Telemedicine as a tool for bridging geographical inequity: insights in geospatial interactions from a study on chronic heart failure patients.

INTRODUCTION: Chronic heart failure patients experience large disparities in quality of and access to treatment, with rural populations receiving lower levels of care. Telemonitoring of patients is increasingly being used as an important tool for improving patient management and care and might reduce geographical inequities in healthcare. METHODS: We investigate the presence and magnitude of a geospatial interaction effect on the health benefit of a supplementary telemedicine intervention, by analyzing the relationship between distance to regular place of treatment and the benefit of telemedicine in a secondary analysis of data from a previously conducted RCT. We use change in EQ5D health status, SF-36 Physical component score and SF-36 Mental component score as the outcomes. In the unadjusted analysis, intervention group and distance group and the interaction term are included as the independent variables, in the adjusted analysis, multiple socioeconomic and health related variables are included to account for potential confounders. RESULTS: We find evidence of a significant interaction between the effects of telemedicine and long distance to treatment for change in EQ5D health status (unadjusted: p = 0.016, adjusted p = 0.009) and unadjusted but not adjusted mental component score (unadjusted: p = 0.013, adjusted p = 0.0728), for the change in physical component score the interaction term was not significant (unadjusted: p = 0.118, adjusted p = 0.092). CONCLUSION: In our study we find that supplementary telemedicine is likely to reduce the health access inequities associated with geographical distance for chronic heart failure patients. However, our sample size was modest and further research is needed to confirm these findings.

Risk of pancreatic cancer in people with new-onset diabetes: A Danish nationwide population-based cohort study.

BACKGROUND: New onset diabetes (NOD) in people 50 years or older may indicate underlying pancreatic ductal adenocarcinoma (PDAC). The cumulative incidence of PDAC among people with NOD remains uncertain on a population-based level. METHODS: This was a nationwide population-based retrospective cohort study based on the Danish national health registries. We investigated the 3-year cumulative incidence of PDAC in people 50 years or older with NOD. We further characterised people with pancreatic cancer-related diabetes (PCRD) in relation to demographic and clinical characteristics, including trajectories of routine biochemical parameters, using people with type 2 diabetes (T2D) as a comparator group. RESULTS: During a 21-year observation period, we identified 353,970 people with NOD. Among them, 2105 people were subsequently diagnosed with pancreatic cancer within 3 years (0.59%, 95% CI [0.57-0.62%]). People with PCRD were older than people with T2D at diabetes diagnosis (median age 70.9 vs. 66.0 years (P < 0.001) and had a higher burden of comorbidities (P = 0.007) and more prescriptions of medications used to treat cardiovascular diseases (all P < 0.001). Distinct trajectories of HbA1c and plasma triglycerides were observed in PCRD vs. T2D, with group differences observed for up to three years prior to NOD diagnosis for HbA1c and up to two years for plasma triglyceride levels. CONCLUSIONS: The 3-year cumulative incidence of PDAC is approximately 0.6% among people 50 years or older with NOD in a nationwide population-based setting. Compared to T2D, people with PCRD are characterised by distinct demographic and clinical profiles, including distinctive trajectories of plasma HbA1c and triglyceride levels.

Implementation of a coagulation component into a phosphate kinetics model in haemodialysis therapy: A tool for detection of clotting problems?

A coagulation component should be considered in phosphate kinetics modelling because intradialytic coagulation of the extracorporeal circuit and dialyser might reduce phosphate removal in haemodialysis. Thus, the objective of this study was to add and evaluate coagulation as an individual linear clearance reduction component to a promising three-compartment model assuming progressive intradialytic clotting. The model was modified and validated on intradialytic plasma and dialysate phosphate samples from 12 haemodialysis patients collected during two treatments (HD1 and HD2) at a Danish hospital ward. The most suitable clearance reduction in each treatment was identified by minimizing the root mean square error (RMSE). The model simulations with and without clearance reduction were compared based on RMSE and coefficient of determination (R2 ) values. Improvements were found for 17 of the 24 model simulations when clearance reduction was added to the model. The slopes of the clearance reduction were in the range of 0.011-0.632/h. Three improvements were found to be statistically significant (|observed z value| > 1.96). A very significant correlation (R2  = 0.708) between the slopes for HD1 and HD2 was found. Adding the clearance reduction component to the model seems promising in phosphate kinetics modelling and might be explained, at least in part, by intradialytic coagulation. In future studies, the model might be developed further to serve as a potentially useful tool for the quantitative detection of clotting problems in haemodialysis. NEW FINDINGS: What is the central question of this study? The aim was to add an intradialytic coagulation component to a modified version of a promising three-compartment phosphate kinetics model. The hypothesis was that circuit and dialyser clotting can be modelled by an individual linear phosphate clearance reduction component during haemodialysis treatment. What is the main finding and its importance? Improvements were found for 17 of 24 model simulations when clearance reduction was added to the model. Thus, the kinetics model seems promising and could be a useful tool for the quantitative detection of clotting problems in haemodialysis patients.

Patient-Reported Outcomes for Function and Pain in Total Knee Arthroplasty Patients.

BACKGROUND: Some patients undergoing total knee arthroplasty successfully manage their condition postoperatively, whereas others encounter challenges in regaining function and controlling pain during recovery at home. OBJECTIVE: The aim of this study was to use traditional statistics and machine learning to develop prediction models that identify patients likely to have increased care needs related to managing function and pain following total knee arthroplasty. METHODS: This study included 201 patients. Outcomes were changes between baseline and follow-up in the functional and pain subcomponents of the Oxford Knee Score. Both classification and regression modeling were applied. Twenty-one predictors were included. Tenfold cross-validation was used, and the regression models were evaluated based on root-mean-square error, mean absolute error, and coefficient of determination. Classification models were evaluated based on the area under the receiver operating curve, sensitivity, and specificity. RESULTS: In classification modeling, random forest and stochastic gradient boosting provided the best overall metrics for model performance. A support vector machine and a stochastic gradient boosting machine in regression modeling provided the best predictive performance. The models performed better in predicting challenges related to function compared to challenges related to pain. DISCUSSION: There is valuable predictive information in the data routinely collected for patients undergoing total knee arthroplasty. The developed models may predict patients who are likely to have enhanced care needs regarding function and pain management. Improvements are needed before the models can be implemented in routine clinical practice.

Epidemiology of hypoglycaemic episodes leading to hospitalisations in Denmark in 1998-2018.

AIMS/HYPOTHESIS: We aimed to investigate the nationwide trends in incidence and associated risk factors, with focus on blood glucose-lowering medication, for the first hypoglycaemic episode leading to hospitalisation in Denmark among people with type 1 and 2 diabetes mellitus. METHODS: A cohort study of all people with diabetes from 1977 to 2018 experiencing hypoglycaemic episodes leading to hospitalisation in 1998-2018 was established. Data were extracted from the Danish National Patient Registry. Trends in incidence rates were investigated with Poisson regression models and linear regressions, and risk factors were investigated with Cox proportional hazards models. RESULTS: A total of 66,438 hypoglycaemic episodes leading to hospitalisation in 1998-2018 was investigated among 641,402 people with type 1 (mean ± SD age 37 ± 22 years) and type 2 diabetes (mean ± SD age 61 ± 17 years). Between 2003 and 2018, the incidence rate fell by 66% for type 1 diabetes (incidence rate ratio [IRR] 0.34 [95% CI 0.31, 0.36], p < 0.0001) and 61% for type 2 diabetes (IRR 0.39 [95% CI 0.36, 0.42], p < 0.0001). With respect to hypoglycaemic episodes, insulin glargine (HR 1.20 [95% CI 1.05, 1.36], p = 0.0059), insulin detemir (HR 1.18 [95% CI 1.04, 1.32], p = 0.0077) and insulin degludec (HR 1.04 [95% CI 0.81,1.33], p = 0.7706) seemed safer than human insulin (long-acting insulin HR 1.38 [95% CI 1.25, 1.52], p < 0.0001; combination insulins HR 1.84 [95% CI 1.65, 2.05], p < 0.0001) and, especially, sodium-glucose cotransporter 2 inhibitors (HR 0.43 [95% CI 0.33, 0.56], p < 0.0001), glucagon-like peptide 1 receptor agonists (HR 0.51 [95% CI 0.44, 0.58], p < 0.0001) and dipeptidyl peptidase 4 inhibitors (HR 0.44 [95% CI 0.38, 0.49], p < 0.0001) seemed safer than sulfonylureas (HR 2.27 [95% CI 2.18, 2.37], p < 0.0001). CONCLUSIONS/INTERPRETATION: Incidence rates of hypoglycaemic episodes leading to hospitalisation are declining in Denmark, and the advent of new treatment alternatives may play a significant role in this decline. From a safety perspective, these findings are important and should be considered by clinicians when assessing treatment options for patients.

