Context is not key: Detecting Alzheimer’s disease with both classical and transformer-based neural language models
Bibliographic record
Abstract
Natural language processing (NLP) has exhibited potential in detecting Alzheimer’s disease (AD) and related dementias, particularly due to the impact of AD on spontaneous speech. Recent research has emphasized the significance of context-based models, such as Bidirectional Encoder Representations from Transformers (BERT). However, these models often come at the expense of increased complexity and computational requirements, which are not always accessible. In light of these considerations, we propose a straightforward and efficient word2vec-based model for AD detection, and evaluate it on the Alzheimer’s Dementia Recognition through Spontaneous Speech (ADReSS) challenge dataset. Additionally, we explore the efficacy of fusing our model with classic linguistic features and compare this to other contextual models by fine-tuning BERT-based and Generative Pre-training Transformer (GPT) sequence classification models. We find that simpler models achieve a remarkable accuracy of 92% in classifying AD cases, along with a root mean square error of 4.21 in estimating Mini-Mental Status Examination (MMSE) scores. Notably, our models outperform all state-of-the-art models in the literature for classifying AD cases and estimating MMSE scores, including contextual language models.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| 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 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".