Leveraging language and cognitive data for PPA subtyping: A systematic review of AI-based approaches
Bibliographic record
Abstract
Primary Progressive Aphasia (PPA) is a neurodegenerative disorder marked by a gradual and selective decline in language. Accurate classification into its three clinical variants-nonfluent/agrammatic (nfvPPA), semantic (svPPA), and logopenic (lvPPA)-is essential but often limited by the time demands and expertise required for traditional assessments. This systematic review evaluates the application of artificial intelligence (AI) in the detection and classification of PPA variants using language and cognitive data. Following PRISMA 2020 guidelines, 14 peer-reviewed studies published between 2014 and 2024 were included. Studies were grouped by input modality: transcribed speech, acoustic features, multimodal data, and language-focused neuropsychological or task-based inputs (excluding studies based solely on general cognitive screening tools). Each was analyzed for methodological approach, AI technique, classification performance, and clinical relevance. AI-based approaches demonstrated high accuracy in distinguishing PPA variants. Transcribed linguistic features provided a practical and effective input source, while acoustic features were particularly sensitive to motor speech deficits in nfvPPA. Multimodal methods achieved the highest classification performance, and task-based models relying on language-oriented standardized assessments yielded interpretable and clinically applicable results. AI-driven analysis of language and cognitive data shows strong potential for improving PPA diagnosis and subtype classification. Future work should address limitations such as methodological variability, and lack of pathological validation. Advancements in cross-linguistic datasets, model transparency, and clinical integration will be essential for broader adoption.
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 | 0.025 | 0.108 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.008 | 0.010 |
| Bibliometrics | 0.018 | 0.014 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".