Reablement professionals' perspectives on client characteristics and factors associated with successful home-based reablement: a qualitative study.

BACKGROUND: To understand what is needed to achieve a successful Danish home-based reablement service from the perspective of reablement professionals. METHODS: Semi-structured interviews and observations were conducted with nine professionals within a municipal visitation unit in the Northern Denmark Region. Thematic analysis was used to analyze the interviews. RESULTS: Four major themes emerged during this study: "Heterogeneity of clients and mixed attitudes towards the reablement intervention", "Shared understanding and acknowledging the need for help as the first step in reablement", "Commitment and motivation are essential for successful reablement", and "Homecare helpers as most important team players". The findings indicate that the clients had both mixed characteristics and attitudes about participating in the reablement intervention. Essential factors for successful reablement included a shared understanding of the reablement intervention, commitment, and motivation in terms of client involvement and staff group collaboration. CONCLUSIONS: Shared understanding of the reablement intervention, commitment, and motivation was found to be essential factors and the driving forces in relation to successful reablement.

Risk of major cardiovascular events, severe hypoglycaemia, and all-cause mortality for users of insulin degludec versus insulin glargine U100-A Danish cohort study.

AIMS: Real-world evidence of the safety of insulin degludec compared with insulin glargine U100 is sparse. This study sought to investigate the risk of major cardiovascular events, severe hypoglycaemia, and all-cause mortality after initiation of degludec or glargine U100 in the population of Denmark. MATERIALS AND METHODS: All Danish people with diabetes initiating treatment on degludec (n=5159) or glargine (n=4041) in 2016 to 2017 were included in the study. The effect of insulin treatment on the endpoints of major cardiovascular events, severe hypoglycaemia, and all-cause mortality was analysed with Cox proportional hazard models. The models were adjusted for age, sex, diabetes duration, diabetes type, highest completed education, and annual income. The model of severe hypoglycaemia was also adjusted for severe hypoglycaemia prior to baseline. The model of mortality was also adjusted for history of alcohol abuse, use of antidepressants, use of opioids, and use of anxiolytics. Lastly, the models of major cardiovascular events and mortality were also adjusted for Charlson comorbidity index. RESULTS: Use of degludec resulted in an almost twofold decrease in risk of death (hazard rate [HR]: 0.54, 95% CI: 0.44-0.65) compared with use of glargine. No statistically significant risk changes were found for major cardiovascular events (HR: 0.86, 95% CI: 0.62-1.19) and severe hypoglycaemia (HR: 1.13, 95% CI: 0.66-1.93). The proportion of cause of death due to malignant neoplasm of pancreas was almost doubled for glargine compared with degludec. CONCLUSIONS: These results indicate that insulin degludec has a safer profile with respect to all-cause mortality as compared with insulin glargine U100.

Association of insulin regimens with severe hypoglycaemia in patients with type 1 diabetes: A Danish case-control study.

AIMS: To evaluate the risk of severe hypoglycaemia for patients with Type 1 diabetes (T1D) when exposed to insulin regimens including human insulin only or insulin analogues. METHODS: A total of 19 896 patients with T1D were extracted from the Danish National Patient Register. Of these, 6379 T1D patients experiencing 1 of more severe hypoglycaemic episodes (total of 17 242 episodes) were matched 1:1 with T1D patients without severe hypoglycaemia. A logistic regression model with last insulin regimen used as exposure was constructed to analyse the effect on severe hypoglycaemia. RESULTS: People on a basal-bolus regimen with insulin analogues had a reduced risk of severe hypoglycaemia of 39% (odds ratio: 0.61, 95% confidence interval: 0.54-0.68) compared to patients on a basal-bolus human insulin only regimen. Furthermore, patients on a premixed regimen containing an insulin analogue had a 58% (odds ratio: 0.42, 95% confidence interval: 0.36-0.49) reduced risk of severe hypoglycaemia compared to patients on premixed human insulin only. CONCLUSION: This study indicates that use of a basal-bolus insulin regimen with an insulin analogue is safer with respect to severe hypoglycaemia in patients with T1D than the use of a basal-bolus human insulin only regimen.

