<p>Mobile application intervention to promote self-management in insulin-requiring type 1 and type 2 diabetes individuals: protocol for a mixed methods study and non-blinded randomized controlled trial</p>

Abstract

Background: Mobile applications (apps) have proven to be useful in supporting diabetes self-care, but non-consideration of users’ needs and non-inclusion of educational features are reasons for low continual use. Well-designed mobile apps that meet the needs of diabetes patients and provide ongoing self-management education and support are required. It was hypothesized that apps designed with such features can improve a range of measures including clinical outcomes, knowledge of diabetes, medication adherence, perceived ability for self-management, and quality-of-life. This may eventually facilitate a more robust and cost-effective approach for improving skills and motivation for the management of diabetes. Methods: This project will be conducted in two phases. It will initially employ a mixed methods study design to investigate the self-management needs and perceptions of diabetes patients on the use of mobile apps to support diabetes self-management. Results of the mixed methods study will inform the content and design of an app which will be employed as an intervention tool in a 12-month parallel randomized controlled trial (RCT). The RCT will compare outcomes in relation to standard-of-care alone with standard-of-care plus a mobile phone diabetes app among 150 insulin-requiring types 1 and 2 diabetes patients. The primary outcome measures are clinical parameters such as hemoglobin A1c (HbA1c), lipids, urine albumin-to-creatinine ratio, blood pressure, frequency in events of emergency hyperglycemia and hypoglycemia. Secondary outcomes include knowledge of diabetes, medication intake and adherence, perception of self-care, and quality-of-life. Discussion: Results from this study will provide empirical evidence on the usefulness of a mobile app developed based on self-management needs analysis of diabetic patients. The long-term goal is to harness knowledge gained from this study to provide evidenced-based data, which promote the scale-up or adoption of mobile applications that provide regular, ongoing education and self-management support to people living with diabetes. Trial registration: Australian New Zealand Clinical Trials Registry, ACTRN12618000065291, Registered on 17 January, 2018 (prospectively registered).

Effectiveness of using SOKARY Mobile Application on the compliance of patients with Type II diabetes: A quasi-experimental study

“…The foregoing present study finding was concerning the effect of SOKARY Mobile Application on patient's compliance is in agreement with Adu et al, 2019 who have presented empirical support for the effectiveness of the utility of smartphone app for built based on patient's needs to support self-management of a patient with diabetes 9 .…”

“…A recent study recommended that utilization of welldesigned mobile application(s) for supporting the patient with diabetes in self-care, likewise applicable mobile features can provide patients a wide range of measures as medication adherence, blood sugar level, knowledge of diabetic diet, and all information that required for selfmanagement for controlling and improving patient's quality of life 9 .…”

Health to Eat: A Smart Plate with Food Recognition, Classification, and Weight Measurement for Type-2 Diabetic Mellitus Patients’ Nutrition Control

“…If type 2 DM patients do not control their blood sugar levels properly, blood sugar levels can rise and fall, making them unstable, which can lead to complications. Diabetes mellitus control is accomplished through the application of basic diabetes mellitus control management principles, such as the modification of unhealthy lifestyles to become healthy through diet, physical exercise, and adherence to antidiabetic drug consumption [ 12 ].…”

“…CNN, or convolutional neural network, is a deep learning method that has been widely applied to image data [ 12 ]. In the case of image classification, the CNN method has succeeded in surpassing machine learning methods such as the SVM method, and currently has the most significant results in image recognition because CNN has a way of working that resembles the function of the human brain, where the computer will be given image data to study [ 19 ], trained to recognize each visual element on the image, and understand each image pattern, so that the computer will be able to identify the image [ 20 ].…”

Desenvolvimento de um sistema web para registro e controle de glicose

“…Essa evolução, por sua vez, demanda uma integração eficiente, garantindo a satisfação das necessidades de atendimento, por meio do desenvolvimento adequado de tecnologias em termos de hardware e software. Diversas pesquisas associadas aplicam os conceitos dos sistemas de saúde inteligentes para abordar os desafios e requisitos que se apresentam (ADU et al, 2019).…”