Machine Learning-Driven Prediction of Comorbidities and Mortality in Adults With Type 1 Diabetes.

BACKGROUND: Comorbidities such as cardiovascular disease (CVD) and diabetic kidney disease (DKD) are major burdens of type 1 diabetes (T1D). Predicting people at high risk of developing comorbidities would enable early intervention. This study aimed to develop models incorporating socioeconomic status (SES) to predict CVD, DKD, and mortality in adults with T1D to improve early identification of comorbidities. METHODS: Nationwide Danish registry data were used. Logistic regression models were developed to predict the development of CVD, DKD, and mortality within five years of T1D diagnosis. Features included age, sex, personal income, and education. Performance was evaluated by five-fold cross-validation with area under the receiver operating characteristic curve (AUROC) and the precision-recall area under the curve (PR-AUC). The importance of SES was assessed from feature importance plots. RESULTS: Of the 6572 included adults (≥21 years) with T1D, 379 (6%) developed CVD, 668 (10%) developed DKD, and 921 (14%) died within the five-year follow-up. The AUROC (±SD) was 0.79 (±0.03) for CVD, 0.61 (±0.03) for DKD, and 0.87 (±0.01) for mortality. The PR-AUC was 0.18 (±0.01), 0.15 (±0.03), and 0.49 (±0.02), respectively. Based on feature importance plots, SES was the most important feature in the DKD model but had minimal impact on models for CVD and mortality. CONCLUSIONS: The developed models showed good performance for predicting CVD and mortality, suggesting they could help in the early identification of these outcomes in individuals with T1D. The importance of SES in individual prediction within diabetes remains uncertain.

Collaborative Care Interventions for Patients with Multimorbidity: Protocol for a Systematic Review and Meta-Analysis with Preliminary Results.

Collaborative care interventions have been proposed as a promising strategy for the management of patients with multimorbidity. This systematic review and meta-analysis aims to assess the effectiveness of collaborative care interventions for adult patients with multimorbidity. Furthermore, a meta-regression analysis is planned to determine if certain participant or intervention characteristics can explain variance in effect.

From Stability to Variability: Classification of Healthy Individuals, Prediabetes, and Type 2 Diabetes Using Glycemic Variability Indices from Continuous Glucose Monitoring Data.

Objective: This study aims to investigate the continuum of glucose control from normoglycemia to dysglycemia (HbA1c ≥ 5.7%/39 mmol/mol) using metrics derived from continuous glucose monitoring (CGM). In addition, we aim to develop a machine learning-based classification model to classify dysglycemia based on observed patterns. Methods: Data from five distinct studies, each featuring at least two days of CGM, were pooled. Participants included individuals classified as healthy, with prediabetes, or with type 2 diabetes mellitus (T2DM). Various CGM indices were extracted and compared across groups. The data set was split 70/30 for training and testing two classification models (XGBoost/Logistic Regression) to differentiate between prediabetes or dysglycemia and the healthy group. Results: The analysis included 836 participants (healthy: n = 282; prediabetes: n = 133; T2DM: n = 432). Across all CGM indices, a progressive shift was observed from the healthy group to those with diabetes (P < 0.001). Statistically significant differences (P < 0.01) were noted in mean glucose, time below range, time above 140 mg/dl, mobility, multiscale complexity index, and glycemic risk index when transitioning from health to prediabetes. The XGBoost models achieved the highest receiver operating characteristic area under the curve values on the test data set ranging from 0.91 [confidence interval (CI): 0.87-0.95] (prediabetes identification) to 0.97 [CI: 0.95-0.98] (dysglycemia identification). Conclusion: Our findings demonstrate a gradual deterioration of glucose homeostasis and increased glycemic variability across the spectrum from normo- to dysglycemia, as evidenced by CGM metrics. The performance of CGM-based indices in classifying healthy individuals and those with prediabetes and diabetes is promising.

Evaluating the Usability of a Telehealth System for People with COPD: A Cross Sectional Study.

