Diabetology最新文献

{"title":"Circadian Regulation of Glucose Metabolism: Implications for Pathogenesis and Chronotherapy of Type 2 Diabetes.","authors":"Michael Oraebosi, Connor Baucom, Ruifeng Cao","doi":"10.3390/diabetology7070122","DOIUrl":"10.3390/diabetology7070122","url":null,"abstract":"<p><p>The global prevalence of type 2 diabetes continues to rise at an alarming pace, challenging existing strategies for disease prevention and management. Beyond traditional risk factors, increasing evidence indicates that glucose metabolism is temporally regulated by the body's 24 h biological clock and oscillates based on the time of day. Disturbances of the circadian clock function are linked to impairments in glucose homeostasis and increased risk of obesity and diabetes. This review explores the intricate relationship between the circadian system and glucose homeostatic control. We begin with an introduction to the hierarchical organization of the circadian system. Next, we examine the role of the circadian clock in regulating organs and tissues that are involved in glucose metabolism, i.e., the pancreas, skeletal muscles, the liver and adipose tissue. We next review evidence that supports the involvement of circadian disturbances in the pathogenesis of diabetes. Finally, we discuss chronotherapy and its potential application in clinical intervention of diabetes. As type 2 diabetes becomes increasingly common worldwide, understanding how the body's internal clock shapes this disease may open new and powerful opportunities for its prevention and treatment.</p>","PeriodicalId":72798,"journal":{"name":"Diabetology","volume":"7 7","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13459836/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148714637","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":"Can a Chatbot Help Heal a Wound? Context-Aware Prompts for Boosting Adherence in Diabetic Foot Ulcers.","authors":"Aria Rabet, Aminreza Khandan, Arian Rabet, Mohammad Dehghan Rouzi, Fabiola Rodriguez, Adriana Garibay, David G Armstrong, Bijan Najafi","doi":"10.3390/diabetology7050096","DOIUrl":"10.3390/diabetology7050096","url":null,"abstract":"<p><strong>Background: </strong>Smart offloading technologies enable the real-time, objective monitoring of adherence in patients with diabetic foot ulcers (DFUs). Although remote tracking may reinforce adherence and improve wound healing, effectiveness depends on sustained device use, particularly as devices are often removed during rest periods. Real-time, behavior-contingent feedback informed by sensor data, including AI-supported messaging capable of detecting nonadherence, may enhance reinforcement. However, the feasibility and behavioral impact of such strategies remain unclear.</p><p><strong>Methods: </strong>We conducted a prospective feasibility case series nested within a larger DFU cohort of 210 participants, enrolling eight adults with active DFUs. Participants used a sensor-integrated offloading device paired with a smartwatch (SmartBoot) and a mobile application (CORA) that delivered notifications to their smartphones. Notifications were either schedule-based or context-aware, using real-time SmartBoot data to generate personalized messages. The primary outcome was a sensor-detected transition from nonadherent to adherent offloading within 60 min.</p><p><strong>Results: </strong>A total of 130 notifications were delivered, with 125 included in the behavioral response analysis. Context-aware notifications demonstrated higher transition rates than schedule-based notifications. Adaptive Reinforcement yielded the highest response rate (77.4%, 24/31), followed by Clinical Course Correction (71.4%, 20/28), whereas Safety and Technical Assurance (40.7%, 11/27) and Motivational Coaching (30.8%, 12/39) showed lower response rates.</p><p><strong>Conclusions: </strong>Real-time, context-aware feedback is feasible and associated with improved short-term adherence, supporting evaluation in larger trials.</p>","PeriodicalId":72798,"journal":{"name":"Diabetology","volume":"7 5","pages":"96"},"PeriodicalIF":2.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13543935/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148898360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Thematic Analysis of Sleep Behavior Self-Regulation in Young Adults with Type 1 Diabetes.","authors":"Madeline Long, Dayna A Johnson, Youjeong Kang, Stephanie Alisha Griggs","doi":"10.3390/diabetology7040080","DOIUrl":"10.3390/diabetology7040080","url":null,"abstract":"<p><strong>Background/objectives: </strong>Sleep is critical for young adults, particularly those with type 1 diabetes (T1D), who face unique challenges in achieving recommended sleep and diabetes health targets. The purpose of this study guided by the theoretical framework of self-regulation theory is to explore how these individuals navigate self-regulatory processes in their sleep behaviors through mechanisms of self-monitoring, self-judgment, and self-evaluation.