboratory features, allows for easy implementation. However, to verify the model's generalizability and external validity, it needs to be evaluated using additional data.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968251376380"},"PeriodicalIF":3.7,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12460283/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145124875","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":"Use of Continuous Glucose Monitors in Publicly Insured Youth With Type 2 Diabetes: A 12-month Pilot and Feasibility Study.","authors":"Sejal Shah, Molly L Tanenbaum, Alondra Loyola, Nathan Grant L Sala, Himani Darji, Sarah Hanes, Franziska K Bishop, Korey K Hood, David M Maahs","doi":"10.1177/19322968251368366","DOIUrl":"10.1177/19322968251368366","url":null,"abstract":"<p><strong>Background: </strong>Type 2 diabetes (T2D) disproportionately affects youth with public insurance of minority and lower socioeconomic status backgrounds. We aimed to determine feasibility of CGM use in this understudied population.</p><p><strong>Methods: </strong>We enrolled youth <20 years old with T2D, provided or prescribed intermittent scanned CGM, and followed established clinic workflows with six data collection visits over 12-months. CGM use was measured by % wear time per two-week period (>75% wear-time as goal) from downloaded report prior to clinic visit. Exploratory outcomes included: 14-day CGM wear time in range (TIR: % time spent between 70 and 180 mg/dl), HbA1c, and patient-reported outcomes (PROs) collected from youth and parents.</p><p><strong>Results: </strong>We enrolled 30 youth (age 15.1 years [SD 2.48]; HbA1c 10.2%, range: 6.5%-15.5%), 46.7% female, 90% Hispanic. At baseline, 37% previously used CGM and 53% lacked glucometer data. CGM use was 50% at three months and 23% at 12 months. CGM wear time decreased by 6.4 days per two weeks by 12 months. Mean HbA1c was 9.8% at 12 months and median TIR decreased from 71% to 42%. Parents and youth had moderate-to-positive attitudes about diabetes technology. Youth endorsed fair levels of global health; and youth and parents endorsed fair general and diabetes-related health-related quality of life.</p><p><strong>Conclusions: </strong>Strategies for sustained CGM use in youth with T2D may differ from adults with T2D or youth with type 1 diabetes. Additional studies are needed to evaluate facilitators and barriers of sustained CGM use to optimize CGM use in youth with T2D.</p><p><strong>Clinicaltrials: </strong>gov registration:NCT05074667.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968251368366"},"PeriodicalIF":3.7,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12450209/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145091810","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":"Implementing a Continuous Glucose Monitoring Hospital Discharge Program: Strategies and Best Practices.","authors":"Nishant Kumar, Amy M Knight, Andrew P Demidowich, Camille F Stanback, Holly Bashura, Qudsia Hussain, Eva H Gonzales, Jordan Funk, Mahsa Motevalli, Mihail Zilbermint","doi":"10.1177/19322968251370754","DOIUrl":"https://doi.org/10.1177/19322968251370754","url":null,"abstract":"<p><p>Continuous glucose monitoring (CGM) has become the standard of care for outpatient diabetes management, yet its initiation during hospitalization-particularly at discharge-remains underutilized. The transition from hospital to home presents a unique opportunity to start CGM, educate patients, and improve glycemic outcomes. Although preliminary studies suggest that CGM initiation at discharge can increase time-in-range and reduce hypoglycemia and hospital readmissions, widespread adoption faces several challenges, including therapeutic inertia, patient selection, insurance barriers, and limited implementation guidance. At the time of this writing, CGMs are not yet US Food and Drug Administration-approved for inpatient use, but approval is anticipated. In this article, we present an actionable, stepwise protocol for CGM initiation at hospital discharge, developed by the Council for Clinical Excellence in Inpatient Diabetes at Johns Hopkins Medicine. The protocol includes multidisciplinary coordination, inclusive patient selection, structured education, designation of outpatient follow-up providers, and emphasis on consistent postdischarge care. We address common barriers such as impaired cognition during recovery and device compatibility with imaging studies. While further research is needed to confirm long-term cost-effectiveness and clinical outcomes, we believe our protocol can serve as a practical foundation for hospitals and providers seeking to safely and effectively integrate CGM initiation into discharge workflows.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968251370754"},"PeriodicalIF":3.7,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145075390","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":"Analysis of Adverse Events in Medical Devices for Diabetes.","authors":"Mariana Ribeiro Brandão, Jefferson Luiz Brum Marques, Renato Garcia Ojeda","doi":"10.1177/19322968251368860","DOIUrl":"10.1177/19322968251368860","url":null,"abstract":"<p><strong>Introduction: </strong>The objective of this study is to identify adverse events involving medical devices used in home environments with a focus on patients with diabetes and to categorize the probable causes.</p><p><strong>Methods: </strong>The chosen technologies that are fundamental for monitoring blood glucose and used in users' decision-making were: blood glucose monitor (BGM), continuous glucose monitoring system (CGM) and Insulin Pump. In the search for evidence, two databases from the collection of technovigilance alerts between January 2019 and December 2024 were used: the Technovigilance Analytical Portal of the National Health Surveillance Agency (ANVISA) of Brazil and MAUDE-FDA-USA.</p><p><strong>Results: </strong>On the MAUDE-FDA platform, the total number of notifications were: 52,601 BGM, 1,624,664 of CGM, and 1,339,652 Insulin Pump. Strategies to mitigate the occurrence of adverse events were presented, related to human, technological, and environmental factors. Regarding the main problems reported with the patient, they were hypoglycemia and hyperglycemia.