Pulmonary Disease (COPD) exacerbations. However, the effect of telehealth for COPD remains uncertain, which may be due to a lack of attention to usability during the development of telehealth solutions. The aim was to evaluate the usability of a telehealth system for COPD using the Danish Telehealth Usability Questionnaire. A total of 96 people with COPD, who were already using a telehealth system consisting of weekly measurements of physiological parameters and symptom-related questionnaires, were included. The D-TUQ was used to assess the usability of the telehealth system. The overall experience with the usability of the telehealth system was mainly positive, but there was room for improvement.

Discordance Between Mealtimes Reported by Trial Participants with Type 2 Diabetes and Healthcare Professionals.

Healthy lifestyle behaviors are essential in the treatment of type 2 diabetes, and meal registration is therefore important. Manual meal registration is cumbersome and could be automated using continuous glucose monitoring (CGM). If such an algorithm is based on patient-reported meals, potential errors might be induced. Thus, the aim was to investigate potential errors in patient-reported mealtimes and the effect on automatic meal detection. Two healthcare professionals (HCPs) reported the mealtimes of the 18 included patients based on the patients' CGM data to assess the agreement between HCP- and patient-reported mealtimes. A developed meal detection algorithm based on detecting the post-prandial glucose response using cross-correlation was used to assess the impact of errors in patient-reported meals. The results showed poor disagreement between HCP- and patient-reported meals and that the meal detection algorithm had a moderately better performance on the HCP-reported meals. Therefore, the possibility of errors in patient-reported mealtimes should be considered in the development of meal detection algorithms. However, more research is needed to confirm the results of this study.

The Effectiveness of Collaborative Care Interventions for the Management of Patients With Multimorbidity: Protocol for a Systematic Review, Meta-Analysis, and Meta-Regression Analysis.

BACKGROUND: Collaborative care interventions have been proposed as a promising strategy to support patients with multimorbidity. Despite this, the effectiveness of collaborative care interventions requires further evaluation. Existing systematic reviews describing the effectiveness of collaborative care interventions in multimorbidity management tend to focus on specific interventions, patient subgroups, and settings. This necessitates a comprehensive review that will provide an overview of the effectiveness of collaborative care interventions for adult patients with multimorbidity. OBJECTIVE: This systematic review aims to systematically assess the effectiveness of collaborative care interventions in comparison to usual care concerning health-related quality of life (HRQoL), mental health, and mortality among adult patients with multimorbidity. METHODS: Randomized controlled trials evaluating collaborative care interventions designed for adult patients (18 years and older) with multimorbidity compared with usual care will be considered for inclusion in this review. HRQoL will be the primary outcome. Mortality and mental health outcomes such as rating scales for anxiety and depression will serve as secondary outcomes. The systematic search will be conducted in the CENTRAL, PubMed, CINAHL, and Embase databases. Additional reference and citation searches will be performed in Google Scholar, Web of Science, and Scopus. Data extraction will be comprehensive and include information about participant characteristics, study design, intervention details, and main outcomes. Included studies will be assessed for limitations according to the Cochrane Risk of Bias tool. Meta-analysis will be conducted to estimate the pooled effect size. Meta-regression or subgroup analysis will be undertaken to explore if certain factors can explain the variation in effect between studies, if feasible. The certainty of evidence will be evaluated using the GRADE (Grading of Recommendations Assessment, Development, and Evaluation) approach. RESULTS: The preliminary literature search was performed on February 16, 2024, and yielded 5255 unique records. A follow-up search will be performed across all databases before submission. The findings will be presented in forest plots, a summary of findings table, and in narrative format. This systematic review is expected to be completed by late 2024. CONCLUSIONS: This review will provide an overview of pooled estimates of treatment effects across HRQoL, mental health, and mortality from randomized controlled trials evaluating collaborative care interventions for adults with multimorbidity. Furthermore, the intention is to clarify the participant, intervention, or study characteristics that may influence the effect of the interventions. This review is expected to provide valuable insights for researchers, clinicians, and other decision-makers about the effectiveness of collaborative care interventions targeting adult patients with multimorbidity. TRIAL REGISTRATION: International Prospective Register of Systematic Reviews (PROSPERO) CRD42024512554; https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=512554. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/58296.

