JMIR Diabetes最新文献

{"title":"Machine Learning-Derived Prenatal Predictive Risk Model to Guide Intervention and Prevent the Progression of Gestational Diabetes Mellitus to Type 2 Diabetes: Prediction Model Development Study.","authors":"Mukkesh Kumar, Li Ting Ang, Cindy Ho, Shu E Soh, Kok Hian Tan, Jerry Kok Yen Chan, Keith M Godfrey, Shiao-Yng Chan, Yap Seng Chong, Johan G Eriksson, Mengling Feng, Neerja Karnani","doi":"10.2196/32366","DOIUrl":"10.2196/32366","url":null,"abstract":"<p><strong>Background: </strong>The increasing prevalence of gestational diabetes mellitus (GDM) is concerning as women with GDM are at high risk of type 2 diabetes (T2D) later in life. The magnitude of this risk highlights the importance of early intervention to prevent the progression of GDM to T2D. Rates of postpartum screening are suboptimal, often as low as 13% in Asian countries. The lack of preventive care through structured postpartum screening in several health care systems and low public awareness are key barriers to postpartum diabetes screening.</p><p><strong>Objective: </strong>In this study, we developed a machine learning model for early prediction of postpartum T2D following routine antenatal GDM screening. The early prediction of postpartum T2D during prenatal care would enable the implementation of effective strategies for diabetes prevention interventions. To our best knowledge, this is the first study that uses machine learning for postpartum T2D risk assessment in antenatal populations of Asian origin.</p><p><strong>Methods: </strong>Prospective multiethnic data (Chinese, Malay, and Indian ethnicities) from 561 pregnancies in Singapore's most deeply phenotyped mother-offspring cohort study-Growing Up in Singapore Towards healthy Outcomes-were used for predictive modeling. The feature variables included were demographics, medical or obstetric history, physical measures, lifestyle information, and GDM diagnosis. Shapley values were combined with CatBoost tree ensembles to perform feature selection. Our game theoretical approach for predictive analytics enables population subtyping and pattern discovery for data-driven precision care. The predictive models were trained using 4 machine learning algorithms: logistic regression, support vector machine, CatBoost gradient boosting, and artificial neural network. We used 5-fold stratified cross-validation to preserve the same proportion of T2D cases in each fold. Grid search pipelines were built to evaluate the best performing hyperparameters.</p><p><strong>Results: </strong>A high performance prediction model for postpartum T2D comprising of 2 midgestation features-midpregnancy BMI after gestational weight gain and diagnosis of GDM-was developed (BMI_GDM CatBoost model: AUC=0.86, 95% CI 0.72-0.99). Prepregnancy BMI alone was inadequate in predicting postpartum T2D risk (ppBMI CatBoost model: AUC=0.62, 95% CI 0.39-0.86). A 2-hour postprandial glucose test (BMI_2hour CatBoost model: AUC=0.86, 95% CI 0.76-0.96) showed a stronger postpartum T2D risk prediction effect compared to fasting glucose test (BMI_Fasting CatBoost model: AUC=0.76, 95% CI 0.61-0.91). The BMI_GDM model was also robust when using a modified 2-point International Association of the Diabetes and Pregnancy Study Groups (IADPSG) 2018 criteria for GDM diagnosis (BMI_GDM2 CatBoost model: AUC=0.84, 95% CI 0.72-0.97). Total gestational weight gain was inversely associated with postpartum T2D outcome, independent of prepregna","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"7 3","pages":"e32366"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9297138/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"40480526","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":"Accessibility and Openness to Diabetes Management Support With Mobile Phones: Survey Study of People With Type 1 Diabetes Using Advanced Diabetes Technologies.","authors":"Yu Kuei Lin,&nbsp;Caroline Richardson,&nbsp;Iulia Dobrin,&nbsp;Rodica Pop-Busui,&nbsp;Gretchen Piatt,&nbsp;John Piette","doi":"10.2196/36140","DOIUrl":"https://doi.org/10.2196/36140","url":null,"abstract":"<p><strong>Background: </strong>Little is known about the feasibility of mobile health (mHealth) support among people with type 1 diabetes (T1D) using advanced diabetes technologies including continuous glucose monitoring (CGM) systems and hybrid closed-loop insulin pumps (HCLs).</p><p><strong>Objective: </strong>This study aims to evaluate patient access and openness to receiving mHealth diabetes support in people with T1D using CGM systems or HCLs.</p><p><strong>Methods: </strong>We conducted a cross-sectional survey among patients with T1D using CGM systems or HCLs managed in an academic medical center. Participants reported information regarding their mobile device use; cellular call, SMS text message, or internet connectivity; and openness to various channels of mHealth communication (smartphone apps, SMS text messages, and interactive voice response [IVR] calls). Participants' demographic characteristics and CGM data were collected from medical records. The analyses focused on differences in openness to mHealth and mHealth communication channels across groups defined by demographic variables and measures of glycemic control.