Identifying Food Preferences and Malnutrition in Older Adults in Care Homes: Co-Design Study of a Digital Nutrition Assessment Tool
Bibliographic record
Abstract
BACKGROUND: Malnutrition is a challenge among older adults and can result in serious health consequences. However, the dietary intake monitoring needed to identify malnutrition for early intervention is affected by issues such as difficulty remembering or needing a dietitian to interpret the results. OBJECTIVE: This study aims to co-design a tool using automated food classification to monitor dietary intake and food preferences, as well as food-related symptoms and mood and hunger ratings, for use in care homes. METHODS: Participants were 2 separate advisory groups and 2 separate sets of prototype testers. The testers for the first prototype were 10 community-dwelling older adults based in the Stirlingshire area in Scotland who noted their feedback on the tool over 2 weeks in a food diary. The second set of testers consisted of 14 individuals (staff: n=8, 57%; and residents: n=6, 43%) based in 4 care homes in Scotland who provided feedback via interview after testing the tool for a minimum of 3 days. In addition, 130 care home staff across the United Kingdom completed the web-based survey on the tool's needs and potential routes to pay for it; 2 care home managers took part in follow-up interviews. Data were collected through food diaries, a web-based survey, audio recordings and transcriptions of focus groups and interviews, and research notes. Systematic text condensation was used to describe themes across the different types of data. RESULTS: Key features identified included ratings of hunger, mood, and gastrointestinal symptoms that could be associated with eating specific foods, as well as a traffic light system to indicate risk. Issues included staff time, Wi-Fi connectivity, and the accurate recognition of pureed food and fortified meals. Different models for potential use and commercialization were identified, including peer support among residents to assist those considered less able, staff-only use of the tool, care home-personalized database menus for easy meal photo selection, and targeted monitoring of residents considered to be at the highest risk using the traffic light system. CONCLUSIONS: The tool was deemed useful for monitoring dietary habits and associated symptoms, but necessary design improvements were identified. These should be incorporated before formal evaluation of the tool as an intervention in this setting. Co-design was vital to help make the tool fit for the intended setting and users.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".