</p><p><strong>Conclusion: </strong>This paper highlights the need to encourage the practice of reporting to generate evidence and to present strategies to mitigate adverse events, such as developing user-centered technologies inserted in an interdisciplinary ecosystem in the form of a living laboratory; considering accessibility aspects in development and incorporation; developing guidance resources for users; considering metrological aspects to ensure technological reliability; and including sustainability, security, and data privacy actions. Interconnectivity opens up opportunities for the ubiquitous management of technological processes throughout the life cycle.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968251368860"},"PeriodicalIF":3.7,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12436335/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145064626","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":"Including Aerobic Exercise Into Data-Based Virtual Twins for Glycemic Simulation.","authors":"Oriol Bustos, Omer Mujahid, Iván Contreras, Aleix Beneyto, Josep Vehi","doi":"10.1177/19322968251364291","DOIUrl":"https://doi.org/10.1177/19322968251364291","url":null,"abstract":"<p><strong>Background: </strong>Data-driven models of the glucose-insulin metabolism have recently emerged as an effective framework for realistic virtual patient modeling in diabetes. The growing demand for personalized therapies requires precise and individualized models that align naturally with machine learning models trained on patient-specific data. Using deep generative models such as generative adversarial networks opens new possibilities for incorporating previously unmodeled physiological phenomena into simulations.</p><p><strong>Methods: </strong>In this study, we developed a new extended version of our conditional Wasserstein generative adversarial network model by incorporating aerobic exercise intensity data from the T1DEXI dataset, along with insulin administration and carbohydrate consumption data. We use an aerobic physical activity model to describe the effects of immediate and prolonged exercise on glycemia from recorded discrete intensity levels. This enables the network to retain contextual information about recent aerobic physical activity. A total of 1479 days of data from 56 patients, including 308 exercise sessions, were used to train and validate our model.</p><p><strong>Results: </strong>We evaluated the model to ensure that it replicates real-world data from the T1DEXI study in terms of mean blood glucose, time below range, time in range, time above range, and time in tight range, both in aggregate and when separated by active and sedentary days. In addition, the model reproduces aerobic exercise-induced glucose drops.</p><p><strong>Conclusions: </strong>This new model provides a more reliable, extended framework for in silico trials that incorporate physical activity scenarios, which has the potential to be used in the design and validation of automated insulin delivery.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968251364291"},"PeriodicalIF":3.7,"publicationDate":"2025-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145064586","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":"Batteries in Diabetes Technology Devices and Recycling: Need for Eco-Design.","authors":"Lutz Heinemann, Sebastian Friedrich Petry, Chris Unsöld, David Klonoff","doi":"10.1177/19322968251368908","DOIUrl":"10.1177/19322968251368908","url":null,"abstract":"<p><p>Batteries are an essential component of many medical products used for diabetes therapy. The increased use of such products comes along with millions of batteries that are disposed of every year. The design of these products should enable the recycling of batteries as they contain a significant number of valuable resources. Regulations in the United States and the European Union concerning batteries used in medical products are changing toward requiring and supporting establishing recycling procedures. Currently, respective programs are active only in some countries. A greener diabetes therapy would include more attention to reducing usage and disposing of batteries.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968251368908"},"PeriodicalIF":3.7,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12425941/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145033434","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":"Machine Learning to Diagnose Complications of Diabetes.","authors":"Agatha F Scheideman, Mandy M Shao, Henry Zelada, Jorge Cuadros, Joshua Foreman, Pinaki Sarder, Cindy Ho, Niels Ejskjaer, Jesper Fleischer, Simon Lebech Cichosz, David G Armstrong, Nestoras Mathioudakis, Tao Wang, Yih Chung Tham, David C Klonoff","doi":"10.1177/19322968251365245","DOIUrl":"10.1177/19322968251365245","url":null,"abstract":"<p><p>Machine learning (ML) uses computer systems to develop statistical algorithms and statistical models that can draw inferences from demographic data, structured behavioral data, continuous glucose monitor (CGM) tracings, laboratory data, cardiovascular and neurological physiology measurements, and images from a variety of sources. ML is becoming increasingly used to diagnose complications of diabetes based on these types of datasets. In this article, we review the current status, barriers to progress, and future prospects for using ML to diagnose seven complications of diabetes, including five traditional complications, one set of other systemic complications, and one prediction that can result in favorable or unfavorable outcomes. The complications include (1) diabetic retinopathy, (2) diabetic nephropathy, (3) peripheral neuropathy, (4) autonomic neuropathy, (5) diabetic foot ulcers, and (6) other systemic complications. The prediction is for outcomes in hospitalized patients with diabetes. ML for these purposes is in its infancy, as evidenced by only a limited number of products having received regulatory clearance at this time. However, as multicenter reference datasets become available, it will become possible to train algorithms on increasingly larger and more complex datasets and patterns so that diagnoses and predictions will become increasingly accurate. The use of novel choices of images and imaging technologies will contribute to progress in this field. ML is poised to become a widely used tool for the diagnosis of complications and predictions of outcomes and glycemia in people with diabetes.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968251365245"},"PeriodicalIF":3.7,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12425951/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145033428","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}