Strategies for online personalised nutrition advice employed in the development of the eNutri web app

Abstract

The internet has considerable potential to improve health-related food choice at low-cost. Online solutions in this field can be deployed quickly and at very low cost, especially if they are not dependent on bespoke devices or offline processes such as the provision and analysis of biological samples. One key challenge is the automated delivery of personalised dietary advice in a replicable, scalable and inexpensive way, using valid nutrition assessment methods and effective recommendations. We have developed a web-based personalised nutrition system (eNutri) which assesses dietary intake using a validated graphical FFQ and provides personalised food-based dietary advice automatically. Its effectiveness was evaluated during an online randomised controlled trial dietary intervention (EatWellUK study) in which personalised dietary advice was compared with general population recommendations (control) delivered online. The present paper presents a review of literature relevant to this work, and describes the strategies used during the development of the eNutri app. Its design and source code have been made publicly available under a permissive open source license, so that other researchers and organisations can benefit from this work. In a context where personalised diet advice has great potential for health promotion and disease prevention at-scale and yet is not currently being offered in the most popular mobile apps, the strategies and approaches described in the present paper can help to inform and advance the design and development of technologies for personalised nutrition.

Diet Quality Index for older adults (DQI-65): development and use in predicting adherence to dietary recommendations and health markers in the UK National Diet and Nutrition Survey

“…4 Portion sizes based on standard portions (31) : 80 g fruit, 150 mL fruit juice, 30 g dried fruit; only up to 1 portion of dried fruit or fruit juice allowed. 5 Represents food group from the UK Eatwell Guide (31) ; based on portions required to meet our previously proposed protein recommendations (27) ; standard portion sizes used (41) : 70 g red meat, 100 g poultry, 140 g fish or shellfish, approximately 120 g or 2 eggs, 150 g legumes, 30 g nuts, 250 mL milk, 30 g cheese, 125 g yoghurt, 100 g meat alternatives; only up to 1 portion of red meat (not processed meat), 1 portion of legumes or nuts and 1 portion of dairy or alternatives allowed per day. 6 Quantification and portion size based on SACN advice (25) ; portion size 140 g cooked fish.…”

“…4 Free sugars represented by non-milk extrinsic sugars from NDNS. 5 Results from 800 subjects due to non-response for body weight measurement. 6 No association reported as all subjects meeting recommendations for trans fatty acids.…”

“…Diet quality indexes (DQI) are useful nutritional assessment tools, accounting for the complexity of dietary exposure and the principle that people eat foods and not nutrients (4) , that can be easily translated into food-based, dietary advice (5) . Their use is increasingly prevalent, with several DQI being investigated within older adults (6)(7)(8)(9)(10)(11)(12)(13)(14)(15)(16)(17)(18) .…”

The Assessment of a Personalized Nutrition Tool (eNutri) in Germany: Pilot Study on Usability Metrics and Users’ Experiences

“…ICT apps capable of providing personal nutritional advice have attracted considerable attention in recent years [12]. To date, very few apps are equipped with the necessary decision engine for generating automated dietary recommendations in a personalized format that are also valid [13]. To address this need, the eNutri web app has been developed at the University of Reading (Hugh Sinclair Unit of Human Nutrition, United Kingdom) to provide automated personalized nutrition (PN) recommendations with a high degree of personalization [13].…”

“…To date, very few apps are equipped with the necessary decision engine for generating automated dietary recommendations in a personalized format that are also valid [13]. To address this need, the eNutri web app has been developed at the University of Reading (Hugh Sinclair Unit of Human Nutrition, United Kingdom) to provide automated personalized nutrition (PN) recommendations with a high degree of personalization [13]. As part of this approach, a validated web-based graphical FFQ illustrating different portion sizes of food items has been integrated into the eNutri app.…”