Intelligent Diabetes Telemonitoring for Patients on Insulin Therapy: A Randomized Controlled Trial Protocol.

Protocol for a three-arm randomized controlled trial investigating telemonitoring with decision support in insulin-treated people with type 2 diabetes.

Open Digital Health Workshops - A Model for Mutual Contact and Knowledge Exchange with the Local Community.

The increasing percentage of elderly in our society is challenging the health care system. To meet the challenge, we have implemented an experience-based master's programme in digital health care. The 3-yrs 90 ECTS programme consists of physical sessions of three days duration and weekly 2-3-hour digital lectures and bi-weekly supervisions. A main goal of the program has been to involve the students in relevant local and regional health problems as well as inviting health care personnel to participate in the planning of the study program, present relevant health problems and challenges and follow our open digital health workshops. In this way we have managed to create a stimulating learning environment for both students on further education and local and regional health care personnel.

Development of a Basal Insulin Titration System to Support Healthcare Providers in Treatment of People with Type 2 Diabetes: Preliminary Results.

The study aims to develop a system for insulin titration in type 2 diabetes to assist primary healthcare providers. Usability testing with end-users is ongoing.

Prediction of Poor Glycemic Control in Children with Type 1 Diabetes.

This study developed and validated a machine learning model for predicting glycemic control in children with type 1 diabetes at the time of diagnosis, revealing age at diagnosis as the most informative predictor.

Identifying Patterns in Long Term CGM and Insulin Data - An Explorative Study.

The increased utilization of continuous glucose monitors (CGM) and smart insulin pens (SIP) among people with type 2 diabetes generates significant health data. This study explored possible patterns in long term CGM and SIP data.

Detailed Insights into Basal Insulin Adherence in People with Type 2 Diabetes Using a Data-Driven Assessment Method.

INTRODUCTION: Basal insulin non-adherence is a challenge in people with type 2 diabetes (T2D). METHODS: Using injection data recorded by a connected insulin pen, we employed a novel three-step methodology to assess three aspects of adherence (overall adherence, adherence distribution, and dose deviation) in individuals with insulin-treated T2D undergoing telemonitoring. RESULTS: Among participants, 52% were considered overall adherent. However, deviations from the recommended dose were observed in all participants, with increased and reduced doses being the predominant forms of non-adherence. CONCLUSIONS: Our study underscores the prevalence of basal insulin dosing irregularities in individuals with insulin-treated T2D undergoing telemonitoring.

Usability Evaluation of a Web-Based Remote Patient Monitoring Application: An Ongoing Study.

This study aims to discover problems and user experiences in a new released version of Sleepiz web application using heuristic evaluation and eye-tracking retrospective think-aloud performed by domain experts and end users. The web application is designed to support healthcare professionals in decision-making and monitoring of elderly people diagnosed with chronic respiratory diseases. Identification of usability problems and user experiences might contribute to improve the platform and will be reported to the developers.

A telemonitoring intervention design for patients with poorly controlled type 2 diabetes: protocol for a feasibility study.