</p><p><strong>Methods: </strong>A qualitative descriptive design was implemented using semi-structured interviews with 34 young adults (ages 18-30) living with T1D. Data were collected through sleep diaries, actigraphy, and continuous glucose monitoring, followed by thematic analysis to identify sleep behavior self-regulation patterns.</p><p><strong>Results: </strong>Three primary themes were identified: (1) Sleep Behavior Self-Monitoring - highlighting participants' awareness of their sleep habits and the diabetes-related impacts on these habits; (2) Self-Judgment - reflecting how personal and societal standards inform their evaluation of sleep health; (3) Self-Evaluation - showing emotional responses associated with sleep outcomes, where good sleep led to positive feelings and motivation, while poor sleep resulted in frustration.</p><p><strong>Conclusions: </strong>Understanding sleep behavior self-regulation among young adults with T1D is crucial for improving sleep health and diabetes management. Targeted interventions incorporating sleep education and self-regulatory strategies may enhance both perceived sleep quality and overall well-being in this population.</p>","PeriodicalId":72798,"journal":{"name":"Diabetology","volume":"7 4","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13155417/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870579","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":"Exploring the Relationship Between Health Biomarkers and Performance on a Novel Color Perimetry Device in Prediabetes and Type 2 Diabetes.","authors":"Liam Burhans, Bismark Owusu-Afriyie, Christopher S Wu, Jennyffer D Smith, Daniel R Coates","doi":"10.3390/diabetology6120147","DOIUrl":"10.3390/diabetology6120147","url":null,"abstract":"<p><strong>Background/objectives: </strong>Type 2 diabetes (T2DM) is a leading cause of vision loss. Functional measurements (color vision and contrast sensitivity) are sensitive to early changes in eyes even before retinopathy is present. This study evaluates a novel color perimetry device as an indicator of diabetic eye disease.</p><p><strong>Methods: </strong>40 subjects (age-matched) were divided into 3 groups by HbA1c or previous diagnosis (control ≤5.6%, prediabetes 5.7-6.4%, diabetes ≥6.5%). Additional health metrics gathered included: BMI, body fat %, total cholesterol, HDL/LDL levels, blood glucose, and blood pressure. Novel color perimetry which measures chromatic thresholds at 4 locations 3 degrees from the fovea for 5 colors (achromatic, red, green, blue, and yellow) was completed. Mars contrast and L'Anthony D15 color testing were also completed. Lens photos excluded those with cataracts.</p><p><strong>Results: </strong>There were differences between the groups for HbA1c (p<0.001), BMI (p=0.046), body fat % (p=0.020), and color perimetry for the yellow condition only (p=0.013). The achromatic condition was highly associated with Mars contrast sensitivity (p<0.001). HbA1c was associated with both parvocellular (average of red and green) (p=0.014) and koniocellular (average of blue and yellow) color perimetry performance (p=0.022).</p><p><strong>Conclusions: </strong>HbA1c is associated with color perimetry across both retinal pathways. The yellow condition in particular holds promise as a biomarker for presence of functional changes in diabetes prior to the onset of retinopathy. Other health metrics did not influence chromatic thresholds. More research needs to be done to evaluate color perimetry in these patient groups to understand these relationships.</p>","PeriodicalId":72798,"journal":{"name":"Diabetology","volume":"6 12","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13533418/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148876722","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 Impact of Cast Walker Design on Metabolic Costs of Walking and Perceived Exertion.","authors":"Emily Standage, Dylan Tookey, Uchechukwu Ukachukwu, Marco Avalos, Ryan T Crews, Noah J Rosenblatt","doi":"10.3390/diabetology6090098","DOIUrl":"10.3390/diabetology6090098","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background/objectives: &lt;/strong&gt;Cast walkers (CWs) are often prescribed to offload diabetic foot ulcers (DFUs). However, their mass, the degree of ankle immobilization and the limb length discrepancy they induce may increase the energetic demands of walking, contributing to lower adherence and poorer healing. The purpose of this study was to evaluate the effects of different commercially available CW options on the metabolic costs and perceived exertion of walking, and on related spatiotemporal kinematics, in healthy young participants as an initial step to understanding factors that impact adherence in patients with DFUs.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Participants walked on an instrumented treadmill at a standardized speed for six minutes under five footwear conditions: (1) athletic shoes only (control); (2) ankle-high CW on the dominant limb with athletic shoe on the contralateral limb; (3) condition two with an external lift on the athletic shoe; (4 and 5) conditions two and three with a knee-high CW. Condition 1 was performed first, after which the CW conditions were randomized. During all conditions, a portable calorimeter recorded gas exchange on a breath-by-breath basis. The metabolic cost of transport (MCoT) was quantified as the mean oxygen consumed per meter walked per kilogram body mass, after accounting for standing. After walking, participants reported perceived exertion using the Borg Rating of Perceived Exertion scale (RPE). From the treadmill data, we extracted the mean step width (SW) as well as absolute values for symmetry indices (SIs) for step length (SL) and step time (ST), all of which have associations with MCoT. For each outcome, linear mixed models compared each CW condition with the control and tested for effects of CW height (ankle-high vs. knee-high) and of the lift.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;A total of 14 healthy young adults without diabetes participated. MCoT, RPE and SW were significantly higher for all CW conditions compared to the control, with less consistent results for asymmetry measures. MCoT was not significantly different across CW height or lift condition although an unexpected interaction between limb and CW height n was observed; MCoT was lower in the knee-high CW with vs. without a lift but did not change in the ankle-high CW based on lift status. Similarly, neither SW nor SIs changed in expected fashions across conditions. In contrast, RPE was significantly lower using the ankle- vs. knee-high CW and when using a lift vs no lift, with no significant interaction.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Although metabolic costs were unaffected by CW design changes, which may reflect the absence of anticipated changes in kinematics that impact MCoT, perceived exertion was reduced through such changes. Unanticipated biomechanical changes may reflect a complex interaction among a number of competing factors that dictate behavior and MCoT. The differing results in perception of exertion and me","PeriodicalId":72798,"journal":{"name":"Diabetology","volume":"6 9","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12462845/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145187742","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 Diabetic Foot Ulcer Outcomes in Medicaid Beneficiaries with Podiatric Care Access.","authors":"Ivan Y Luu, Alexander T Hong, Ashton Lee, Juan C Arias, Chia-Ding Shih, David G Armstrong, Tze-Woei Tan","doi":"10.3390/diabetology5050036","DOIUrl":"https://doi.org/10.3390/diabetology5050036","url":null,"abstract":"<p><strong>Objectives: </strong>This study aims to examine the association between state Medicaid coverage of podiatry services and the outcomes of beneficiaries with new diabetic foot ulcers (DFUs).</p><p><strong>Methods: </strong>Medicaid beneficiaries who developed a DFU between 2010 and 2015 were identified using the PearlDiver claims database. The states were categorized into covered states (CS) and non-covered states (NCS) based on podiatric coverage during the study period. The outcomes included major amputation, minor amputation, and hospitalization due to foot infection within 12 months of index diagnosis. Logistic regression was used to assess the association of state coverage type and outcomes, controlling for age, sex, and the Charlson Comorbidity Index (CCI).</p><p><strong>Results: </strong>Our study included 16,905 Medicaid beneficiaries who developed new DFUs: 14,748 in CS and 2157 in NCS. The overall major amputation rate was 2.6%. The risk of major amputation was 48% lower among Medicaid beneficiaries in CS (OR 0.52, 95% CI 0.31-0.90) than in NCS. The Medicaid beneficiaries in CS had a 24% lower risk of hospitalization for foot infection (OR 0.76, 95% CI 0.67-0.85) but had a 58% higher risk of minor amputation (OR 1.58, 95% CI 1.22-2.07) than in NCS.</p><p><strong>Conclusions: </strong>Medicaid coverage of podiatry services might be associated with lower rates of major amputation and reduced risk of hospitalization for foot infection.</p>","PeriodicalId":72798,"journal":{"name":"Diabetology","volume":"5 5","pages":"491-500"},"PeriodicalIF":2.