The use of artificial intelligence (AI) and big data in medicine has increased in recent years. Indeed, the use of AI in mobile health (mHealth) apps could considerably assist both individuals and health care professionals in the prevention and management of chronic diseases, in a person-centered manner. Nonetheless, there are several challenges that must be overcome to provide high-quality, usable, and effective mHealth apps. Here, we review the rationale and guidelines for the implementation of mHealth apps and the challenges regarding quality, usability, and user engagement and behavior change, with a special focus on the prevention and management of noncommunicable diseases. We suggest that a cocreation-based framework is the best method to address these challenges. Finally, we describe the current and future roles of AI in improving personalized medicine and provide recommendations for developing AI-based mHealth apps. We conclude that the implementation of AI and mHealth apps for routine clinical practice and remote health care will not be feasible until we overcome the main challenges regarding data privacy and security, quality assessment, and the reproducibility and uncertainty of AI results. Moreover, there is a lack of both standardized methods to measure the clinical outcomes of mHealth apps and techniques to encourage user engagement and behavior changes in the long term. We expect that in the near future, these obstacles will be overcome and that the ongoing European project, Watching the risk factors (WARIFA), will provide considerable advances in the implementation of AI-based mHealth apps for disease prevention and health promotion.

A recent Finnish study described reduced fertility in patients with childhood-onset type 1 diabetes. The Type 1 Diabetes Genetics Consortium (T1DGC) is an international programme studying the genetics and pathogenesis of type 1 diabetes that includes families with the disease. Our aim was to assess fertility, defined as number of offspring, in the affected and unaffected siblings included in the T1DGC. Clinical information from participants aged ≥18 years at the time of examination was included in the present analysis. The number of offspring of affected and unaffected siblings was compared (in families including both) and the influence of birth year, disease duration and age of onset was assessed, the last in affected siblings only, using Poisson regression models. A total of 3010 affected and 801 unaffected adult siblings that belonged to 1761 families were assessed. The mean number of offspring was higher in the unaffected than in the affected individuals, and the difference between the two groups was more pronounced in women than men. Poisson regression analysis showed that both sex and birth cohort significantly affected the differences between groups. In the affected siblings, adult onset (≥18 years), female sex and older birth cohort were associated with higher fertility. Patients with type 1 diabetes have fewer children than their unaffected siblings. This effect is more evident in women and in older birth cohorts. Onset of type 1 diabetes as an adult rather than a child is associated with a higher number of offspring, even after accounting for birth cohort and disease duration.

Purpose: The main objective of this study was to assess quality of life (QoL) and treatment satisfaction in a group of patients with type 1 diabetes (T1D) and explore their needs regarding and their perception of QoL living with diabetes. Materials and methods: Patients with type 1 diabetes attending the outpatient endocrinology clinics of a reference hospital were invited to participate in a cross-sectional study. Clinical and sociodemographic data were obtained (interview and clinical records), and diabetes-related QoL was assessed using a standardized questionnaire. In 67 participants, satisfaction with treatment was also assessed, and an open interview was performed, assessing the impact of diabetes, long-term worries, flexibility, restrictions, and self-perception of QoL. Descriptive statistical analysis, bivariate analysis, and multivariate analysis were performed in order to find factors associated with QoL. Interviews were analyzed and summarized questionwise. Results: Mean patient age was 31.4±11.6 years, diabetes duration 14.2±9.3 years, and glycated hemoglobin (HbA_1c) 8.5%±1.9% (69±20.8 mmol/mol International Federation of Clinical Chemistry [IFCC]). The questionnaires showed good average QoL scores (94.6+22.9) and treatment satisfaction scores (25.7±6.7). QoL worsened with increasing HbA_1c, female sex, severity of complications, and lower education (r²=0.283, P<0.005). In the open interview, 68.5% of the patients reported that diabetes had changed their lives, 83.5% identified complications as their most important long-term concern, and 59.7% said that they needed more training to manage the disease. Conclusion: Poor glycemic control, lower education, complications, and female sex are associated with worse QoL. Semi-structured interviews identified aspects not included in the standardized questionnaires.