BACKGROUND: Maintaining optimal glycemic control in type 2 diabetes (T2D) is difficult. Telemedicine has the potential to support people with poorly regulated T2D in the achievement of glycemic control, especially if the telemedicine solution includes a telemonitoring component. However, the ideal telemonitoring design for people with T2D remains unclear. Therefore, the aim of this feasibility study is to evaluate the feasibility of two telemonitoring designs for people with non-insulin-dependent T2D with a goal of identifying the optimal telemonitoring intervention for a planned future large-scale randomized controlled trial. METHOD: This 3-month randomized feasibility study will be conducted in four municipalities in North Denmark starting in January 2024. There will be 15 participants from each municipality. Two different telemonitoring intervention designs will be tested. One intervention will include self-monitoring of blood glucose (SMBG) combined with sleep and mental health monitoring. The second intervention will include an identical setup but with the addition of blood pressure and activity monitoring. Two municipalities will be allocated to one intervention design, whereas the other two municipalities will be allocated to the second intervention design. Qualitative interviews with participants and clinicians will be conducted to gain insight into their experiences with and acceptance of the intervention designs and trial procedures (e.g., blood sampling and questionnaires). In addition, sources of differences in direct intervention costs between the two alternative interventions will be investigated. DISCUSSION: Telemonitoring has the potential to support people with diabetes in achieving glycemic control, but the existing evidence is inconsistent, and thus, the optimal design of interventions remains unclear. The results of this feasibility study are expected to produce relevant information about telemonitoring designs for people with T2D and help guide the design of future studies. A well-tested telemonitoring design is essential to ensure the quality of telemedicine initiatives, with goals of user acceptance and improved patient outcomes. TRIAL REGISTRATION: ClinicalTrials.gov, ID: NCT06134934 . Registered November 1, 2023. The feasibility trial has been approved (N-20230026) by the North Denmark Region Committee on Health Research Ethics (June 5, 2023).

Improving traumatic fracture detection on radiographs with artificial intelligence support: a multi-reader study.

Objectives: The aim of this study was to evaluate the diagnostic performance of nonspecialist readers with and without the use of an artificial intelligence (AI) support tool to detect traumatic fractures on radiographs of the appendicular skeleton. Methods: The design was a retrospective, fully crossed multi-reader, multi-case study on a balanced dataset of patients (≥2 years of age) with an AI tool as a diagnostic intervention. Fifteen readers assessed 340 radiographic exams, with and without the AI tool in 2 different sessions and the time spent was automatically recorded. Reference standard was established by 3 consultant radiologists. Sensitivity, specificity, and false positives per patient were calculated. Results: Patient-wise sensitivity increased from 72% to 80% (P < .05) and patient-wise specificity increased from 81% to 85% (P < .05) in exams aided by the AI tool compared to the unaided exams. The increase in sensitivity resulted in a relative reduction of missed fractures of 29%. The average rate of false positives per patient decreased from 0.16 to 0.14, corresponding to a relative reduction of 21%. There was no significant difference in average reading time spent per exam. The largest gain in fracture detection performance, with AI support, across all readers, was on nonobvious fractures with a significant increase in sensitivity of 11 percentage points (pp) (60%-71%). Conclusions: The diagnostic performance for detection of traumatic fractures on radiographs of the appendicular skeleton improved among nonspecialist readers tested AI fracture detection support tool showed an overall reader improvement in sensitivity and specificity when supported by an AI tool. Improvement was seen in both sensitivity and specificity without negatively affecting the interpretation time. Advances in knowledge: The division and analysis of obvious and nonobvious fractures are novel in AI reader comparison studies like this.

Detection of structural lesions of the sacroiliac joints in patients with spondyloarthritis: A comparison of T1-weighted 3D spoiled gradient echo MRI and MRI-based synthetic CT versus T1-weighted turbo spin echo MRI.