</p><p><strong>Results: </strong>Among all participants (N=310; female: n=198, 63.9%; mean age 45, SD 16 years), 98.1% (n=304) reported active cellphone use and 80% (n=248) were receptive to receiving mHealth support to improve glucose control. Among participants receptive to mHealth support, 98% (243/248) were willing to share CGM glucose data for mHealth diabetes self-care assistance. Most (176/248, 71%) were open to receiving messages via apps, 56% (139/248) were open to SMS text messages, and 12.1% (30/248) were open to IVR calls. Older participants were more likely to prefer SMS text messages (P=.009) and IVR calls (P=.03) than younger participants.</p><p><strong>Conclusions: </strong>Most people with T1D who use advanced diabetes technologies have access to cell phones and are receptive to receiving mHealth support to improve diabetes control.</p>","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"7 2","pages":"e36140"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9270702/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9575534","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":"Evaluating the Implementation of the GREAT4Diabetes WhatsApp Chatbot to Educate People With Type 2 Diabetes During the COVID-19 Pandemic: Convergent Mixed Methods Study.","authors":"Robert Mash, Darcelle Schouw, Alex Emilio Fischer","doi":"10.2196/37882","DOIUrl":"10.2196/37882","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;In South Africa, diabetes is a leading cause of morbidity and mortality, which was exacerbated during the COVID-19 pandemic. Most education and counseling activities were stopped during the lockdown, and the GREAT4Diabetes WhatsApp Chatbot was innovated to fill this gap.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to evaluate the implementation of the chatbot in Cape Town, South Africa, between May and October 2021.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Convergent mixed methods were used to evaluate the implementation outcomes: acceptability, adoption, appropriateness, feasibility, fidelity, cost, coverage, effects, and sustainability. Quantitative data were derived from the chatbot and analyzed using the SPSS. Qualitative data were collected from key informants and analyzed using the framework method assisted by Atlas-ti. The chatbot provided users with 16 voice messages and graphics in English, Afrikaans, or Xhosa. Messages focused on COVID-19 infection and self-management of type 2 diabetes.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The chatbot was adopted by the Metro Health Services to assist people with diabetes who had restricted health care during the lockdown and were at a higher risk of hospitalization and death from COVID-19 infection. The chatbot was disseminated via health care workers in primary care facilities and local nonprofit organizations and via local media and television. Two technical glitches interrupted the dissemination but did not substantially affect user behavior. Minor changes were made to the chatbot to improve its utility. Many patients had access to smartphones and were able to use the chatbot via WhatsApp. Overall, 8158 people connected with the chatbot and 4577 (56.1%) proceeded to listen to the messages, with 12.56% (575/4577) of them listening to all 16 messages, mostly within 32 days. The incremental setup costs were ZAR 255,000 (US $16,876) and operational costs over 6 months were ZAR 462,473 (US $30,607). More than 90% of the users who listened to each message found them useful. Of the 533 who completed the whole program, 351 (71.1%) said they changed their self-management a lot and 87.6% (369/421) were more confident. Most users changed their lifestyles in terms of diet (315/414, 76.1%) and physical activity (222/414, 53.6%). Health care workers also saw benefits to patients and recommended that the service continues. Sustainability of the chatbot will depend on the future policy of the provincial Department of Health toward mobile health and the willingness to contract with Aviro Health. There is the potential to go to scale and include other languages and chronic conditions.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The chatbot shows great potential to complement traditional health care approaches for people with diabetes and assist with more comprehensive patient education. Further research is needed to fully explore the patient's experience of the chatbot and evaluate its effectiveness","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":" ","pages":"e37882"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9236126/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44675468","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":"Smartphone Apps for Diabetes Medication Adherence: Systematic Review.","authors":"Sheikh Mohammed Shariful Islam,&nbsp;Vinaytosh Mishra,&nbsp;Muhammad Umer Siddiqui,&nbsp;Jeban Chandir Moses,&nbsp;Sasan Adibi,&nbsp;Lemai Nguyen,&nbsp;Nilmini Wickramasinghe","doi":"10.2196/33264","DOIUrl":"https://doi.org/10.2196/33264","url":null,"abstract":"<p><strong>Background: </strong>Diabetes is one of the leading noncommunicable chronic diseases globally. In people with diabetes, blood glucose levels need to be monitored regularly and managed adequately through healthy lifestyles and medications. However, various factors contribute to poor medication adherence. Smartphone apps can improve medication adherence in people with diabetes, but it is not clear which app features are most beneficial.