Optimization of cognitive assessment in Parkinsonisms by applying artificial intelligence to a comprehensive screening test
Bibliographic record
Abstract
The assessment of cognitive deficits is pivotal for diagnosis and management in patients with parkinsonisms. Low levels of correspondence are observed between evaluations assessed with screening cognitive tests in comparison with those assessed with in-depth neuropsychological batteries. A new tool, we named CoMDA (Cognition in Movement Disorders Assessment), was composed by merging Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA), and Frontal Assessment Battery (FAB). In total, 500 patients (400 with Parkinson's disease, 41 with vascular parkinsonism, 31 with progressive supranuclear palsy, and 28 with multiple system atrophy) underwent CoMDA (level 1-L1) and in-depth neuropsychological battery (level 2-L2). Machine learning was developed to classify the CoMDA score and obtain an accurate prediction of the cognitive profile along three different classes: normal cognition (NC), mild cognitive impairment (MCI), and impaired cognition (IC). The classification accuracy of CoMDA, assessed by ROC analysis, was compared with MMSE, MoCA, and FAB. The area under the curve (AUC) of CoMDA was significantly higher than that of MMSE, MoCA and FAB (p < 0.0001, p = 0.028 and p = 0.0007, respectively). Among 15 different algorithmic methods, the Quadratic Discriminant Analysis algorithm (CoMDA-ML) showed higher overall-metrics performance levels in predictive performance. Considering L2 as a 3-level continuous feature, CoMDA-ML produces accurate and generalizable classifications: micro-average ROC curve, AUC = 0.81; and AUC = 0.85 for NC, 0.67 for MCI, and 0.83 for IC. CoMDA and COMDA-ML are reliable and time-sparing tools, accurate in classifying cognitive profile in parkinsonisms.This study has been registered on ClinicalTrials.gov (NCT04858893).
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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".