Development and Evaluation of an Android-based Platform for Early MCI Detection in an Elderly Population
Bibliographic record
Abstract
Abstract Background Mild cognitive impairment (MCI) is an intermediate stage of cognitive decline fitting in-between normal cognition and dementia. With the growing aging population, this study aimed to develop and psychometrically validate an android-based application for early MCI detection in elderly subjects. Method This study was conducted in two phases, including 1-Initial design and prototyping of the application named M-Check, 2-psychometric evaluation. After the design and development of the M-Check app, it was evaluated by experts and elderly subjects. Face validity was determined by two checklists provided to the expert panel and the elderly subjects. Convergent validity of the M-Check app was assessed using the Montreal Cognitive Assessment (MoCA) battery through Pearson correlation. Test-retest and internal consistency and reliability were evaluated using Intra-Class Correlation (ICC) and Kuder-Richardson coefficients, respectively. In addition, the usability was assessed by a System Usability Scale (SUS) questionnaire. SPSS 16.0 was employed to analyze the data. Result The app’s usability assessment by elderlies and experts scored 77.11 and 82.5, respectively. Also, the correlation showed that the M-Check app was negatively correlated with the MoCA test (r = -0.71, p <0.005), and the ICC was more than 0.7. Moreover, the Richardson’s Coder coefficient was 0.82, corresponding to an acceptable reliability. Conclusion In this study, we validated the M-Check app for the detection of MCI based on the growing need for cognitive assessment tools that can identify early decline. Such screeners are expected to take much shorter time than typical neuropsychological batteries do. Additional work are yet to be underway to ensure that M-Check is ready to launch and used without the presence of a trained person.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".