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11706342/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142959571","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":"Outcomes for Patients with Diabetic Foot Ulcers Following Transition from Medicaid to Commercial Insurance.","authors":"KiBeom Kwon, Taylor A Brown, Juan C Arias Aristizábal, David G Armstrong, Tze-Woei Tan","doi":"10.3390/diabetology5030027","DOIUrl":"10.3390/diabetology5030027","url":null,"abstract":"<p><strong>Objective: </strong>This study investigates the outcomes of Medicaid beneficiaries with diabetic foot ulcers (DFUs) who had transitioned to commercial insurance.</p><p><strong>Methods: </strong>We utilized the PearlDiver claims database to identify adult patients diagnosed with a new DFU between 2010 and 2019. The study cohort comprised 8856 Medicaid beneficiaries who had at least three years of continuous enrollment after DFU diagnosis. Medicaid beneficiaries who transitioned to Medicare during follow-up were excluded. Adjusted comparisons of outcomes were performed by propensity matching the two groups for age, gender, and Charlson Comorbidity Index (CCI) in a 1:1 ratio. We used logistic regression and Kaplan-Meier estimate to evaluate the association between insurance change (from Medicaid to commercial insurance) and major amputation.</p><p><strong>Results: </strong>Among the 8856 Medicaid beneficiaries with DFUs, 66% (<i>n</i> = 5809) had transitioned to commercial insurance coverage during follow-up. The overall major amputation rate was 2.8% (<i>n</i> = 247), with a lower rate observed in patients who transitioned to commercial insurance compared to those with continuous Medicaid coverage (2.6% vs. 3.2%, <i>p</i> < 0.05). In multivariable analysis, Medicaid beneficiaries who transitioned to commercial insurance had a 27% lower risk of major amputation (study cohort: odds ratios [OR] 0.75, 95% CI 0.56-0.97, <i>p</i> = 0.03; matched cohort: OR 0.65, 95% 0.22, 0.55, <i>p</i> = 0.01) compared to those with continuous Medicaid coverage.</p><p><strong>Conclusions: </strong>Transitioning from Medicaid to commercial insurance may be associated with a lower risk of major amputation among Medicaid beneficiaries with DFUs.</p>","PeriodicalId":72798,"journal":{"name":"Diabetology","volume":"5 3","pages":"356-364"},"PeriodicalIF":2.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11525773/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142559626","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":"Diet Supplementation with Rosemary (Rosmarinus officinalis L.) Leaf Powder Exhibits an Antidiabetic Property in Streptozotocin-Induced Diabetic Male Wistar Rats","authors":"Zelipha N. Kabubii, J. Mbaria, P. M. Mathiu, John M. Wanjohi, Evans N. Nyaboga","doi":"10.3390/diabetology5010002","DOIUrl":"https://doi.org/10.3390/diabetology5010002","url":null,"abstract":"Diabetes mellitus is a metabolic disorder that has a high global health burden and causes high mortality and morbidity in humans. Medicinal herbs and plants offer a promising alternative to conventional therapies for the management of diabetes. Rosemary (Rosmarinus officinalis L.) is a traditional medicinal herb that has been used for the management of several diseases. Therefore, the present study investigates the antidiabetic properties of diets supplemented with R. officinalis leaf powder on streptozotocin-induced diabetic Wistar rats. First, the phytochemicals and 2,2-dephenyl-1-picrylhydrazyl (DPPH) free-radical scavenging activity of aqueous R. officinalis leaf extract were determined. Streptozotocin-induced diabetic male Wistar rats were fed a diet supplemented with R. officinalis leaf powder (ROP) at 3%, 6%, and 12%, respectively, for 6 weeks. Investigations of food intake, body weight, rat relative organ weights, blood glucose, lipid profiles, creatinine, bilirubin, alanine aminotransferase (ALT), and aspartate aminotransferase (AST) were estimated according to standard procedures. The results show that ROP aqueous extract contains significant amounts of phenolics, flavonoids, and tannins, which exhibit in vitro DPPH free-radical scavenging activity. Based on an in vivo study, ROP reduced blood glucose levels in streptozotocin-induced diabetic animals (p < 0.05). Dietary supplementation with ROP in diabetic rats significantly (p < 0.05) lowered ALT, AST, bilirubin, creatinine, total triglyceride (TG), total cholesterol (TC), and low-density lipoprotein (LDL) levels while increasing high-density lipoproteins (HDLs) when compared with the diabetic control group. Our findings demonstrate that a diet supplemented with R. officinalis leaf powder exhibits an antidiabetic potential with improved health