Phosphate Kinetic Models in Hemodialysis: A Systematic Review.

BACKGROUND: Understanding phosphate kinetics in dialysis patients is important for the prevention of hyperphosphatemia and related complications. One approach to gain new insights into phosphate behavior is physiologic modeling. Various models that describe and quantify intra- and/or interdialytic phosphate kinetics have been proposed, but there is a dearth of comprehensive comparisons of the available models. The objective of this analysis was to provide a systematic review of existing published models of phosphate metabolism in the setting of maintenance hemodialysis therapy. STUDY DESIGN: Systematic review. SETTING & POPULATION: Hemodialysis patients. SELECTION CRITERIA FOR STUDIES: Studies published in peer-reviewed journals in English about phosphate kinetic modeling in the setting of hemodialysis therapy. PREDICTOR: Modeling equations from specific reviewed studies. OUTCOMES: Changes in plasma phosphate or serum phosphate concentrations. RESULTS: Of 1,964 nonduplicate studies evaluated, 11 were included, comprising 9 different phosphate models with 1-, 2-, 3-, or 4-compartment assumptions. Between 2 and 11 model parameters were included in the models studied. Quality scores of the studies using the Newcastle-Ottawa Scale ranged from 2 to 11 (scale, 0-14). 2 studies were considered low quality, 6 were considered medium quality, and 3 were considered high quality. LIMITATIONS: Only English-language studies were included. CONCLUSIONS: Many parameters known to influence phosphate balance are not included in existing phosphate models that do not fully reflect the physiology of phosphate metabolism in the setting of hemodialysis. Moreover, models have not been sufficiently validated for their use as a tool to simulate phosphate kinetics in hemodialysis therapy.

Probing community nurses' professional basis: a situational case study in diabetic foot ulcer treatment.

Complicated and long-lasting wound care of diabetic foot ulcers are moving from specialists in wound care at hospitals towards community nurses without specialist diabetic foot ulcer wound care knowledge. The aim of the study is to elucidate community nurses' professional basis for treating diabetic foot ulcers. A situational case study design was adopted in an archetypical Danish community nursing setting. Experience is a crucial component in the community nurses' professional basis for treating diabetic foot ulcers. Peer-to-peer training is the prevailing way to learn about diabetic foot ulcer, however, this contributes to the risk of low evidence-based practice. Finally, a frequent behaviour among the community nurses is to consult colleagues before treating the diabetic foot ulcers.

Interaction between functional health literacy and telehomecare: Short-term effects from a randomized trial.

This study was conducted as part of a randomized, controlled trial, and explored whether the introduction of a Danish telehomecare intervention, referred to as 'the Telekit', and its associated educational components affect functional health literacy. The study sample consisted of 60 chronic obstructive pulmonary disease patients in the intervention group who received the Telekit, and 56 in the control group; all participants were collected from the large-scale, randomized TeleCare North trial by consecutive sampling. To avoid recall bias, the design did not include a baseline measurement, comparing instead the post-intervention measurements between the intervention and control groups. First, the comparability of the two groups was determined, and statistically significant differences in their functional health literacy scores were examined using an independent t-test. Furthermore, the associations between functional health literacy and both groups were tested using multiple regression analysis. No statistically significant difference was observed between the intervention and control groups, suggesting that the introduction of the Telekit and its associated educational components has no effect on functional health literacy. However, further research should be conducted using a larger sample.

HEALTH PROFESSIONALS' USER EXPERIENCE OF THE INTELLIGENT BED IN PATIENTS' HOMES.

BACKGROUND: The intelligent bed is a medical bed with several home healthcare functions. It includes, among others, an "out of bed" detector, a moisture detector, and a catheter bag detector. The design purpose of the intelligent bed is to assist patients in their daily living, facilitate the work of clinical staff, and improves the quality of care. The aim of this sub-study of the iCare project was to explore how health professionals (HPs) experience and use the intelligent bed in patients' homes. METHODS: The overall research design is inspired by case study methodology. A triangulation of data collection techniques has been used: log book, documentation study, participant observations (n = 45 hr), and qualitative interviews (n = 23). The data have been analyzed by means of Nvivo 9.0. FINDINGS: We identified several themes: HP transformation from passive technology recipient to innovator; individualized care; work flow redesign; and sensor technology intruding on patient privacy. CONCLUSIONS: It is suggested that functions of the intelligent bed can result in more individualized care, workflow redesign, and time savings for the health professionals in caring for elderly patients. However, the technology intruded on patients' privacy.

