Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Diabetes mellitus is a chronic metabolic disorder that results in abnormal blood glucose regulations. Blood glucose level is preferably maintained close to normality through self-management practices, which involves actively tracking blood glucose levels and taking proper actions including adjusting diet and insulin medications. Blood glucose anomalies could be defined as any undesirable reading either due to a precisely known reason (normal cause variation) or unknown reason (special cause variation) to the patient. Recently, machine learning applications have been widely introduced within the diabetes research in general and blood glucose anomalies detection in particular. However, irrespective of their expanding and increasing popularity, there is lack of updated reviews that materialize the current trends in modelling options and strategies for blood glucose anomalies classification and detection in people with diabetes. Objective: The objective of this review is to identify, assess and analyze the state-of-the-art machine learning strategies and its hybrid systems focusing on blood glucose anomalies classification and detection including glycemic variability, hyperglycemia, and hypoglycemia in type 1 diabetes within the context of personalized decision support systems and blood glucose alarm events applications, which are important constituents for optimal diabetes self-management. Methods: A rigorous literature was conducted between September 1 and October 1, 2017, through various online databases including Google scholar, PubMed, ScienceDirect and others. Peer reviewed journals and articles were considered. Relevant articles were first identified by reviewing the title, keywords, and abstracts as a preliminary filter with our selection criteria, and then reviewed the full text articles that fulfilled the inclusion criteria. Information from the selected literature was extracted based on some predefined categories, which were based on previous research and further elaborated through brainstorming. Results: The initial hit was vetted using the title, abstract, and keywords, and retrieved a total of 496 papers. After a thorough assessment and screening 47 articles were left, which were critically analyzed. The inter-rater agreement was measured using Cohen Kappa test, and disagreements were resolved through discussion. The state-of-the-art classes of machine learning have been developed and tested up to the task and achieved promising performance including artificial neural network, support vector machine, decision tree, genetic algorithm, Gaussian process regression, Bayesian neural network, deep belief network, and others. Conclusions: Despite the complexity of blood glucose dynamics, there are many attempts to capture hypoglycemia, hyperglycemia incidences and the extent of an individual’s glycemic variability using different approaches. Recently, advancement of diabetes technologies and continuous accumulation of self-collected health data has paved the way for popularity of machine learning in these tasks. According to the review, most of the identified studies used a theoretical threshold, which suffers from inter and intra-patient variation. Therefore, future studies should consider the difference among patients and also track its temporal change overtime. Moreover, studies should also give more emphasis on the types of inputs used and its associated time lag. Generally, we foresee these developments might encourage researchers to further develop and test these systems on a large-scale basis.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Health authorities recommend educating diabetes patients and their families and initiating measures aiming at improving self-management, promoting a positive behavior change and reducing the risk of complications. Social media could be valid channels to intervene and deliver diabetes education. However it is not well known if the use of these channels in interventions can help to improve patients’ outcomes. Objective: To review and describe the current existing evidence on the use of social media in interventions targeting people affected with diabetes. Methods: A search was conducted across four databases (Pubmed; SCOPUS; EMBASE; and Cochrane Library). The quality of the evidence of the included primary studies was graded according to the GRADE criteria, and the risk of bias of systematic reviews was assessed by drawing on the AMSTAR guidelines. The outcomes reported by these studies were extracted and analysed. Results: Twenty articles of moderate and high quality were included in the review; 17 primary studies and three systematic reviews. Thirteen among the sixteen publications measuring the effect on HbA1c of the intervention using social media have reported significant reductions. The five studies that measured satisfaction with the interventions using social media found positive effects. There was mixed evidence regarding the effect of interventions using social media on health related quality of life (two publications found positive effects and three found no differences); and also on diabetes knowledge or empowerment (two articles reported improvements and two reported no significant changes). Conclusions: There is little evidence of good quality on the use of social media in interventions aimed at people with diabetes. However, the use of these channels is mostly linked to benefits on patients’ outcomes. Public health institutions, clinicians and other stakeholders that aim at improving the education of diabetes patients could consider the use of social media in their interventions. Clinical Trial: This review has been registered in PROSPERO (registration number: CRD42018088206).

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet

Background: There is growing evidence that apps and digital interventions have a positive impact on diabetes self-management. Standard self-management for patients with diabetes could therefore be supplemented by apps and digital interventions to increase patients’ skills. Several initiatives, models, and frameworks suggest how health apps and digital interventions could be evaluated, but there are few standards for this. And although there are many methods for evaluating apps and digital interventions, a more specific approach might be needed for assessing digital diabetes self-management interventions. Objective: This review aims to identify which methods and criteria are used to evaluate apps and digital interventions for diabetes self-management, and to describe how patients were involved in these evaluations. Methods: We searched CINAHL, EMBASE, MEDLINE, and Web of Science for articles published from 2015 that referred to the evaluation of apps and digital interventions for diabetes self-management and involved patients in the evaluation. We then conducted a narrative qualitative synthesis of the findings, structured around the included studies’ quality, methods of evaluation, and evaluation criteria. Results: Of 1681 articles identified, 31 fulfilled the inclusion criteria. A total of 7 articles were considered of high confidence in the evidence. Apps were the most commonly used platform for diabetes self-management (18/31, 58%), and type 2 diabetes (T2D) was the targeted health condition most studies focused on (12/31, 38%). Questionnaires, interviews, and user-group meetings were the most common methods of evaluation. Furthermore, the most evaluated criteria for apps and digital diabetes self-management interventions were cognitive impact, clinical impact, and usability. Feasibility and security and privacy were not evaluated by studies considered of high confidence in the evidence. Conclusions: There were few studies with high confidence in the evidence that involved patients in the evaluation of apps and digital interventions for diabetes self-management. Additional evaluation criteria, such as sustainability and interoperability, should be focused on more in future studies to provide a better understanding of the effects and potential of apps and digital interventions for diabetes self-management.

Mobile and tablet apps, ubiquitous and pervasive computing, wearable computing and domotics for health.