Ariel M Lorenzo, Reden E Nolasco, Erovita Teresita B Agustin
{"title":"Climate-Responsive Validation of Non-invasive Glucose Sensing: Addressing Background Spectral Variability.","authors":"Ariel M Lorenzo, Reden E Nolasco, Erovita Teresita B Agustin","doi":"10.1177/19322968261506189","DOIUrl":"10.1177/19322968261506189","url":null,"abstract":"","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968261506189"},"PeriodicalIF":4.9,"publicationDate":"2026-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13768263/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149394394","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}
Andrea Benedetti, John J Shin, Benyamin Grosman, Ohad Cohen, Robert A Vigersky, Kamuran Turksoy, Toni L Cordero, Anirban Roy
{"title":"Development and Validation of a Meal Detection-Based Tool for User Behavior and Meal Management Analysis.","authors":"Andrea Benedetti, John J Shin, Benyamin Grosman, Ohad Cohen, Robert A Vigersky, Kamuran Turksoy, Toni L Cordero, Anirban Roy","doi":"10.1177/19322968261502414","DOIUrl":"10.1177/19322968261502414","url":null,"abstract":"<p><strong>Background: </strong>Management of the timing and frequency of meal announcements remains a key determinant of postprandial glycemic control in hybrid automated insulin delivery (AID) systems. Tools that translate routine device data into clinically interpretable insights on meal management behavior for individual patients and broader cohorts remain limited. These tools can potentially provide clinicians and users objective data to formulate personalized meal-related recommendations to safely improve outcomes.</p><p><strong>Methods: </strong>We developed a framework to quantify meal management behavior from routine AID data. The framework combines a meal detection model and a behavioral classification module that categorizes events as on-time, late, or missed based on temporal relationship between detected meals and carbohydrate entries. The meal detection model was trained on data from adults with type 1 diabetes using MiniMed 780G system (NCT04479826) and evaluated in a validation cohort of 157 individuals with type 1 diabetes using advanced hybrid closed-loop (AHCL) (NCT03959423) system.</p><p><strong>Results: </strong>Meal events detection accuracy reached 96.9% in the validation cohort, with precision ≥89.6%, recall ≥93.9%, and area under the curve = 0.996. Application of the tool to the validation cohort showed that a higher proportion of on-time announcements correlated with higher time in range (TIR) (ρ = 0.375, <i>q</i> < 0.001) and lower hyperglycemia. Each 10% increase in on-time announcements corresponded to a 2.66% increase in TIR. Increasing delay of late announcements was associated with worse postprandial glycemic outcomes.</p><p><strong>Conclusions: </strong>This framework enables insights into meal announcement patterns that may support patient counseling, clinical decision support, and large-scale analyses in AHCL systems.</p><p><strong>Clinical trial registration number: </strong>NCT04479826, NCT03959423.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968261502414"},"PeriodicalIF":4.9,"publicationDate":"2026-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13768315/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149386708","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}
Nila Novita Sari, Quoc Cuong Ngo, Rajna Ogrin, Samantha Hanna, Kate Waller, Barbara Polus, Richard J MacIsaac, Elif Ekinci, Dinesh Kant Kumar
{"title":"Automated Prediction of Diabetes-Related Foot Ulcer Healing at Initial Assessment.","authors":"Nila Novita Sari, Quoc Cuong Ngo, Rajna Ogrin, Samantha Hanna, Kate Waller, Barbara Polus, Richard J MacIsaac, Elif Ekinci, Dinesh Kant Kumar","doi":"10.1177/19322968261501979","DOIUrl":"10.1177/19322968261501979","url":null,"abstract":"<p><strong>Background: </strong>Diabetes-related foot ulcers (DFUs) that fail to heal within the expected trajectory and become chronic are associated with substantial morbidity. The current clinical standard for identifying chronic DFUs relies on a <50% reduction in wound area over 4 weeks. There is a critical need for tools that can predict wound-healing outcomes at first clinical presentation to enable timely, individualised wound management. We have developed and validated TherMUL, an AI device that analyses the texture of thermal images to predict DFU healing.