Validation of the Test of Functional Health Literacy in Adults in a Danish population.

OBJECTIVE: To describe how the original American full-length version of the Test of Functional Health Literacy in Adults (TOFHLA) was translated and adapted for use in the Danish setting and culture. A reliable Danish version of the TOFHLA was created and pretested using patients diagnosed with chronic obstructive pulmonary disease (COPD) as case group. METHODS: Forty-two patients with COPD completed the Danish TOFHLA and participated in a face-to-face interview concerning their basic demographics. Statistical analyses were conducted to explore the demographic data provided by the participants and to determine the internal consistency and reliability of the Danish TOFHLA. RESULTS: The mean age of sample was 68.7 years (range 34-86). The face validity, internal consistency and item to scale correlations of the Danish TOFHLA were determined and found to fulfil well-established criteria; on this basis, we found the reliability and consistency of the Danish TOFHLA to be satisfying. CONCLUSION: The Danish TOFHLA is now ready for application in future research projects, which test levels of functional health literacy in an elderly Danish population at risk of chronic diseases. The evolvement in the measurement of health literacy is still ongoing, as there is a need to refine existing methods. Until recently, there has been a total lack of instruments for assessing health literacy in Scandinavia; it is hoped that this development of the Danish TOFHLA will promote further research within the field of health literacy in Scandinavia and other European countries.

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.

Identification of individuals with diabetes who are eligible for continuous glucose monitoring forecasting.

BACKGROUND AND OBJECTIVES: Predicting glucose levels in individuals with diabetes offers potential improvements in glucose control. However, not all patients exhibit predictable glucose dynamics, which may lead to ineffective treatment strategies. We sought to investigate the efficacy of a 7-day blinded screening test in identifying diabetes patients suitable for glucose forecasting. METHODS: Participants with type 1 diabetes (T1D) were stratified into high and low initial error groups based on screening results (eligible and non-eligible). Long-term glucose predictions (30/60 min lead time) were evaluated among 334 individuals who underwent continuous glucose monitoring (CGM) over a total of 64,460,560 min. RESULTS: A strong correlation was observed between screening accuracy and long-term mean absolute relative difference (MARD) (0.661-0.736; p < 0.001), suggesting significant predictability between screening and long-term errors. Group analysis revealed a notable reduction in predictions falling within zone D of the Clark Error Grid by a factor of three and in zone C by a factor of two. CONCLUSIONS: The identification of eligible patients for glucose prediction through screening represents a practical and effective strategy. Implementation of this approach could lead to a decrease in adverse glucose predictions.

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.

Application of Machine Learning in Multimorbidity Research: Protocol for a Scoping Review.

BACKGROUND: Multimorbidity, defined as the coexistence of multiple chronic conditions, poses significant challenges to health care systems on a global scale. It is associated with increased mortality, reduced quality of life, and increased health care costs. The burden of multimorbidity is expected to worsen if no effective intervention is taken. Machine learning has the potential to assist in addressing these challenges since it offers advanced analysis and decision-making capabilities, such as disease prediction, treatment development, and clinical strategies. OBJECTIVE: This paper represents the protocol of a scoping review that aims to identify and explore the current literature concerning the use of machine learning for patients with multimorbidity. More precisely, the objective is to recognize various machine learning models, the patient groups involved, features considered, types of input data, the maturity of the machine learning algorithms, and the outcomes from these machine learning models. METHODS: The scoping review will be based on the guidelines of the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews). Five databases (PubMed, Embase, IEEE, Web of Science, and Scopus) are chosen to conduct a literature search. Two reviewers will independently screen the titles, abstracts, and full texts of identified studies based on predefined eligibility criteria. Covidence (Veritas Health Innovation Ltd) will be used as a tool for managing and screening papers. Only studies that examine more than 1 chronic disease or individuals with a single chronic condition at risk of developing another will be included in the scoping review. Data from the included studies will be collected using Microsoft Excel (Microsoft Corp). The focus of the data extraction will be on bibliographical information, objectives, study populations, types of input data, types of algorithm, performance, maturity of the algorithms, and outcome. RESULTS: The screening process will be presented in a PRISMA-ScR flow diagram. The findings of the scoping review will be conveyed through a narrative synthesis. Additionally, data extracted from the studies will be presented in more comprehensive formats, such as charts or tables. The results will be presented in a forthcoming scoping review, which will be published in a peer-reviewed journal. CONCLUSIONS: To our knowledge, this may be the first scoping review to investigate the use of machine learning in multimorbidity research. The goal of the scoping review is to summarize the field of literature on machine learning in patients with multiple chronic conditions, highlight different approaches, and potentially discover research gaps. The results will offer insights for future research within this field, contributing to developments that can enhance patient outcomes. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/53761.