OBJECTIVES: To investigate the detection of erosion, sclerosis and ankylosis using 1 mm 3D T1-weighted spoiled gradient echo (T1w-GRE) MRI and 1 mm MRI-based synthetic CT (sCT), compared with conventional 4 mm T1w-TSE. MATERIALS AND METHODS: Prospective, cross-sectional study. Semi-coronal 4 mm T1w-TSE and axial T1w-GRE with 1.6 mm slice thickness and 0.8 mm spacing between overlapping slices were performed. The T1w-GRE images were processed into sCT images using a commercial deep learning algorithm, BoneMRI. Both were reconstructed into 1 mm semi-coronal images. T1w-TSE, T1w-GRE and sCT images were assessed independently by 3 expert and 4 non-expert readers for erosion, sclerosis and ankylosis. Cohen's kappa for inter-reader agreement, exact McNemar test for lesion frequencies and Wilcoxon signed-rank test for confidence in lesion detection were used. RESULTS: Nineteen patients with axial spondyloarthritis were evaluated. T1w-GRE increased inter-reader agreement for detecting erosion (kappa 0.42 vs 0.21 in non-experts), increased detection of erosion (57 vs 43 of 152 joint quadrants) and sclerosis (26 vs 17 of 152 joint quadrants) among experts, and increased reader confidence for scoring erosion and sclerosis. sCT increased inter-reader agreement for detecting sclerosis (kappa 0.69 vs 0.37 in experts) and ankylosis (0.71 vs 0.52 in non-experts), increased detection of sclerosis (34 vs 17 of 152 joint quadrants) and ankylosis (20 vs 13 of 76 joint halves) among experts, and increased reader confidence for scoring erosion, sclerosis and ankylosis. CONCLUSION: T1w-GRE and sCT increase sensitivity and reader confidence for the detection of erosion, sclerosis and ankylosis, compared with T1w-TSE. CLINICAL RELEVANCE STATEMENT: These methods improve the detection of sacroiliac joint structural lesions and might be a useful addition to SIJ MRI protocols both in routine clinical care and as structural outcome measures in clinical trials.

Adherence to newer second-line oral antidiabetic drugs among people with type 2 diabetes-A systematic review.

The adherence to oral antidiabetic drugs (OADs) among people with type 2 diabetes (T2D) is suboptimal. However, new OADs have been marketed within the last 10 years. As these new drugs differ in mechanism of action, treatment complexity, and side effects, they may influence adherence. Thus, the aim of this study was to assess the adherence to newer second-line OADs, defined as drugs marketed in 2012-2022, among people with T2D. A systematic review was performed in CINAHL, Cochrane Trials, Embase, PubMed, PsycINFO, and Scopus. Articles were included if they were original research of adherence to newer second-line OADs and reported objective adherence quantification. The quality of the articles was assessed using JBI's critical appraisal tools. The overall findings were reported according to the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines and summarized in a narrative synthesis. All seven included articles were European retrospective cohort studies investigating alogliptin, canagliflozin, dapagliflozin, empagliflozin, and unspecified types of SGLT2i. Treatment discontinuation and medication possession ratio (MPR) were the most frequently reported adherence quantification measures. Within the first 12 months of treatment, 29%-44% of subjects on SGLT2i discontinued the treatment. In terms of MPR, 61.7%-94.9% of subjects on either alogliptin, canagliflozin, dapagliflozin, empagliflozin or an unspecified SGLT2i were adherent. The two investigated adherence quantification measures, treatment discontinuation and MPR, suggest that adherence to the newer second-line OADs may be better than that of older OADs. However, a study directly comparing older and newer OADs should be done to verify this.

The Effectiveness of Digital Health Lifestyle Interventions on People With Prediabetes: Protocol for a Systematic Review, Meta-Analysis, and Meta-Regression.

