Objective: This study aimed to evaluate the effectiveness of the app‐based, multimodal weight loss program zanadio.Methods: A randomized‐controlled trial was conducted from January 2021 to March 2022. A total of 150 adults with obesity were randomized into an intervention group and used zanadio for 1 year or into a wait list control group. The primary end point, weight change, and the secondary end points, quality of life, well‐being, and waist to height ratio, were assessed every 3 months for up to 1 year via telephone interviews and online questionnaires.Results: After 12 months, participants of the intervention group lost, on average, −7.75% (95% CI: −9.66% to −5.84%) of their initial weight, achieving a clinically relevant and statistically stronger weight reduction than the control group (mean = 0.00% [95% CI: −1.98% to 1.99%]). All secondary end points improved significantly in the intervention group, with significantly greater improvements in well‐being and waist to height ratio than in the control group.Conclusions: This study showed that adults with obesity who have used zanadio achieved a significant and clinically relevant weight loss within 12 months and improved further obesity‐related health variables compared with a control group. Because of its effectiveness and flexible applicability, the app‐based multimodal treatment zanadio might alleviate the present care gap for patients with obesity in Germany.

(1) Background: This study aimed at providing preliminary evidence for mebix, an app-based treatment program for patients with diabetes mellitus type II. The main target was to show a positive healthcare impact as defined by improved blood glucose control, i.e., reduced HbA1c values. (2) Methods: For this, a 3-month, prospective, open-label trial with an intraindividual control group was conducted. Participants received the mebix intervention for 3 months. HbA1c values were observed every 3 months: retrospectively, at baseline, and 3 months after the start of using the app. Additionally, weight and patients’ reported outcomes (well-being, diabetes-related distress, and self-management) were assessed. Data generated within the app were summarized and analyzed (steps, physical activity, fulfilled tasks, and food logs). (3) Results: After the usage of mebix for 3 months, participants significantly reduced their HbA1c levels (−1.0 ± 0.8%). Moreover, improvements in weight, well-being, and self-management as well as a reduction in diabetes-related distress were observed. App-generated data mainly supported the other main finding, that higher baseline HbA1c values lead to higher reductions. Overall, the study provided preliminary evidence that mebix can help patients improve metabolic and psychological health outcomes.

Background: Digital technologies for type 2 diabetes mellitus (T2DM) care hold great potential to improve patients’ health in the long term. Only a subset of telemedicine offerings are digital interventions that meet the criteria for prescribable digitale Gesundheitsanwendung (digital health apps; DiGAs) in Germany. Digital treatments further provide vast amounts of patient data that are important to generate evidence. Objective: This systematic review aims to analyze the efficacy of multimodal digital therapies that mainly meet the DiGA criteria for patients with T2DM and to elicit the potential of such therapies. This includes evidence from randomized controlled trials (RCTs) as well as from real-world data. The outcome of interest was a reduction in glycated hemoglobin (hemoglobin A1c [HbA1c]; long-term blood glucose measurements). Methods: A systematic literature search was conducted in the literature bases PubMed, LIVIVO, and Cochrane, based on the predefined PICO (Population; Intervention; Control; Outcome) scheme. Identified studies were assessed for risk of bias, pragmatism, and overall quality of evidence. Meta-analyses were conducted for between group differences using RCTs only, and for within-group differences using RCTs and non-RCTs, to examine the effect of the interventions on HbA1c. Results: In total, 795 records were identified, of which 24 were eligible for this systematic review and 23 studies were eligible for the meta-analysis. The results of the meta-analyses showed significant and clinically relevant reductions in HbA1c in patients with T2DM. Regarding the between-group difference for HbA1c reduction, the pooled effect of the RCTs showed a reduction of –0.36% (95% CI –0.59% to –0.14%; P<.001), favoring app-based interventions. The average mean within-group reduction in HbA1c was –0.79 (95% CI –1.02 to –0.55), with no significant difference between RCTs (–0.69, 95% CI –1.13 to –0.24) and non-RCTs (–0.87, 95% CI –1.16 to –0.57; P<.01, differences between RCTs and RCTs P=.44). A pragmatism rating showed that both study types were on average (very) pragmatic, that is, close to usual care. However, the overall quality of evidence was low to very low. Conclusions: This systematic review shows that digital therapies that mainly meet the DiGA criteria can effectively improve HbA1c in patients with T2DM. The integration of digital health care into usual care holds great potential and should be considered as a complementary option to usual care in the future. Trial Registration: PROSPERO CRD42023440203; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=440203