Prediction of pancreatic cancer risk in patients with new-onset diabetes using a machine learning approach based on routine biochemical parameters.

OBJECTIVE: To develop a machine-learning model that can predict the risk of pancreatic ductal adenocarcinoma (PDAC) in people with new-onset diabetes (NOD). METHODS: From a population-based sample of individuals with NOD aged >50 years, patients with pancreatic cancer-related diabetes (PCRD), defined as NOD followed by a PDAC diagnosis within 3 years, were included (n = 716). These PCRD patients were randomly matched in a 1:1 ratio with individuals having NOD. Data from Danish national health registries were used to develop a random forest model to distinguish PCRD from Type 2 diabetes. The model was based on age, gender, and parameters derived from feature engineering on trajectories of routine biochemical variables. Model performance was evaluated using receiver operating characteristic curves (ROC) and relative risk scores. RESULTS: The most discriminative model included 20 features and achieved a ROC-AUC of 0.78 (CI:0.75-0.83). Compared to the general NOD population, the relative risk for PCRD was 20-fold increase for the 1 % of patients predicted by the model to have the highest cancer risk (3-year cancer risk of 12 % and sensitivity of 20 %). Age was the most discriminative single feature, followed by the rate of change in haemoglobin A1c and the latest plasma triglyceride level. When the prediction model was restricted to patients with PDAC diagnosed six months after diabetes diagnosis, the ROC-AUC was 0.74 (CI:0.69-0.79). CONCLUSION: In a population-based setting, a machine-learning model utilising information on age, sex and trajectories of routine biochemical variables demonstrated good discriminative ability between PCRD and Type 2 diabetes.

Prediction of People With Type 2 Diabetes Not Achieving HbA1c Target After Initiation of Fast-Acting Insulin Therapy: Using Machine Learning Framework on Clinical Trial Data.

BACKGROUND AND AIMS: Glycemic control is crucial for people with type 2 diabetes. However, only about half achieve the advocated HbA1c target of ≤7%. Identifying those who will probably struggle to reach this target may be valuable as they require additional support. Thus, the aim of this study was to develop a model to predict people with type 2 diabetes not achieving HbA1c target after initiating fast-acting insulin. METHODS: Data from a randomized controlled trial (NCT01819129) of participants with type 2 diabetes initiating fast-acting insulin were used. Data included demographics, clinical laboratory values, self-monitored blood glucose (SMBG), health-related quality of life (SF-36), and body measurements. A logistic regression was developed to predict HbA1c target nonachievers. A potential of 196 features was input for a forward feature selection. To assess the performance, a 20-repeated stratified 5-fold cross-validation with area under the receiver operating characteristics curve (AUROC) was used. RESULTS: Out of the 467 included participants, 98 (21%) did not achieve HbA1c target of ≤7%. The forward selection identified 7 features: baseline HbA1c (%), mean postprandial SMBG at all meals 3 consecutive days before baseline (mmol/L), sex, no ketones in urine, baseline albumin (g/dL), baseline low-density lipoprotein cholesterol (mmol/L), and traces of protein in urine. The model had an AUROC of 0.745 [95% CI = 0.734, 0.756]. CONCLUSIONS: The model was able to predict those who did not achieve HbA1c target with promising performance, potentially enabling early identification of people with type 2 diabetes who require additional support to reach glycemic control.

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.