Sensor-based evaluation of intermittent fasting regimes: a machine learning and statistical approach
Authors' conclusion
The findings highlight the effectiveness of using sensor data, combined with advanced statistical and machine learning approaches, to passively evaluate dietary adherence in an intermittent fasting context.
Study context
- Population
- Time-series sensor data (CGM, acceleration data, food diaries) from two completed human trials, including individuals with and without T1D, and a synthetic data set2 trials + synthetic data
- Comparison
- Machine learning models vs Hutchison Heuristic statistical method
- Primary endpoint
- Performance of sensor-based models in determining dietary adherence (fasting vs non-fasting times) in intermittent fasting
Methodological detailsmachine learning, secondary use of data from two completed human trials and a synthetic data set
- Machine learning
- Secondary use of data from two completed human trials and a synthetic data set
Primary result
As reported in the abstract
Distinguishing fasting vs non-fasting times
Machine learning models
0.88
average F1-score
Further findings
- A dashboard was developed to visualize results efficiently and in a user-friendly manner
Original publication
Sensor-based evaluation of intermittent fasting regimes: a machine learning and statistical approach. Int J Obes (Lond). Published 22 August 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →