Journal of Diabetes Science and Technology最新文献

{"title":"Identification of Core Outcome Domains and Design of a Survey Questionnaire to Evaluate Impacts of Digital Health Solutions That Matter to People With Diabetes.","authors":"Soren Eik Skovlund, Scibilia Renza, Julie Laurent, Paco Cerletti","doi":"10.1177/19322968231179740","DOIUrl":"10.1177/19322968231179740","url":null,"abstract":"<p><strong>Background: </strong>Digital health solutions (DHS) are increasingly used to support people with diabetes (PwD) to help manage their diabetes and to gather and manage health and treatment data. There is a need for scientifically reliable and valid methods to measure the value and impact of DHS on outcomes that matter to PwD. Here, we describe the development of a survey questionnaire designed to assess the perceptions of PwD toward DHS and their prioritized outcomes for DHS evaluation.</p><p><strong>Method: </strong>We applied a structured process for engagement of a total of nine PwD and representatives of diabetes advocacy organizations. Questionnaire development consisted of a scoping literature review, individual interviews, workshops, asynchronous virtual collaboration, and cognitive debriefing interviews.</p><p><strong>Results: </strong>We identified three overarching categories of DHS, which were meaningful to PwD and crucial for the identification of relevant outcomes: (1) online/digital tools for information, education, support, motivation; (2) personal health monitoring to support self-management; (3) digital and telehealth solutions for engaging with health professionals. Overall outcome domains identified to be important were diabetes-related quality of life, distress, treatment burden, and confidence in self-management. Additional positive and negative outcomes specific to DHS were identified and corresponding questions were incorporated into the survey questionnaire.</p><p><strong>Conclusion: </strong>We identified the need for self-reporting of quality of life, diabetes distress, treatment burden, and confidence in self-management, as well as specific positive and negative impacts of DHS. We designed a survey questionnaire to further assess the perceptions and perspectives of people with type 1 and 2 diabetes on outcomes relevant for DHS evaluations.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"136-142"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11688682/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9717842","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":"Consensus Report on Glucagon-Like Peptide-1 Receptor Agonists as Adjunctive Treatment for Individuals With Type 1 Diabetes Using an Automated Insulin Delivery System.","authors":"Viral N Shah, Anne L Peters, Guillermo E Umpierrez, Jennifer L Sherr, Halis Kaan Akturk, Grazia Aleppo, Lia Bally, Eda Cengiz, Ali Cinar, Kathleen Dungan, Chiara Fabris, Peter G Jacobs, Rayhan A Lal, Julia K Mader, Umesh Masharani, Priya Prahalad, Signe Schmidt, Eric Zijlstra, Cindy N Ho, Alessandra T Ayers, Tiffany Tian, Rachel E Aaron, David C Klonoff","doi":"10.1177/19322968241291512","DOIUrl":"10.1177/19322968241291512","url":null,"abstract":"<p><p>With increasing prevalence of obesity and cardiovascular diseases, there is a growing interest in the use of glucagon-like peptide-1 receptor agonists (GLP-1RAs) as an adjunct therapy in type 1 diabetes (T1D). The GLP-1RAs are currently not approved by the US Food and Drug Administration for the treatment of T1D in the absence of randomized controlled trials documenting efficacy and safety of these agents in this population. The Diabetes Technology Society convened a series of three consensus meetings of clinicians and researchers with expertise in diabetes technology, GLP-1RA therapy, and T1D management. The project was aimed at synthesizing current literature and providing conclusions on the use of GLP-1RA therapy as an adjunct to automated insulin delivery (AID) systems in adults with T1D. The expert panel members met virtually three times on January 17, 2024, and April 24, 2024, and August 14, 2024, to discuss topics ranging from physiology and outcomes of GLP-1RAs in T1D to limitations of current sensors, algorithms, and insulin for AID systems. The panelists also identified research gaps and future directions for research. The panelists voted to in favor of 31 recommendations. This report presents the consensus opinions of the participants that, in adults with T1D using AID systems, GLP-1RAs have the potential to (1) provide effective adjunct therapy and (2) improve glycemic and metabolic outcomes without increasing the risk of severe hypoglycemia or diabetic ketoacidosis.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"191-216"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11571606/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142621198","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":"Discordance Between Clinician and Person-With-Diabetes Perceptions Regarding Technology Barriers and Benefits.","authors":"Ananta Addala, Kelsey R Howard, Yasaman Hosseinipour, Laya Ekhlaspour","doi":"10.1177/19322968241285045","DOIUrl":"10.1177/19322968241285045","url":null,"abstract":"<p><p>The quality of clinician-patient relationship is integral to patient health and well-being. This article is a narrative review of published literature on concordance between clinician and patient perspectives on barriers to diabetes technology use. The goals of this manuscript were to review published literature on concordance and to provide practical recommendations for clinicians and researchers. In this review, we discuss the qualitative and quantitative methods that can be applied to measure clinician and patient concordance. There is