</p><p><strong>Methods: </strong>Adults with neuropathic DFUs were recruited from 2 specialist foot clinics in Melbourne, Australia. TherMUL, a software-based device, was used to take thermal images during the initial visit. Texture features were extracted using grey-level co-occurrence matrix (GLCM) analysis. Wound-healing status at 12 weeks served as the ground-truth label for model training. A support vector machine (SVM) classifier was trained using the images from 44 healed and 24 unhealed DFUs. A separate unseen dataset was used for a preliminary feasibility assessment.</p><p><strong>Results: </strong>The classifier achieved a mean area under the curve (AUC) of 0.635, with a sensitivity of 75.8% for predicting unhealed DFUs, and a specificity of 53% for identifying healed DFUs. In the preliminary evaluation, 5 of 7 predictions correctly matched the 12-week podiatry outcomes.</p><p><strong>Conclusion: </strong>This study demonstrated early feasibility of using TherMUL to assist clinicians in predicting 12-week DFU healing outcomes at first clinical presentation, with moderate discriminative performance. This non-contact, point-of-care approach has the potential to support earlier identification of DFUs unlikely to heal and enable more timely, targeted wound management strategies.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968261501979"},"PeriodicalIF":4.9,"publicationDate":"2026-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13747917/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149379206","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}
Margaret Wei, Omar Kais Ibrahim, Jacqueline Marie Deirmenjian, Tochukwu Madu, Gian Paolo Simone, Steve Kim, Elizabeth Vi Nguyen, Cameron Escovedo, Hai Tran, Shawna Masih, Nichole McCann Ballweg, Elizabeth Zakis, Jennifer Ting-Chan, Roma Gianchandani
{"title":"Evaluation of Diabetic Ketoacidosis Outcomes Following the Adoption of a Computer-Based Variable-Rate Insulin Infusion Algorithm.","authors":"Margaret Wei, Omar Kais Ibrahim, Jacqueline Marie Deirmenjian, Tochukwu Madu, Gian Paolo Simone, Steve Kim, Elizabeth Vi Nguyen, Cameron Escovedo, Hai Tran, Shawna Masih, Nichole McCann Ballweg, Elizabeth Zakis, Jennifer Ting-Chan, Roma Gianchandani","doi":"10.1177/19322968261501915","DOIUrl":"10.1177/19322968261501915","url":null,"abstract":"<p><strong>Background: </strong>Diabetic ketoacidosis (DKA) management by variable-rate insulin infusion is increasing with the widespread adoption of electronic glucose management systems (eGMS). Herein, we evaluate the implementation of an updated process for DKA management incorporating the eGMS algorithm.</p><p><strong>Methods: </strong>An eGMS was implemented within the Cedars-Sinai Health System at our tertiary academic center (AC) and community hospital (CH) in January 2024. We compared outcomes after eGMS implementation (post-GMS) to the previous standard of care (pre-GMS). Adult patients admitted to the intensive care unit with a primary diagnosis of DKA and treated with an insulin infusion between January 2023 and December 2024 were included. We separately evaluated outcomes of hypoglycemia (blood glucose, BG <70 mg/dL) and severe hypoglycemia (BG <40 mg/dL) and treatment efficacy.</p><p><strong>Results: </strong>In total, 324 patients were included in the pre-GMS and 211 patients in the post-GMS cohorts. There was a decrease in the prevalence of hypoglycemia (pre-GMS: 11.0%, post-GMS: 4.3%, <i>P</i> = .005) and severe hypoglycemia (pre-GMS: 1.90%, post-GMS: 0.00%, <i>P</i> = .047). At AC, the hospital length of stay (LOS) decreased from 8.6 to 6.0 days (<i>P</i> = .012). At CH, insulin drip duration increased significantly (pre-GMS: 26.4 h, post-GMS: 36.7 h, <i>P</i> = .004), but there was no impact on LOS.</p><p><strong>Conclusion: </strong>Updating the DKA process and implementing an eGMS improved hypoglycemia rates throughout the institution. Hospital LOS was reduced at the AC, reflecting standardization and streamlining of the DKA processes.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968261501915"},"PeriodicalIF":4.9,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13735760/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149321714","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}
Line Davidsen, Morten Hasselstrøm Jensen, Thomas Kronborg, Stine Hangaard, Peter Vestergaard, Asbjørn Mohr Drewes, Filip Krag Knop, Simon Lebech Cichosz, Søren Schou Olesen
{"title":"Increased Glycemic Variability in Patients With Chronic Pancreatitis and Diabetes Compared to Type 2 Diabetes.","authors":"Line Davidsen, Morten Hasselstrøm Jensen, Thomas Kronborg, Stine Hangaard, Peter Vestergaard, Asbjørn Mohr Drewes, Filip Krag Knop, Simon Lebech Cichosz, Søren Schou Olesen","doi":"10.1177/19322968251356239","DOIUrl":"10.1177/19322968251356239","url":null,"abstract":"<p><strong>Background: </strong>Glycemic variability in diabetes secondary to pancreatic diseases (pancreatic diabetes) remains unclear. We compared glycemic control and variability in patients with pancreatic diabetes and a matched group of individuals with type 2 diabetes using continuous glucose monitoring (CGM).</p><p><strong>Methods: </strong>We included 30 patients with chronic pancreatitis and insulin-treated secondary diabetes and 30 individuals with insulin-treated type 2 diabetes (matched on HbA1c, age, and sex). Participants wore a blinded CGM for 20±2 days. Glycemic variability was assessed using coefficient of variation (CV), standard deviation (SD), mean amplitude of glycemic excursions (MAGE), and continuous overall net glycemic action (CONGA) at 1 and 2-hour intervals. Glycemic control was evaluated based on time spent in predefined glucose ranges: >250 mg/dL, 181 to 250 mg/dL, 70 to 180 mg/dL (target range), 54 to 69 mg/dL, and <54 mg/dL. CGM parameters were compared between groups.</p><p><strong>Results: </strong>All CGM-derived measures of glycemic variability (CV, SD, MAGE, CONGA1, and CONGA2) were significantly higher in patients with chronic pancreatitis and diabetes compared to individuals with type 2 diabetes (<i>P</i> < 0.01). Patients with chronic pancreatitis spent more time with glucose >250 mg/dL (8.8% vs 3.1%, <i>P</i> = 0.008), less time in the target range (70-180 mg/dL; 56.7% vs 68.5%, <i>P</i> = 0.044), and more time at 54-69 mg/dL (0.2% vs 0.0%, <i>P</i> = 0.041). Their glycemia risk index for hyperglycemia was also higher (25.5 vs 16.5, <i>P</i> = 0.033).</p><p><strong>Conclusion: </strong>Patients with pancreatic diabetes have higher glycemic variability than individuals with type 2 diabetes despite comparable levels of HbA1c.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1878-1887"},"PeriodicalIF":4.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12276207/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144667725","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}
Rawan AlSaad, Ali Elhenidy, Aliya Tabassum, Nour Odeh, Eman AboArqoub, Aya Odeh, Maya AlTamimi, Alaa Abd-Alrazaq, Rajat Thomas, Mohammed Bashir, Javaid Sheikh
{"title":"Artificial Intelligence in Gestational Diabetes Care: A Systematic Review.","authors":"Rawan AlSaad, Ali Elhenidy, Aliya Tabassum, Nour Odeh, Eman AboArqoub, Aya Odeh, Maya AlTamimi, Alaa Abd-Alrazaq, Rajat Thomas, Mohammed Bashir, Javaid Sheikh","doi":"10.1177/19322968251355967","DOIUrl":"10.1177/19322968251355967","url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence (AI) has emerged as a transformative tool for advancing gestational diabetes mellitus (GDM) care, offering dynamic, data-driven methods for early detection, management, and personalized intervention.</p><p><strong>Objective: </strong>This systematic review aims to comprehensively explore and synthesize the use of AI models in GDM care, including screening, diagnosis, management, and prediction of maternal and neonatal outcomes. Specifically, we examine (1) study designs and population characteristics; (2) the use of AI across different aspects of GDM care; (3) types of input data used for AI modeling; and (4) AI model types, validation strategies, and performance metrics.</p><p><strong>Methods: </strong>A systematic search was conducted across six electronic databases, identifying 126 eligible studies published up to February 2025. Data extraction and quality appraisal were independently conducted by six reviewers, using a modified version of the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool for risk of bias assessment.</p><p><strong>Results: </strong>Among 126 studies, 75% employed retrospective designs, with sample sizes ranging from 17 to over 100 000 participants. Most AI applications (85%) focused on early GDM prediction, while fewer addressed management, outcomes, or monitoring. Classical machine learning dominated (84%), with logistic regression and random forest frequently used. Internal validation was common (68%), but external validation was rare (6%). Our risk of bias appraisal indicated an overall moderate-to-good methodological quality, with notable deficiencies in analysis reporting.