Finding Optimal Alphabet for Encoding Daily Continuous Glucose Monitoring Time Series Into Compressed Text
Authors' conclusion
Encoding CGM data into text could enhance the classification of CGM profiles and enable the use of well-established search engines with CGM data.
Study context
- Population
- Individuals with T1D or T2D, and without diabetes, from six distinct studies with different treatment modalitiessix studies
- Comparison
- Eight alphabets for encoding daily continuous glucose monitoring (CGM) profiles into text
- Outcome
- Optimal alphabet for encoding the CGM daily profile, by AIC derived from error and compression ratio
Methodological detailstraining (70%) and validation (30%) split, data from six distinct studies
- Training (70%) and validation (30%) split
- Data from six distinct studies
Performance
As reported in the abstract
Optimal alphabet (lowest AIC)
- A 9-letter alphabet was optimal for encoding daily CGM profiles for T1D or T2D, yielding the lowest Akaike information criterion (AIC) score
- In health, fewer letters were needed, given the lower variation of the data
- Training data
Further findings
Pearson correlation of 9-letter alphabet with CV
- 9-letter alphabet approximated the CV; correlations
- 0.945 and 0.965
Original publication
Finding Optimal Alphabet for Encoding Daily Continuous Glucose Monitoring Time Series Into Compressed Text. J Diabetes Sci Technol. Published 20 March 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →