For low and lower-middle income countries (LLMIC), a ‘global nutrition transition’ exists involving the dual burden of malnutrition and non-communicable chronic diseases, with type 2 diabetes now becoming highly prevalent. For LLMIC risk factors related to dietary intake (e.g. low fruit and vegetable intake) and malnutrition are the top two contributors to burden of disease. In low-income countries malnutrition, is the leading cause of disease burden with dietary risks placed fifth.
The lack of comprehensive, reliable data on the contemporary dietary intakes of individuals in LLMIC hinders the ability to determine nutritional adequacy of intakes and provide timely intervention in these settings. Inherent logistical challenges (e.g. geography, infrastructure) within these settings combined with the resource-intensive nature of the dietary assessment methods commonly used (e.g. interviewer-administered 24-hour recalls and direct observation with weighing of food) can be time and cost prohibitive to regular use, further compounding this problem. In addition, due to a lack of skilled workers in LLMIC, regular and ongoing surveillance of nutritional adequacy of dietary intakes of individuals is often reliant on external organizations and individuals to undertake these activities.
OUR PROPOSED SOLUTION
The project will address this problem by developing the Voice-Image-Sensor technology for Individual Dietary Assessment (VISIDA) system, a novel dietary assessment method which combines voice and imaging sensor technologies to overcome limitations of current methods used in LMIC settings. In addition to producing an acceptable and valid dietary assessment method, we will develop and evaluate an implementation framework to guide the use of the method in similar settings.
The VISIDA system, is a multi-component system for the collection, analysis and interpretation of individual dietary intake data. The system is modular to facilitate iteration of the components as the technologies and techniques advance.
The VISIDA system currently comprises:
1. A smartphone app (Android OS) for the collection of intake and recipe data via images and voice recordings (or as a text description) before and following eating occasions and food preparation. Breastfeeding occasion data can also be collected as a frequency. Intake data can be collected for a single person or multiple individuals with the same household (e.g. mother and her child/ren). The app is designed for individuals to collect their intake and/or for others in their household and has several features to support use by individuals with low literacy levels. The app may also be used by field workers or research assistants to capture intake on behalf of others in scenarios where observation is already occurring.
2. An offline data visualization and annotation program (Windows OS) for use in the field to review and annotate data collected via the smartphone app in settings where access to the internet may be limited. The annotated data is exported and uploaded into the web-based platform for analysis. This is an optional component designed to optimize data quality.
3. A web-based content management system for the semi-automated analysis of the collected dietary intake data which produces estimates of nutrient intake. The system also contains a data visualization dashboard to facilitate interpretation of dietary intake data by exploring nutritional adequacy and key nutrient food sources.
We have also explored the use a wrist sensor for detection of hand-to-mouth gestures to be used to verify eating occasions occurred in comparison to the smartphone app data. The foundational work of this component (the OREBA dataset) has been completed in Newcastle with the intention to apply models to data collected in the field.
The VISIDA system will allow for rapid individualized dietary assessment and also support for the data interpretation and the provision of feedback. The system will allow for identification of individuals with nutritional needs that should be prioritized to optimize health. Further, the VISIDA system can complement population surveillance strategies ensuring that vulnerable groups can be targeted to optimise intake and the evaluation of the effectiveness of nutrition interventions can occur in a timely manner.
An outcome from this project will be to create several dietary training modules for local health workers and nutritionists and an implementation framework for other LLMIC that will be made readily accessible online.