Purpose. To explore the factors involved in adherence to self-care behaviors in patients with type 1 diabetes. Materials and Methods. Patients with type 1 diabetes (age range: 14-71 years) were invited to participate at seven Spanish hospitals. They completed a dossier which recorded sociodemographic and clinical variables and also measured personality variables, emotional state, beliefs, and concerns regarding the illness, by means of questionnaires. Results. A total of 428 patients with type 1 diabetes were included (58% women, age 36 (11.8) years, diabetes duration 18.3 (10.2) years, HbA1c 7.9 +/-1.3%). A total of 60.1% of patients found it difficult to follow the treatment recommendations for the care of their disease. The reasons given were mood (25.2%), lack of motivation (13.4%), work (12%), and economic difficulties (3.8%). Other personal reasons were reported by 5.7%. Motivation, training in diabetes management, importance the patient attributed to the disease, and self-efficacy were the variables that predicted adherence to self-care behaviors, together accounting for 32% of its variance. Anxiety and depression were highly prevalent in this study population (57.1% and 23.1%, respectively) and were associated with lower adherence. Conclusion. In the present study assessing patients with type 1 diabetes, motivation, training in diabetes management, beliefs regarding the disease, and self-efficacy were the main contributors to adherence to self-care behaviors. On the other hand, anxiety and depression were highly prevalent and associated with lower adherence. Thus, supplementing therapeutic education with strategies designed to raise levels of motivation, discussion of beliefs about the disease, and encouragement of self-efficacy might be a useful way to increase patient involvement in self-care.

Background: Type 2 diabetes mellitus (T2DM) is a chronic disease in which health outcomes are related to decision making by patients and health care professionals. Objective: This study aims to assess the effectiveness of internet-based multicomponent interventions to support decision making of all actors involved in the care of patients with T2DM in primary care. Methods: The INDICA study is an open, community-based, multicenter trial with random allocation to usual care or the intervention for patients, the intervention for health care professionals in primary care, or the combined intervention for both. In the intervention for patients, participants received an educational group program and were monitored and supported by logs, a web-based platform, and automated SMS. Those in the intervention for professionals also received an educational program, a decision support tool embedded in the electronic clinical record, and periodic feedback about patients’ results. A total of 2334 people with T2DM, regardless of glycated hemoglobin (HbA1c) levels and without diabetes-related complications, were included. The primary end point was change in HbA1c level. The main analysis was performed using multilevel mixed models. Results: For the overall sample, the intervention for patients attained a significant mean reduction in HbA1c levels of ‒0.27 (95% CI ‒0.45 to ‒0.10) at month 3 and ‒0.26 (95% CI ‒0.44 to ‒0.08) at month 6 compared with usual care, which remained marginally significant at month 12. A clinically relevant reduction in HbA1c level was observed in 35.6% (191/537) of patients in the intervention for patients and 26.0% (152/586) of those in usual care at month 12 (P=.006). In the combined intervention, HbA1c reduction was significant until month 18 (181/557, 32.6% vs 140/586, 23.9%; P=.009). Considering the subgroup of patients uncontrolled at baseline, all interventions produced significant reductions in HbA1c levels across the entire study period: ‒0.49 (95% CI ‒0.70 to ‒0.27) for the intervention for patients, ‒0.35 (95% CI ‒0.59 to ‒0.14) for the intervention for professionals, and ‒0.35 (95% CI ‒0.57 to ‒0.13) for the combined intervention. Differences in HbA1c for the area under the curve considering the entire period were significant for the intervention for patients and the combined intervention compared with usual care (P=.03 for both). Compared with usual care, the intervention for professionals and the combined intervention had significant longer-term reductions in systolic and diastolic blood pressure. Conclusions: In uncontrolled patients, the intervention for patients at baseline provided clinically relevant and significant longer-term reductions of HbA1c levels. The intervention for professionals and combined intervention also improved the cardiovascular risk profile of patients. Trial Registration: ClinicalTrials.gov NCT01657227; https://clinicaltrials.gov/ct2/show/NCT01657227

Digital health literacy (DHL) is the ability to search, understand and evaluate information from digital media and apply that knowledge to solve health problems. However, currently many citizens have not developed these skills, and this compromises not only the self-management of their health, but the possibility that health services are socially sustainable. The objective of this article was to present the objectives, activities and results of the IC-Health project whose objective was to develop a series of massive open online courses (MOOCs) to improve the DHL skills of European citizens. An exploratory report on DHL’s current evidence was developed. Furthermore, a survey, focus groups and group interviews were conducted to determine DHL levels and the needs of population cohorts (children; adolescents; pregnant and lactating women; the elderly; and people affected by type 1 and type 2 diabetes). A participation strategy with end users was designed through a community of practice for the creation of MOOCs with the seven European countries that participated in the consortium. Thirty-five MOOCs were developed in eight different languages and a descriptive and exploratory assessment of MOOCs was conducted with new participants. This first evaluation indicated that MOOCs can be an effective educational resource for DHL and a facilitator of shared decision-making processes. The process of co-creation of MOOCs, the components, the challenges and the opportunities identified in this European project could be useful for other developers of MOOCs who want to co-create interventions with beneficiaries in similar settings. Further longer-term actions are still needed to improve citizens’ DHL.