variability in how concordance is defined, with some studies using questionnaires related to working alliance, while others use a dichotomous variable. We also explore the impact of concordance and discordance on diabetes care, barriers to technology adoption, and disparities in technology use. Published literature has emphasized that physicians may not be aware of their patients' perspectives and values. Discordance between clinicians and patients can be a barrier to diabetes management and technology use. Future directions for research in diabetes technology including strategies for recruiting and retaining representative samples, are discussed. Recommendations are given for clinical care, including shared decision-making frameworks, establishing social support groups optimizing clinician-patient communication, and using patient-reported outcomes to measure patient perspectives on outcomes of interest.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"18-26"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11571633/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142377875","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":"Adverse Event Causes From 2022 for Four Continuous Glucose Monitors.","authors":"Jan S Krouwer","doi":"10.1177/19322968231178525","DOIUrl":"10.1177/19322968231178525","url":null,"abstract":"<p><strong>Background: </strong>Adverse events for continuous glucose monitors (CGMs) represent a significant issue for people with diabetes with 281 963 CGM adverse events occurring in 2022. The process to obtain adverse events and the US Food and Drug Administration (FDA) database that contains them are reviewed.</p><p><strong>Methods: </strong>Tables were created in SQL Server for four CGM products (Dexcom G6, all versions of Abbott Libre, Medtronic Guardian 3, and Senseonics Eversense) containing either malfunction or injury adverse events sorted by the manufacturer's chosen product code. As the product code is not always clear (or appropriate), the causes of the events were determined from the text description of the adverse event. The resulting causes were listed in decreasing order in tables for each product and event type.</p><p><strong>Results: </strong>A common effect of several event causes prevented the user from obtaining a result. Inaccuracy was also a frequent complaint. Other causes were specific to that device.</p><p><strong>Conclusions: </strong>Creating tables based on manufacturer problem codes for their CGMs, followed by analysis of the adverse event text, facilitates the analysis of event causes. Analyzing adverse event data is the first step in trying to reduce the number of adverse events.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"80-83"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11688675/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9615700","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":"Current Perspective on the Potential Benefits of Smart Insulin Pens on Glycemic Control in Patients With Diabetes: Spanish Delphi Consensus.","authors":"Jesús Moreno-Fernandez, Gonzalo Díaz-Soto, Juan Girbes, Francisco Javier Arroyo","doi":"10.1177/19322968231178022","DOIUrl":"10.1177/19322968231178022","url":null,"abstract":"<p><strong>Introduction: </strong>Diabetes mellitus (DM) is a chronic disease with high morbidity and mortality, and glycemic control is key to avoiding complications. Technological innovations have led to the development of new tools to help patients with DM manage their condition.</p><p><strong>Objective: </strong>This consensus assesses the current perspective of physicians on the potential benefits of using smart insulin pens in the glycemic control of patients with type 1 diabetes (DM1) in Spain.</p><p><strong>Methods: </strong>The Delphi technique was used by 110 physicians who were experts in managing patients with DM1. The questionnaire consisted of 94 questions.</p><p><strong>Results: </strong>The consensus obtained was 95.74%. The experts recommended using the ambulatory glucose profile report and the different time-in-range (TIR) metrics to assess poor glycemic control. Between 31% and 65% of patients had TIR values less than 70% and were diagnosed based on glycosylated hemoglobin values. They believed that less than 10% of patients needed to remember to administer the basal insulin dose and between 10% and 30% needed to remember the prandial insulin dose.</p><p><strong>Conclusions: </strong>The perception of physicians in their usual practice leads them to recommend the use of ambulatory glucose profile and time in range for glycemic control. Forgetting to administer insulin is a very common problem and the actual occurrence rate does not correspond with clinicians' perceptions. Technological improvements and the use of smart insulin pens can increase treatment adherence, strengthen the doctor-patient relationship, and help improve patients' education and quality of life.