</p><p><strong>Objective: </strong>This study aims to systematically review and evaluate high-quality apps for diabetes medication adherence, which are freely available to the public in Android and Apple app stores and present the technical features of the apps.</p><p><strong>Methods: </strong>We systematically searched Apple App Store and Google Play for apps that assist in diabetes medication adherence, using predefined selection criteria. We assessed apps using the Mobile App Rating Scale (MARS) and calculated the mean app-specific score (MASS) by taking the average of app-specific scores on 6 dimensions, namely, awareness, knowledge, attitudes, intention to change, help-seeking, and behavior change rated on a 5-point scale (1=strongly disagree and 5=strongly agree). We used the mean of the app's performance on these 6 dimensions to calculate the MASS. Apps that achieved a total MASS mean quality score greater than 4 out of 5 were considered to be of high quality in our study. We formulated a task-technology fit matrix to evaluate the apps for diabetes medication adherence.</p><p><strong>Results: </strong>We identified 8 high-quality apps (MASS score≥4) and presented the findings under 3 main categories: characteristics of the included apps, app features, and diabetes medication adherence. Our framework to evaluate smartphone apps in promoting diabetes medication adherence considered physiological factors influencing diabetes and app features. On evaluation, we observed that 25% of the apps promoted high adherence and another 25% of the apps promoted moderate adherence. Finally, we found that 50% of the apps provided low adherence to diabetes medication.</p><p><strong>Conclusions: </strong>Our findings show that almost half of the high-quality apps publicly available for free did not achieve high to moderate medication adherence. Our framework could have positive implications for the future design and development of apps for patients with diabetes. Additionally, apps need to be evaluated using a standardized framework, and only those promoting higher medication adherence should be prescribed for better health outcomes.</p>","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":" ","pages":"e33264"},"PeriodicalIF":0.0,"publicationDate":"2022-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9257622/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"40140288","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":"Informing a Randomized Control Trial in Rural Populations: Adaptation of a Diabetes Self-Management Education and Support Intervention","authors":"Tamara K. Oser, Linda Zittleman, K. Curcija, Bethany M. Kwan, Shawnecca Burke, Sindy Gonzalez, Kelsey Huss, Marilee Johnson, Norah Sanchez, J. Neuberger, E. Iacob, Juliana Simonetti, Michelle L. Litchman","doi":"10.2196/35664","DOIUrl":"https://doi.org/10.2196/35664","url":null,"abstract":"Background Over 34 million people in the United States have diabetes, with 1.5 million diagnosed every year. Diabetes self-management education and support (DSMES) is a crucial component of treatment to delay or prevent complications. Rural communities face many unique challenges in accessing DSMES, including geographic barriers and availability of DSMES programs that are culturally adapted to rural context. Objective Boot Camp Translation (BCT) is an established approach to community-based participatory research used to translate complex clinical and scientific information into concepts, messages, and materials that are understandable, meaningful, and relevant to community members and patients. This study aimed to utilize BCT to adapt an existing DSMES program for delivery in rural primary care for English- and Spanish-speaking people with diabetes. Methods The High Plains Research Network (HPRN) Community Advisory Council (C.A.C.) partnered with researchers at the University of Colorado and University of Utah to use BCT to aid in translating medical jargon and materials from an existing DSMES program, called “Diabetes One Day (D1D).” BCT consisted of 10 virtual meetings over a 6-month period among the C.A.C., which included 15 diverse community stakeholders. Both English-speaking and bilingual Spanish-English–speaking C.A.C. members were recruited to reflect the diversity of the rural communities in which the adapted program would be delivered. Results The BCT process guided adaptations to D1D for use in rural settings (R-D1D). R-D1D adaptations reflect both content and delivery to assure that the intervention is appropriate and likely to be accepted by rural English- and Spanish-speaking people with diabetes. Additionally, BCT informed the design of recruitment and program materials and identification