Mobile application integrated with machine learning for patients with type two diabetes mellitus in Ethiopia Amharic version

Gubala Endeshaw Getu

Funding Area: Critical shared infrastructure / Infraestructura compartida critica

Problem Statement: The world prevalence of diabetes among adults (aged 20–79 years) will be 7.7%, and 439 million adults by 2030. Between 2010 and 2030, there will be a 69% increase in numbers of adults with diabetes in developing countries. High-quality information and education would improve recognition and management of the condition. Existing technologies, such as telehealth and mobile health apps and wearable devices, offer emerging opportunities to improve access to obesity care and enhance the quality, efficiency and cost-effectiveness of weight management interventions and long-term patient support. Future application of machine learning and artificial intelligence to obesity care could see interventions become increasingly automated and personalised.

Proposed Activities:  Problem definition: Preliminary study of proposed mobile app and machine learning algorithm solution to the end users problems, and feasibility Study  Problem analysis and design: User interface requirements, Processing requirements, Storage requirement, Control requirements  Problem Implementation: Conceptual Design, and Detailed Design (User Interface Design, Data design, Process Design)  Feedback from user on designed Mobile application integrated with machine learning solution  Documentation, presentation, feasibility analysis, fact finding, project and process management  Implementation  Evaluation and Validation  Maintenance and support

Openness:  Documents will be published through open document editor like LibreOffice  Mobile app backend will be developed by open source software python  Mobile app frontend will be developed by open source framework Xamarin  GIT an open source platform will be used for mobile app maintenance and update  Numpy an open source software will be used to define machine learning  An open source google cloud API will be used to integrate mobile app with machine learning  An open source visual studio and visual studio code will be used for mobile app development

Challenges: Electric and internet fluctuation, and inflation

Neglectedness: No

Success: Measure level of user engagement with app, assess the impact of app on patient’s health outcome, gather user feedback, evaluate the performance of machine learning algorithm, long-term behavior change,

Total Budget: 24,475 USD

Affiliations: No

LMIE Carveout: the project will be implemented in Ethiopia. The beneficiary of the project will be Ethiopian. All the team member of the project are Ethiopian.

Team Skills: The project manager Mr. Gubala is registered dietician and information technologist with plenty of experience on educating programming at Mizan-Tepi university information technology department currently lecture at university of Gondar, department of nutrition and dietetics. The rest two three member of the project are lecturer in information technology and the other two are registered dietician and lecturers.

Submission Number: 36