</p><p><strong>Conclusions: </strong>AI demonstrates strong potential to improve GDM prediction, screening, and management. Nonetheless, broader validation, enhanced model interpretability, and prospective studies in diverse populations are needed to translate these technologies into clinical practice.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1933-1950"},"PeriodicalIF":4.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12380749/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144956150","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}
Hellena Hailu Habte-Asres, Joseph Ngmenesegre Suglo, Khuram Chaudhry, Angus Forbes, David C Wheeler, Janaka Karalliedde
{"title":"Scoping Review-Diabetes Technology for Individuals on Kidney Replacement Therapy (Dialysis): Current Trends and Future Directions.","authors":"Hellena Hailu Habte-Asres, Joseph Ngmenesegre Suglo, Khuram Chaudhry, Angus Forbes, David C Wheeler, Janaka Karalliedde","doi":"10.1177/19322968251353811","DOIUrl":"10.1177/19322968251353811","url":null,"abstract":"<p><strong>Aim: </strong>This review aims to map the existing literature on the use of diabetes technology in people receiving dialysis, with a focus on utilization, accuracy, and effectiveness.</p><p><strong>Methods: </strong>A scoping review was conducted using the Joanna Briggs Institute methodology, with systematic searches of Medline, Embase, and CINAHL for studies on diabetes technologies in dialysis populations.</p><p><strong>Results: </strong>The search identified 1060 continuous glucose monitoring (CGM) and 1467 continuous subcutaneous insulin infusion or automated insulin delivery (CSII/AID) records, with 64 studies included. Eighteen studies assessed CGM accuracy, reporting mean absolute relative difference (MARD) values ranging from 8.1% to 29%, with over 97% of readings falling within Clarke error grid zones A or B. Thirteen studies compared glycemic markers, finding that HbA<sub>1c</sub> underestimated glucose by 7.3 mmol/mol, while glycated albumin showed a stronger correlation (r = 0.508). Four studies reported on dialysis effects, showing that people on automated peritoneal dialysis (APD) had lower mean glucose levels (181 ± 64 mg/dL) compared to continuous ambulatory peritoneal dialysis (CAPD) (238 ± 67 mg/dL; <i>P</i> < .05). Eleven studies evaluating diabetes treatment efficacy using CGM found that dulaglutide significantly reduced glucose CV from 28.1% to 19.8% (<i>P</i> = .003). Twenty-two studies examining glycemic outcomes reported that TIR was lower on dialysis days (80.2%, <i>P</i> = .02). Finally, four AID studies reported TIR improvements of up to 37.6% and a 1.5 mmol/L reduction in glucose (<i>P</i> = .003).</p><p><strong>Conclusion: </strong>This review highlights the potential of CGM and AID to improve diabetes outcomes in people on dialysis. While their clinical utility is evident, broader access and further research are needed to optimize their use in this high-risk population.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1985-2002"},"PeriodicalIF":4.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12405195/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144956180","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 and Driving Safety: Clarifying the Inference From a Survey of Insulin-Treated Adults With Type 2 Diabetes.","authors":"Ngoc-Nguyen Thi Nguyen","doi":"10.1177/19322968261483747","DOIUrl":"10.1177/19322968261483747","url":null,"abstract":"","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"2019"},"PeriodicalIF":4.9,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13546383/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148891935","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}
Tanja Fredensborg Holm, Thomas Kronborg, Morten Hasselstrøm Jensen, Stine Hangaard
{"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<sub>1c</sub>] ≥39 mmol/mol and <48 mmol/mol) and normoglycemia (HbA<sub>1c</sub> <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":"1888-1898"},"PeriodicalIF":4.9,"publicationDate":"2026-11-01","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}