Diagnostic utility of speech-based biomarkers in mild cognitive impairment: a systematic review and meta-analysis
Bibliographic record
Abstract
BACKGROUND: Among various tools developed for mild cognitive impairment (MCI) detection, analysing speech features is a non-invasive and cost-effective approach that shows promise for early detection. This review aimed to systematically synthesise and analyse current evidence on the diagnostic utility of speech-based biomarkers for identifying MCI. METHODS: A systematic review and meta-analysis were conducted following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. PubMed, Scopus, Ovid Medline and PsycINFO databases were searched up to April 2025 without restrictions on language, article status or year. RESULTS: Of 4432 identified records, 54 peer-reviewed articles met the inclusion criteria. Fixed-effects meta-analyses showed pooled estimates of 80.0% 'accuracy' [95% confidence intervals (CI): 70.0%-89.0%, P < .001, n = 21], 78.0% 'area under the curve' (95% CI: 70.0%-86.0%, P < .001, n = 21), 80.0% 'sensitivity' (95% CI: 71.0%-90.0%, P < .001, n = 22), and 77.0% 'specificity' (95% CI: 65.0%-89.0%, P < .001, n = 15) in differentiating MCI from cognitively unimpaired (CU) individuals. Egger's regression tests indicated no publication bias (P ≥ .299), and the I2 statistic revealed no heterogeneity across studies (I2 = 0.00%, P = 1.00). Four studies also included a subjective cognitive decline group, reporting significant differences in certain speech features compared to CU. CONCLUSIONS: Speech analysis demonstrates moderate classification performance, with balanced sensitivity and specificity, in distinguishing MCI from CU, suggesting its potential as an accurate and cost-effective diagnostic tool for MCI detection. Further research is needed to address variations in study methodologies, refine speech analysis protocols and validate findings in diverse populations to enhance generalisability.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.007 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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 teacher head, 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".