of recruitment venues. During the BCT process, the importance of tailoring materials to reflect culture differences in English- and Spanish-speaking patients was identified. Conclusions BCT was an effective strategy for academic researchers to partner with rural community members to adapt an existing DSMES intervention for delivery in rural areas to both English- and Spanish-speaking patients with diabetes. Through BCT, adaptations to recruitment materials and methods, program content and delivery, and supplemental materials were developed. The need to culturally adapt Spanish materials with input from stakeholders rather than simply translate materials into Spanish was highlighted. The importance of increasing awareness of the connection between diabetes and depression or diabetes distress, adaptations to include local foods, and the importance of the relationship between people with diabetes and their primary care practices were identified.","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44029637","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":"Community Health Worker-Led mHealth-Enabled Diabetes Self-management Education and Support Intervention in Rural Latino Adults: Single-Arm Feasibility Trial.","authors":"Shiyu Li,&nbsp;Zenong Yin,&nbsp;Janna Lesser,&nbsp;Chengdong Li,&nbsp;Byeong Yeob Choi,&nbsp;Deborah Parra-Medina,&nbsp;Belinda Flores,&nbsp;Brittany Dennis,&nbsp;Jing Wang","doi":"10.2196/37534","DOIUrl":"https://doi.org/10.2196/37534","url":null,"abstract":"<p><strong>Background: </strong>Latinos living in rural South Texas have a higher prevalence of diabetes, but their access to diabetes self-management education and support (DSMES) is limited.</p><p><strong>Objective: </strong>We aimed to test the feasibility of a community health worker-led, mobile health (mHealth)-based DSMES intervention to reduce disparities in accessing DSMES in underserved rural Latino residents in South Texas.</p><p><strong>Methods: </strong>This 12-week, single-arm, pre-post trial was delivered by trained community health workers to 15 adults with type 2 diabetes. The intervention consisted of digital diabetes education, self-monitoring, a cloud-based connected platform, and community health worker support. Feasibility was evaluated as retention, actual intervention use, program satisfaction, and barriers to implementation. We also explored the intervention's effect on weight loss and hemoglobin A_1c (HbA_1c).</p><p><strong>Results: </strong>All 15 participants were Latino (mean age 61.87 years, SD 10.67; 9/15 female, 60%). The retention rate at posttest was 14 of 15 (93%). On average, the participants completed 37 of 42 (88%) digital diabetes education lessons with 8 participants completing all lessons. Participants spent 81/91 days (89%) step tracking, 71/91 days (78%) food logging, 43/91 days (47%) blood glucose self-monitoring, and 74/91 days (81%) weight self-monitoring. The level of program satisfaction was high. On average, participants lost 3.5 (SD 3.2) kg of body weight (P=.001), while HbA_1c level remained unchanged from baseline (6.91%, SD 1.28%) to posttest (7.04%, SD 1.66%; P=.668).</p><p><strong>Conclusions: </strong>A community health worker-led mHealth-based intervention was feasible and acceptable to improve access to DSMES services for Latino adults living in rural communities. Future randomized controlled trials are needed to test intervention efficacy on weight loss and glycemic control.</p>","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"7 2","pages":"e37534"},"PeriodicalIF":0.0,"publicationDate":"2022-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9153909/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9854371","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 the Digital Diabetes Questionnaire as a Clinical Tool in Routine Diabetes Care: Focus Group Discussions With Patients and Health Care Professionals","authors":"Maria Svedbo Engström, U. Johansson, J. Leksell, Ebba Linder, K. Eeg-Olofsson","doi":"10.2196/34561","DOIUrl":"https://doi.org/10.2196/34561","url":null,"abstract":"Background The Diabetes Questionnaire is a digital patient-reported outcome and experience measure for adults living with diabetes. The Diabetes Questionnaire is intended for use in routine clinical visits in diabetes care and to enable patient perspectives to be integrated into the Swedish National Diabetes Register. The Diabetes Questionnaire was developed on the basis of patients’ perspectives, and evidence for its measurement qualities has been demonstrated. Patients receive an invitation to complete the questionnaire before clinical visits, and the patient and health care professional (HCP) can discuss the findings, which are instantly displayed during the visit. Implementation processes for new tools in routine care need to be studied to understand the influence of contextual factors, the support needed, and how patients and HCPs experience clinical use. Objective The aim of this study was to describe patients’ and HCPs’ experiences of initiating the use of the digital Diabetes Questionnaire as a clinical tool in routine diabetes care, supported by