Background: Previous research has identified four distinct endotypes of type 2 diabetes in Asian Indians, which include Severe Insulin Deficient Diabetes (SIDD), Combined Insulin Resistant and Deficient Diabetes (CIRDD), Insulin Resistance and Obese Diabetes (IROD), and Mild Age-related Diabetes (MARD). DIANA (Diabetes Novel Subgroup Assessment) is an online precision medicine tool that can predict endotype membership of type 2 diabetes and individual risk for retinopathy and nephropathy. Methodology: The DIANA tool determines subgroup membership using a machine learning model (support vector machine) on T2D subgroups in the Asian Indian population. We used a support vector machine (SVM) model to classify type 2 diabetes patient endotypes, and the model is trained based on k-fold cross-validation. Its performance was compared with an algorithm determined based on conditional pre-determined cut-offs and weights for each clinical feature [age at diagnosis, BMI, waist, HbA_1c, Serum Triglycerides, HDL-Cholesterol, (C-peptide fasting, C-peptide stimulated) – optional. This study employed local interpretable model-agnostic explanations (LIME) and SHapley Additive exPlanations (SHAP) to demystify the endotype prediction model. A random forest model was built to assess an individual’s risk for nephropathy and retinopathy based on individual risk algorithms. Findings: The SVM model has relatively high accuracy, specificity, sensitivity, and precision values compared to conditional pre-determined cut-offs 98% vs 63.6%, 99.8% vs 88%, 98.5% vs 65.1%, and 98.7% vs 63.4%. Clinician face value validation of the prediction by the SVM model reported an accuracy, specificity, sensitivity and precision compared to conditional pre-determined cut-offs 97% vs 85%, 95.3% vs 63%, 95.8% vs 73%, and 98.9% vs 66.9%. Additionally, our study demonstrated the impact of features on ML models through LIME and SHAP analyses. The accuracy of the random forest risk prediction model for nephropathy and retinopathy was 89.6% (p < 0.05) and 78.4% (p < 0.05), respectively. Conclusion: We conclude that, DIANA is an accurate, clinically explainable AI tool that clinicians can use to make informed decisions on risk assessment and provide precision management to individuals with new-onset type 2 diabetes.

Aims: Digital applications have the potential to enhance diabetes management, particularly in patients treated with insulin. This study aims to evaluate the impact of a digital application on self-management (ESYSTA, Germany), expressed in a change in HbA1c levels, in people with diabetes treated with insulin.Materials and methods: A randomized controlled, multicentric trial was conducted in 204 people with diabetes (60% type 2 diabetes) treated with insulin to assess the efficacy of ESYSTA. Participants were randomly assigned to either the intervention group (IG) using ESYSTA in addition to the German standard of Care (SoC) according to the German disease management programs (DMP) for 6 months or a control group (CG) receiving SoC only. The primary endpoint was the change in HbA1c levels. Secondary endpoints included well-being and diabetes-related distress.Results: A clinically relevant reduction in HbA1c levels of on average −0.48% points (−0.66; −0.29) was observed in the IG after 6 months. Compared to the CG, this reduction was more pronounced, especially in the per-protocol sample [mean difference, −0.28% points; 95% CI (−0.54; −0.02)]. Improvements in the IG in further secondary endpoints, such as well-being or diabetes-related distress, indicate enhanced overall glycemic control and patient satisfaction in the IG.Conclusions: The use of ESYSTA improved HbA1c levels and other secondary outcomes in people with diabetes who are treated with insulin in comparison with German SoC in the context of DMP. These findings support the integration of digital tools in routine diabetes care to optimize patient outcomes.Clinical Trial Registration: https://drks.de/search/de/trial/DRKS00025996, identifier DRKS00025996.

Background: Digital interventions are promising additions for both usual care and rehabilitation. Evidence and studies for the latter, however, are still rare. Objective: The aim of the study was to examine the app/web-based patient education program called “mebix” (previously called “Vision 2 – Gesundes Herz”) regarding its effectiveness in relation to the parameters of disease-specific quality of life (HeartQoL), cardiovascular risk profile (Cardiovascular Risk Management [CARRISMA]), and prognostic estimation of early retirement (Screening instrument work and occupation [SIBAR]) in 190 participants from a cardiological rehabilitation clinic. Methods: To evaluate mebix, 354 patients from the Roderbirken Clinic of the German Pension Insurance Rhineland (Germany) with a coronary heart diesase were recruited and randomized either to the intervention group (using mebix postrehabiliation for up to 12 months) or the control group (receiving standard care). The data collection took place at the end of inpatient rehabilitation (t0), as well as 6 months (t1) and 12 months (t2) after the end of rehabilitation. Analyses of variance are used to assess the overall significance of difference in outcome parameters between groups and over time. Results: The primary endpoint of disease-related quality of life shows a significant improvement of 7.35 points over the course of the intervention that is also more pronounced in the intervention group. Similarly, the 10-year risk of cardiovascular death and myocardial infarction showed significant improvements in the cardiovascular risk profile over time and between groups, indicating better results in the intervention group (ie, a reduction of −1.59 and −5.03, respectively). Secondary outcomes like the body weight and cholesterol levels were significantly reduced in the intervention group, also in comparison with the control group. In addition, the SIBAR was significantly lower/better at the end of the observation period than at the beginning of the observation for both groups. Conclusions: Overall, the digital training program represents an effective follow-up offer after rehabilitation that could be incorporated into standard care to further improve disease-related quality of life and cardiovascular risk profiles.