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"123-135"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11688688/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9565548","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":"Psychosocial Aspects of Diabetes Technologies: Commentary on the Current Status of the Evidence and Suggestions for Future Directions.","authors":"Katharine Barnard-Kelly, Linda Gonder-Frederick, Jill Weissberg-Benchell, Lauren E Wisk","doi":"10.1177/19322968241276550","DOIUrl":"10.1177/19322968241276550","url":null,"abstract":"<p><p>Diabetes technologies, including continuous glucose monitors, insulin pumps, and automated insulin delivery systems offer the possibility of improving glycemic outcomes, including reduced hemoglobin A1c, increased time in range, and reduced hypoglycemia. Given the rapid expansion in the use of diabetes technology over the past few years, and touted promise of these devices for improving both clinical and psychosocial outcomes, it is critically important to understand issues in technology adoption, equity in access, maintaining long-term usage, opportunities for expanded device benefit, and limitations of the existing evidence base. We provide a brief overview of the status of the literature-with a focus on psychosocial outcomes-and provide recommendations for future work and considerations in clinical applications. Despite the wealth of the existing literature exploring psychosocial outcomes, there is substantial room to expand our current knowledge base to more comprehensively address reasons for differential effects, with increased attention to issues of health equity and data harmonization around patient-reported outcomes.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"27-33"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11571636/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142466697","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":"Treatment Satisfaction and Well-Being With Continuous Glucose Monitoring in People With Type 1 Diabetes: An Analysis Based on the GOLD Randomized Trial.","authors":"Daniel Pylov, William Polonsky, Henrik Imberg, Helen Holmer, Jarl Hellman, Magnus Wijkman, Jan Bolinder, Tim Heisse, Sofia Dahlqvist, Thomas Nyström, Erik Schwarz, Irl Hirsch, Marcus Lind","doi":"10.1177/19322968231183974","DOIUrl":"10.1177/19322968231183974","url":null,"abstract":"<p><strong>Background: </strong>The GOLD trial demonstrated that continuous glucose monitoring (CGM) in people with type 1 diabetes (T1D) managed with multiple daily insulin injections (MDI) improved not only glucose control but also overall well-being and treatment satisfaction. This analysis investigated which factors contributed to improved well-being and treatment satisfaction with CGM.</p><p><strong>Methods: </strong>The GOLD trial was a randomized crossover trial comparing CGM versus self-monitored blood glucose (SMBG) over 16 months. Endpoints included well-being measured by the World Health Organization-Five Well-Being Index (WHO-5) and treatment satisfaction by the Diabetes Treatment Satisfaction Questionnaire (DTSQ) as well as glucose metrics. Multivariable R²-decomposition was used to understand which variables contributed most to treatment satisfaction.</p><p><strong>Results: </strong>A total of 139 participants were included. Multivariable analyses revealed that increased convenience and flexibility contributed to 60% (95% confidence interval [CI] = 50%-69%) of the improvement in treatment satisfaction (Diabetes Treatment Satisfaction Questionnaire <i>change</i> version [DTSQ<i>c</i>]) observed with CGM, whereas perceived effects on hypoglycemia and hyperglycemia only contributed to 6% (95% CI = 2%-11%) of improvements. Significant improvements in well-being (WHO-5) by CGM were observed for the following: feeling cheerful (<i>P</i> = .025), calm and relaxed (<i>P</i> = .024), being active (<i>P</i> = .046), and waking up fresh and rested (<i>P</i> = .044). HbA1c reductions and increased time in range (TIR) were associated with increased treatment satisfaction, whereas glycemic variability was not. HbA1c reduction showed also an association with increased well-being and increased TIR with less diabetes-related distress.</p><p><strong>Conclusions: </strong>While CGM improves glucose control in people with T1D on MDI, increased convenience and flexibility through CGM is of even greater importance for treatment satisfaction and patient well-being. These CGM-mediated effects should be taken into account when considering CGM initiation.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"143-152"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11688678/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10259898","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":"Development and Validation of an Electronic Health Record-Based Risk Assessment Tool for Hypoglycemia in Patients With Type 2 Diabetes Mellitus.","authors":"Sisi Ma, Alison Alvear, Pamela J Schreiner, Elizabeth R Seaquist, Thomas Kirsh, Lisa S Chow","doi":"10.1177/19322968231184497","DOIUrl":"10.1177/19322968231184497","url":null,"abstract":"<p><strong>Background: </strong>The recent availability of high-quality data from clinical trials, together with machine learning (ML) techniques, presents exciting opportunities for developing prediction models for clinical outcomes.</p><p><strong>Methods: </strong>As a proof-of-concept, we translated a hypoglycemia risk model derived from the Action to Control Cardiovascular Risk in Diabetes (ACCORD) study into the HypoHazardScore, a risk assessment tool applicable to electronic health record (EHR) data. To assess its performance, we conducted a 16-week clinical study at the University of Minnesota where participants (N = 40) with type 2 diabetes mellitus (T2DM) had hypoglycemia assessed prospectively by continuous glucose monitoring (CGM).</p><p><strong>Results: </strong>The HypoHazardScore combines 16 risk factors commonly found within the EHR. The HypoHazardScore successfully predicted (area under the curve [AUC] = 0.723) whether participants experienced least one CGM-assessed hypoglycemic event (glucose <54 mg/dL for ≥15 minutes from two CGMs) while significantly correlating with frequency of CGM-assessed hypoglycemic events (r = 0.38) and percent time experiencing CGM-assessed hypoglycemia (r = 0.39). Compared to participants with a low HypoHazardScore (N = 19, score <4, median score of 4), participants with a high HypoHazardScore (N = 21, score ≥4) had more frequent CGM-assessed hypoglycemic events (high: 1.6 ± 2.2 events/week; low: 0.3 ± 0.5 events/week) and experienced more CGM-assessed hypoglycemia (high: 1.4% ± 2.0%; low: 0.2% ± 0.4% time) during the 16-week follow-up.