a structured implementation strategy involving initial education, local facilitators, and regular follow-ups. Methods In this qualitative study, semistructured focus group discussions were conducted 12 months after the use of the Diabetes Questionnaire was initiated. Participants were diabetes specialist nurses and physicians (20 participants in 4 groups) at hospital-based outpatient clinics or primary health care clinics and adults with type 1 or type 2 diabetes (15 participants in 4 groups). The audiotaped transcripts were analyzed using inductive qualitative content analysis. Results The results revealed 2 main categories that integrated patients’ and HCPs’ experiences, which together formed an overarching theme: While implementation demands new approaches, the Diabetes Questionnaire provides a broader perspective. The first main category (The Diabetes Questionnaire supports person-centered clinical visits) comprised comments expressing that the digital Diabetes Questionnaire can initiate and encourage reflection in preparation for clinical visits, bring important topics to light during clinical visits, and broaden the scope of discussion by providing additional information. The second main category (The process of initiating the implementation of the Diabetes Questionnaire) comprised comments that described differences in engagement among HCPs and their managers, challenges of establishing new routines, experiences of support during implementation, thoughts about the Diabetes Questionnaire, need to change local administrative routines, and opportunities and concerns for continued use. Conclusions The Diabetes Questionnaire can broaden the scope of health data in routine diabetes care. While implementation demands new approaches, patients and HCPs saw potential positive impacts of using the questionnaire at both the individual and group levels. Our results can inform further development of imp","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47382819","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":"Evaluation of Self-care Activities and Quality of Life in Patients With Type 2 Diabetes Treated With Metformin Using the 2D Matrix Code of Outer Drug Packages as Patient Identifier: the DePRO Proof-of-Concept Observational Study","authors":"C. Mueller, Isabel Schauerte, Stephan Martin, V. Irrgang","doi":"10.2196/31832","DOIUrl":"https://doi.org/10.2196/31832","url":null,"abstract":"Background The use of digital technology to assess patients remotely can reduce clinical study costs. In the European Union, the 2D matrix code on prescription drug packaging serves as a unique identifier of a given package of medication, and thus, also of the patient receiving that medication. Scanning of the 2D matrix code may therefore allow remote patient authentication in clinical studies. Objective The aim of the DePRO study was to assess the feasibility of a fully digital data-capture workflow, the authentication of participants via drug packaging 2D matrix codes, in patients with type 2 diabetes mellitus (T2DM) who use metformin. The primary objective was to describe the self-care activities of these patients. Secondary objectives were to evaluate (1) the self-reported health status of these patients, (2) the association of self-care activities with demographics and disease characteristics, and (3) the usability of the my ePRO app. Methods DePRO was an observational, multicenter, cross-sectional, digital, and patient-driven study conducted in Germany from June to December 2020. Adult patients prescribed metformin were invited to participate via their pharmacist or a medication tracker app. Participants downloaded the my ePRO app onto their own mobile device, scanned the 2D matrix code on their metformin package for registration and authentication, and provided informed consent via an electronic form. They were then able to complete a study-specific questionnaire on demographics and clinical characteristics, the German version of the Summary of Diabetes Self-Care Activities measure (SDSCA-G), the Diabetes Treatment Satisfaction Questionnaire (DTSQ), and the EQ-5D-5L. The patients conducted the study without support from a health care professional. Statistical analyses were exploratory and descriptive. Results In total, 3219 patients were invited to participate. The proportion of patients giving consent was greater among those invited by pharmacists (19/217, 8.8%) than among those invited via the medication tracker app (13/3002, 0.4%). Of the 29 patients eligible for analysis, 28 (97%) completed all study questionnaires. Most of the patients (23/29, 79%) were aged <60 years, and 59% (17/29) were male. The patients spent a mean total of 3.5 (SD 1.3) days out of 7 days on self-care activities (SDSCA-G). Most patients (24/29, 83%) were satisfied to extremely satisfied with their current treatment (DTSQ). Events of perceived hyperglycemia or hypoglycemia were reported by 20 of 29 (69%) patients. The best possible health status (EQ-5D-5L) was reported by 18 of 28 (64%) patients. Age was positively correlated with time spent on general and specific diet (Spearman coefficient 0.390 and 