BACKGROUND: There has been an increasing interest in the use of digital health lifestyle interventions for people with prediabetes, as these interventions may offer a scalable approach to preventing type 2 diabetes. Previous systematic reviews on digital health lifestyle interventions for people with prediabetes had limitations, such as a narrow focus on certain types of interventions, a lack of statistical pooling, and no broader subgroup analysis of intervention characteristics. The identified limitations observed in previous systematic reviews substantiate the necessity of conducting a comprehensive review to address these gaps within the field. This will enable a comprehensive understanding of the effectiveness of digital health lifestyle interventions for people with prediabetes. OBJECTIVE: The objective of this systematic review, meta-analysis, and meta-regression is to systematically investigate the effectiveness of digital health lifestyle interventions on prediabetes-related outcomes in comparison with any comparator without a digital component among adults with prediabetes. METHODS: This systematic review will include randomized controlled trials that investigate the effectiveness of digital health lifestyle interventions on adults (aged 18 years or older) with prediabetes and compare the digital interventions with nondigital interventions. The primary outcome will be change in body weight (kg). Secondary outcomes include, among others, change in glycemic status, markers of cardiometabolic health, feasibility outcomes, and incidence of type 2 diabetes. Embase, PubMed, CINAHL, and CENTRAL (Cochrane Central Register of Controlled Trials) will be systematically searched. The data items to be extracted include study characteristics, participant characteristics, intervention characteristics, and relevant outcomes. To estimate the overall effect size, a meta-analysis will be conducted using the mean difference. Additionally, if feasible, meta-regression on study, intervention, and participant characteristics will be performed. The Cochrane risk of bias tool will be applied to assess study quality, and the GRADE (Grading of Recommendations Assessment, Development and Evaluation) approach will be used to assess the certainty of evidence. RESULTS: The results are projected to yield an overall estimate of the effectiveness of digital health lifestyle interventions on adults with prediabetes and elucidate the characteristics that contribute to their effectiveness. CONCLUSIONS: The insights gained from this study may help clarify the potential of digital health lifestyle interventions for people with prediabetes and guide the decision-making regarding future intervention components. TRIAL REGISTRATION: PROSPERO CRD42023426919; http://tinyurl.com/d3enrw9j. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/50340.

Diabetes Management Support in Preschool and Primary School: A Qualitative Ideation Study Presenting Recommendations for Improved Communicative Practice.

Diabetes care in institutional settings is a significant challenge that affects the whole family as well as care workers and teachers. The present study is the ideation part of a rigorous development process in the KIds with Diabetes in School (KIDS) project. We have previously conducted a thorough three-part needs assessment in which we explored the problem area from the viewpoints of (1) municipal administrative staff, (2) preschool and school staff and (3) families. Based on the identified needs and to a great extent on the contents and shortcomings of existing guidelines, the objective of the present study is to explore and develop possible solutions and recommendations for addressing the challenges and problems. To meet this objective, we held comprehensive multistakeholder participatory workshops in each of the five Danish regions. Five main themes with multiple subthemes were identified as areas to be addressed: (1) training and knowledge, (2) communication and collaboration, (3) the designated contact/support person, (4) national guidelines, and (5) the Diabetes Coordinator. Our findings demonstrate that communicative structures and dynamics are at the very heart of the identified problems and challenges and that the possible solutions should revolve around improving existing structures and highlighting the importance of constantly working on understanding and developing communication strategies. We propose a set of recommendations for practice based on these communicative needs.

A Three-Step Data-Driven Methodology to Assess Adherence to Basal Insulin Therapy in Patients With Insulin-Treated Type 2 Diabetes.

BACKGROUND: While health care providers (HCPs) are generally aware of the challenges concerning insulin adherence in adults with insulin-treated type 2 diabetes (T2D), data guiding identification of insulin nonadherence and understanding of injection patterns have been limited. Hence, the aim of this study was to examine detailed injection data and provide methods for assessing different aspects of basal insulin adherence. METHOD: Basal insulin data recorded by a connected insulin pen and prescribed doses were collected from 103 insulin-treated patients (aged ≥18 years) with T2D from an ongoing clinical trial (NCT04981808). We categorized the data and analyzed distributions of correct doses, increased doses, reduced doses, and missed doses to quantify adherence. We developed a three-step model evaluating three aspects of adherence (overall adherence, adherence distribution, and dose deviation) offering HCPs a comprehensive assessment approach. RESULTS: We used data from a connected insulin pen to exemplify the use of the three-step model to evaluate overall, adherence, adherence distribution, and dose deviation using patient cases. CONCLUSION: The methodology provides HCPs with detailed access to previously limited clinical data on insulin administration, making it possible to identify specific nonadherence behavior which will guide patient-HCP discussions and potentially provide valuable insights for tailoring the most appropriate forms of support.