</p><p><strong>Conclusions: </strong>We demonstrated that a hypoglycemia risk model can be successfully adapted from the ACCORD data to the EHR, with validation by a prospective study using CGM-assessed hypoglycemia. The HypoHazardScore represents a significant advancement toward implementing an EHR-based decision support system that can help reduce hypoglycemia in patients with T2DM.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"105-113"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11688684/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9695189","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 Empirical Review of Key Glucose Monitoring Devices: Product Iterations and Patent Protection.","authors":"Jonathan J Darrow, Victor Van de Wiele, David Beran, Aaron S Kesselheim","doi":"10.1177/19322968231178016","DOIUrl":"10.1177/19322968231178016","url":null,"abstract":"<p><strong>Introduction: </strong>Each year, people with diabetes and their insurers or governments spend billions of dollars on blood glucose monitors and their associated components. These monitors have evolved substantially since their introduction in the 1970s, and manufacturers frequently protect original medical devices and their modifications by applying for and obtaining patent protection.</p><p><strong>Research design and methods: </strong>We tracked the product iterations of five widely used blood glucose monitors-manufactured by LifeScan, Dexcom, Abbott, Roche, and Trividia-from information published by the U.S. Food and Drug Administration (FDA), and extracted relevant U.S. patents.</p><p><strong>Results: </strong>We found 384 products made by the five manufacturers of interest, including 130 devices cleared through the 510(k) pathway, 251 approved via the premarket approval (PMA) pathway or via PMA supplements, and three for which <i>de novo</i> requests were granted. We identified 8095 patents potentially relevant to these devices, 2469 (31%) of which were likely to have expired by July 2021.</p><p><strong>Conclusions: </strong>Manufacturers of blood glucose monitoring systems frequently modified their devices and obtained patent protection related to these device modifications. The therapeutic value of these new modifications should be critically evaluated and balanced against their additional cost. Older glucose monitoring devices that were marketed in decades past are now in the public domain and no longer protected by patents. Newer devices will join them as their patents expire. Increased demand from people with diabetes and the health care system for older, off-patent devices would provide an incentive for the medical device industry to make these devices more widely available, enabling good care at lower cost when such devices are substantially equivalent in effectiveness and safety. In turn, availability and awareness of older, off-patent devices could help stimulate such demand.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"84-90"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11688697/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9572341","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":"Development and Validation of Binary Classifiers to Predict Nocturnal Hypoglycemia in Adults With Type 1 Diabetes.","authors":"Ioannis Afentakis, Rebecca Unsworth, Pau Herrero, Nick Oliver, Monika Reddy, Pantelis Georgiou","doi":"10.1177/19322968231185796","DOIUrl":"10.1177/19322968231185796","url":null,"abstract":"<p><strong>Background: </strong>One of the biggest challenges for people with type 1 diabetes (T1D) using multiple daily injections (MDIs) is nocturnal hypoglycemia (NH). Recurrent NH can lead to serious complications; hence, prevention is of high importance. In this work, we develop and externally validate, device-agnostic Machine Learning (ML) models to provide bedtime decision support to people with T1D and minimize the risk of NH.</p><p><strong>Methods: </strong>We present the design and development of binary classifiers to predict NH (blood glucose levels occurring below 70 mg/dL). Using data collected from a 6-month study of 37 adult participants with T1D under free-living conditions, we extract daytime features from continuous glucose monitor (CGM) sensors, administered insulin, meal, and physical activity information. We use these features to train and test the performance of two ML algorithms: Random Forests (RF) and Support Vector Machines (SVMs). We further evaluate our model in an external population of 20 adults with T1D using MDI insulin therapy and wearing CGM and flash glucose monitoring sensors for two periods of eight weeks each.</p><p><strong>Results: </strong>At population-level, SVM outperforms RF algorithm with a receiver operating characteristic-area under curve (ROC-AUC) of 79.36% (95% CI: 76.86%, 81.86%). The proposed SVM model generalizes well in an unseen population (ROC-AUC = 77.06%), as well as between the two different glucose sensors (ROC-AUC = 77.74%).</p><p><strong>Conclusions: </strong>Our model shows state-of-the-art performance, generalizability, and robustness in sensor devices from different manufacturers. We believe it is a potential viable approach to inform people with T1D about their risk of NH before it occurs.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"153-160"},"PeriodicalIF":4.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11696951/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9773156","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}