0.434, respectively). Conclusions The DePRO study demonstrates the feasibility of fully digital authentication (via 2D matrix codes on drug packaging) and data capture in patients with T2DM. Personal invitations yielded higher recruitment rates than remote invitatio","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46062446","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":"Accuracy of the Standard GlucoNavii Mentor in Blood Glucose Monitoring According to International Organization for Standardization 15197:2013 Criteria","authors":"Heeyoung Hwang, L. Leonardi, A. Nicolucci","doi":"10.2196/20774","DOIUrl":"https://doi.org/10.2196/20774","url":null,"abstract":"This study was performed to assess the system accuracy of the blood glucose monitoring system SD GlucoNavii Mentor (SD Biosensor Inc, Korea). The study procedures were based on International Organization for Standardization 15197:2013, in that capillary blood samples from 100 participants’ fingertips were measured with three reagent system lots of the self-monitoring blood glucose system. Samples were collected for comparison measurements on a hexokinase-based glucose analyzer (Cobas Integra400 Plus, Roche Instrument Center, Switzerland). Glucose concentrations were distributed as required by International Organization for Standardization 15197. For each of the 100 evaluable samples, duplicate measurements were taken from three different reagent lots, for a total of 600 measurements. Overall, 98.3% (590/600) of individual measurement results (185/186, 99.5% for glucose values <100 mg/dl and 405/414, 97.8% for glucose values ≥100 mg/dl) were within ±15 mg/dl or ±15% of the corresponding comparison method results. All results (100%) fell into the consensus error grid zones A and B, indicating only clinically acceptable results. In conclusion, the blood glucose monitoring system SD GlucoNavii Mentor device fulfilled the system accuracy criteria of the International Organization for Standardization 15197, indicating measurement accuracy sufficient for diabetes therapy.","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"68431838","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":"Identifying Patients With Hypoglycemia Using Natural Language Processing: Systematic Literature Review.","authors":"Yaguang Zheng,&nbsp;Victoria Vaughan Dickson,&nbsp;Saul Blecker,&nbsp;Jason M Ng,&nbsp;Brynne Campbell Rice,&nbsp;Gail D'Eramo Melkus,&nbsp;Liat Shenkar,&nbsp;Marie Claire R Mortejo,&nbsp;Stephen B Johnson","doi":"10.2196/34681","DOIUrl":"https://doi.org/10.2196/34681","url":null,"abstract":"<p><strong>Background: </strong>Accurately identifying patients with hypoglycemia is key to preventing adverse events and mortality. Natural language processing (NLP), a form of artificial intelligence, uses computational algorithms to extract information from text data. NLP is a scalable, efficient, and quick method to extract hypoglycemia-related information when using electronic health record data sources from a large population.</p><p><strong>Objective: </strong>The objective of this systematic review was to synthesize the literature on the application of NLP to extract hypoglycemia from electronic health record clinical notes.</p><p><strong>Methods: </strong>Literature searches were conducted electronically in PubMed, Web of Science Core Collection, CINAHL (EBSCO), PsycINFO (Ovid), IEEE Xplore, Google Scholar, and ACL Anthology. Keywords included hypoglycemia, low blood glucose, NLP, and machine learning. Inclusion criteria included studies that applied NLP to identify hypoglycemia, reported the outcomes related to hypoglycemia, and were published in English as full papers.</p><p><strong>Results: </strong>This review (n=8 studies) revealed heterogeneity of the reported results related to hypoglycemia. Of the 8 included studies, 4 (50%) reported that the prevalence rate of any level of hypoglycemia was 3.4% to 46.2%. The use of NLP to analyze clinical notes improved the capture of undocumented or missed hypoglycemic events using International Classification of Diseases, Ninth Revision (ICD-9), and International Classification of Diseases, Tenth Revision (ICD-10), and laboratory testing. The combination of NLP and ICD-9 or ICD-10 codes significantly increased the identification of hypoglycemic events compared with individual methods; for example, the prevalence rates of hypoglycemia were 12.4% for International Classification of Diseases codes, 25.1% for an NLP algorithm, and 32.2% for combined algorithms. All the reviewed studies applied rule-based NLP algorithms to identify hypoglycemia.</p><p><strong>Conclusions: </strong>The findings provided evidence that the application of NLP to analyze clinical notes improved the capture of hypoglycemic events, particularly when combined with the ICD-9 or ICD-10 codes and laboratory testing.</p>","PeriodicalId":52371,"journal":{"name":"JMIR Diabetes","volume":"7 2","pages":"e34681"},"PeriodicalIF":0.0,"publicationDate":"2022-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9152713/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9492666","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}