Novel energy balance tracking to support personalised AI health coaching: a real-world evaluation of the ENHANCE framework
Authors' conclusion
This scalable method delivers the accuracy and practicality needed for real-world EB tracking-laying the foundation for continuous personalised AI coaching.
Study context
- Population
- Participants tracking energy balance over the Christmas to New Year 2024/25 festive period with Wi-Fi scales and a mobile app18 analysed
- Participants
- 23 participants
- Outcome
- Accuracy of ENHANCE energy balance (EB) tracking
- Follow-up
- 4 weeks
Methodological details4-week, real-world, Five excluded due to illness (n = 4) or bereavement (n = 1)
- 4-week
- Real-world
- Five excluded due to illness (n = 4) or bereavement (n = 1)
Main finding
As reported in the abstract
- Group-level predicted trends explained smoothed trend variance (R²)
- 0.904
- Predicted vs smoothed trend, MAE
- 93 g
- Corrected trends vs piecewise segments, MAE
- 46 g
- Raw trends vs piecewise segments, MAE
- 77 g
- Individual-level mean energy balance (EB) corrections
- +41 kcal/day
- Mean EB correction as share of reported intake
- 2%
Observational data: associations, not effects.
Further findings
Adherence
- Body weight measurements completed, mean (SD)
- 94% (5.1%)
- EB-related submissions completed
- 100%
Acceptability questionnaire · end of study
- Burden
- 1.8/5
- Behavioural reactivity
- 1.5/5
Calculated mean net fat weight change during monitoring
- Mean (SD)
- +0.8 kg (0.4 kg)
Mean net EB
- Mean (SD)
- +223 kcal/day (130 kcal/day)
Original publication
Novel energy balance tracking to support personalised AI health coaching: a real-world evaluation of the ENHANCE framework. Int J Obes (Lond). Published 12 May 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →