Abstract: FR-PO0041
A Digital Self-Management Intervention Improves Dietary Behavior in People Living with Nondialysis-Dependent CKD
Session Information
- Artificial Intelligence: Clinical Prediction, Decision Support, and Digital Kidney Care
October 23, 2026 | Location: Exhibit Hall A, Convention Center
Abstract Time: 10:00 AM - 12:00 PM
Category: Artificial Intelligence, Digital Health, and Data Science
- 300 Artificial Intelligence, Digital Health, and Data Science
Authors
- Hudson, Ralph Henry Lloyd, University of Leicester, Leicester, England, United Kingdom
- Lightfoot, Courtney Jane, University of Leicester Department of Cardiovascular Sciences, Leicester, England, United Kingdom
- Sohansoha, Gurneet Kaur, University of Leicester Department of Cardiovascular Sciences, Leicester, England, United Kingdom
- Ford, Ella C., School of Humanities and Social Sciences, Leeds Beckett University, Leeds, United Kingdom
- Vadaszy, Noemi, University of Leicester Department of Cardiovascular Sciences, Leicester, England, United Kingdom
- Wilkinson, Thomas James, University of Leicester Diabetes Research Centre, Leicester, United Kingdom
- Graham-Brown, Matthew, University of Leicester Department of Cardiovascular Sciences, Leicester, United Kingdom
Background
Poor dietary behavior is a modifiable risk factor in CKD, contributing to disease progression and cardiovascular morbidity. To support people living with CKD to better self-manage their health and lifestyle, we co-developed the 'My Kidneys & Me' (MK&M) digital platform with people living with CKD. MK&M offers theory-based education alongside action-focused (behavior change) sessions on maintaining a healthy, balanced diet, complemented by tools to track dietary goals.
Methods
420 adults aged ≥18 years with CKD stages 3-4 were recruited from 26 hospitals and randomised 2:1 to intervention (MK&M; n=280) or control (usual care; n=140). Diet quality was assessed at baseline and 20 weeks using the UK Diabetes Diet Questionnaire (UKDDQ). The UKDDQ asks participants how often they consumed key foods and drinks (e.g. vegetables, fruit, sugary drinks, processed foods) over the past month and generates a total score from 0–100, with higher scores indicating healthier dietary behavior. Baseline, age and sex adjusted ANCOVA analyses were used to compare UKDDQ scores at 20 weeks between groups, and also to examine individual UKDDQ questionnaire items, adjusting for each item's individual baseline value, to identify the specific dietary behaviors that changed. Results reported as (mean difference [95% CI], p-value).
Results
Significant improvement in diet quality was observed at 20 weeks (1.79 [0.21, 3.38], p=0.026). Item-level analyses identified significant reductions in the intake of several foods whose frequent consumption decreases UKDDQ scores, including bread (−0.27 [−0.44, −0.11], p<0.001), cheese (−0.36 [−0.58, −0.14], p<0.001), processed meat (−0.25 [−0.48, −0.03], p=0.028), savory snacks (−0.38 [−0.71, −0.04], p=0.028), and sweets/chocolate (−0.25 [−0.47, −0.02], p=0.035).
Conclusion
The use of MK&M was associated with improvements in overall diet quality and reductions in the intake of key dietary items in people with non-dialysis CKD. The findings highlight the potential of MK&M as a scalable digital health intervention to support targeted dietary behavior change.