outcomes, as demonstrated by the improved lipid and liver profile enzymes in our animal model.","PeriodicalId":72798,"journal":{"name":"Diabetology","volume":"75 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139387215","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":"Does the Efficacy of Semaglutide Treatment Differ between Low-Risk and High-Risk Subgroups of Patients with Type 2 Diabetes and Obesity Based on SCORE2, SCORE2-Diabetes, and ASCVD Calculations?","authors":"Martina Matovinović, Andrej Belančić, Juraj Jug, F. Mustač, Maja Sirovica, Mihovil Santini, Anja Bošnjaković, M. Lovrić, M. Lovrić Benčić","doi":"10.3390/diabetology5010003","DOIUrl":"https://doi.org/10.3390/diabetology5010003","url":null,"abstract":"Background: Diabetes is the primary contributor to cardiovascular disease risk, and when combined with obesity, it further underscores the significance of cardiovascular risk assessment. Methods: A retrospective study of 64 patients with type 2 diabetes (T2D) and obesity on once-weekly subcutaneous semaglutide stratified by cardiovascular risk categories determined using the SCORE2/SCORE2-OP, SCORE2-Diabetes, and ASCVD score calculations. We compare the differences between groups (ASCVD: low + borderline + intermediate versus high-risk group; SCORE2/SCORE2-OP: low + moderate versus high + very high-risk group and SCORE2-Diabetes: low + moderate versus high + very high-risk group) in terms of change from baseline in body mass index (BMI) and HbA1c and weight loss outcomes. Results: Patients in the high-risk group, according to ASCVD risk score, had statistically better results in weight loss ≥ 3%, ≥5%, and ≥10% compared to ASCVD low + borderline + intermediate and without difference regarding HbA1c. According to SCORE2/SCORE2-OP, the high + very high-risk group had statistically better HbA1c and weight loss results but only for ≥5% versus the low + moderate risk group. Based on the score SCORE2-Diabetes, the high + very high-risk group had statistically significant better results in lowering HbA1c and weight loss but only for ≥5% versus the low + moderate risk group. Conclusions: To the best of our knowledge, this study represents the initial investigation linking glycemic control and weight reduction outcomes in individuals with T2D and obesity treated with once-weekly semaglutide stratified by cardiovascular risk categories determined using the SCORE2/SCORE2-OP, SCORE2-Diabetes and ASCVD score calculations.","PeriodicalId":72798,"journal":{"name":"Diabetology","volume":"54 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139386732","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":"A Comparative Analysis of Machine Learning Models for the Detection of Undiagnosed Diabetes Patients","authors":"S. Cichosz, Clara Bender, Ole Hejlesen","doi":"10.3390/diabetology5010001","DOIUrl":"https://doi.org/10.3390/diabetology5010001","url":null,"abstract":"Introduction: Early detection of type 2 diabetes is essential for preventing long-term complications. However, screening the entire population for diabetes is not cost-effective, so identifying individuals at high risk for this disease is crucial. The aim of this study was to compare the performance of five diverse machine learning (ML) models in classifying undiagnosed diabetes using large heterogeneous datasets. Methods: We used machine learning data from several years of the National Health and Nutrition Examination Survey (NHANES) from 2005 to 2018 to identify people with undiagnosed diabetes. The dataset included 45,431 participants, and biochemical confirmation of glucose control (HbA1c) were used to identify undiagnosed diabetes. The predictors were based on simple and clinically obtainable variables, which could be feasible for prescreening for diabetes. We included five ML models for comparison: random forest, AdaBoost, RUSBoost, LogitBoost, and a neural network. Results: The prevalence of undiagnosed diabetes was 4%. For the classification of undiagnosed diabetes, the area under the ROC curve (AUC) values were between 0.776 and 0.806. The positive predictive values (PPVs) were between 0.083 and 0.091, the negative predictive values (NPVs) were between 0.984 and 0.99, and the sensitivities were between 0.742 and 0.871. Conclusion: We have demonstrated that several types of classification models can accurately classify undiagnosed diabetes from simple and clinically obtainable variables. These results suggest that the use of machine learning for prescreening for undiagnosed diabetes could be a useful tool in clinical practice.","PeriodicalId":72798,"journal":{"name":"Diabetology","volume":"24 21","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139388854","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}