Development and first‐stage validation of a digital version of the Digit Symbol Substitution test for use in assessing cognitive function in older people with diabetes
Performance · Correlation between P&P and digital DSSTResult — go to the resultr 0.76Authors' conclusion
This study describes the development of and provides first-stage validation data for a newly developed digital cognitive assessment tool that may be used for screening and surveillance of cognitive function in older people with diabetes. More studies are needed to further validate this tool, especially when self-administered and in different clinical settings.
Study context
- Population
- Individuals with T2D aged ≥60 years; one-time meeting with both versions administeredinvited
- Participants
- 100 individuals
- Comparison
- Digital digit symbol substitution test (DSST) vs pencil-and-paper DSST
- Outcome
- Correlation between digital and P&P versions of the DSST
Methodological detailsdevelopment and first-stage validation, machine-learning algorithm
- Development and first-stage validation
- Machine-learning algorithm
Performance
Correlation between P&P and digital DSST
r
0.76
P < 0.001
As reported in the abstract
Further findings
| Outcome | Digital DSST |
|---|---|
| ML model accuracy | |
| Overall accuracy | 89.1% |
Correlation between machine-learning (ML) model and manual reading of digital DSST
- Correlation ML model vs manual reading of digital DSST (r)
- 0.99
- p < 0.001
Original publication
Development and first‐stage validation of a digital version of the Digit Symbol Substitution test for use in assessing cognitive function in older people with diabetes. Diabetes Obes Metab. Published 17 May 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →