Home › Research › Digital health tools
nterpretable Alzheimer’s Disease Detection from CHAT Transcripts Using Criterion-Guided LLM Prompting and In-Context Learning
ajroudi k, Khedher MI, Jemai o.. Research Square, 2026-09-10
Topic: Brain imaging, connectivity and assessment
Early detection of Alzheimer’s disease (AD) from spontaneous speech remains a clinically significant challenge. Transformer-based models such as BERT perform well through fine-tuning, but they require labelled data, are sensitive to domain shift, and offer limited interpretability. We introduce a training-free, criterion-guided reasoning framework that leverages in-context learning (ICL) and chain-of-thought (CoT) prompting for AD detection from manually transcribed speech, with no parameter update. CHAT annotation symbols are first normalised into natural-language markers; a LLaMA model then extracts three discriminative linguistic criteria (lexical impoverishment, disfluency, and coherence degradation); a Kimi model classifies through a criterion-grounded CoT prompt with diversity-selected in-context examples; and a DSPy module explains each prediction. On the ADReSS 2020 benchmark (48 test transcripts), the framework reaches 85.4% accuracy and 85.1 F1, outperforming the evaluated supervised and LLM-based baselines by at least 4.2 percentage points. Performance drops to 57.5% on ASR transcripts, revealing a dependence on high-quality manual transcriptions
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
APA 7th
k, a., Khedher, M. I., & o, J. (2026). nterpretable Alzheimer’s Disease Detection from CHAT Transcripts Using Criterion-Guided LLM Prompting and In-Context Learning. Research Square. https://doi.org/10.21203/rs.3.rs-10559912/v1
Vancouver
k a, Khedher MI, o J. nterpretable Alzheimer’s Disease Detection from CHAT Transcripts Using Criterion-Guided LLM Prompting and In-Context Learning. Research Square. 2026. doi:10.21203/rs.3.rs-10559912/v1.
BibTeX
@article{k2026-9d27135c,
author = {k, ajroudi and Khedher, M. I. and o, Jemai},
title = {{nterpretable Alzheimer’s Disease Detection from CHAT Transcripts Using Criterion-Guided LLM Prompting and In-Context Learning}},
journal = {Research Square},
year = {2026},
doi = {10.21203/rs.3.rs-10559912/v1},
url = {https://doi.org/10.21203/rs.3.rs-10559912/v1}
}
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. Check the citation against the original before you use it.
Key findings
- Early detection of Alzheimer’s disease (AD) from spontaneous speech remains a clinically significant challenge.
New to this subject? Start with our plain-English guide: Digital health →
Study details
- Effect size85.4%; 57.5%
- Evidence strengthLow
How this study scored 16/100
Preprint — not yet peer-reviewed. It scored 24 on the same rubric, but non-peer-reviewed sources are capped at 16, so it shows as 16. Scored zero for study design, sample size, studied in people and randomised / blinded because the record does not state it. We have no data on times cited, citations per year, impact for its field and year, cited by studies here, still being cited, senior author's track record, institution's track record and multi-centre collaboration, so those were left out: it earned 15 of the 62 points we could judge it on, which is 24 out of 100.
| Component | Points | Why |
|---|---|---|
| Journal tier | 2 / 10 | Tier 4 — not a peer-reviewed journal (Research Square) |
| Journal's citation record | 0 / 4 | Not a journal article, so the journal's record does not count |
| Study design | 0 / 12 | No study design recorded — scores zero, not guessed (not stated in the record — scored 0) |
| Strength of evidence | 1 / 5 | Rated “low” in our summary |
| Peer-review validation | 4 / 10 | Preprint — not yet peer-reviewed. Hosted on a preprint server. |
| How recent | 5 / 5 | 2026 — within 1 year(s) of the newest study here |
| Sample size | 0 / 4 | Participant count not stated — scores zero (not stated in the record — scored 0) |
| Effect reported | 2 / 3 | Effect reported as a number, without an interval or test |
| Studied in people | 0 / 3 | Not stated whether this was studied in people — scores zero (not stated in the record — scored 0) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | — / 7 | No citation count (not found in OpenAlex) — left out of this score |
| Citations per year | — / 5 | No citation count or no year — left out of this score |
| Impact for its field and year | — / 6 | No field-weighted citation impact (OpenAlex has none yet) — left out of this score |
| Cited by studies here | — / 6 | Not yet checked against this library's citation graph — left out of this score |
| Still being cited | — / 4 | No yearly citation counts — left out of this score |
| Senior author's track record | — / 4 | Senior author's record not available — left out of this score |
| Institution's track record | — / 3 | No institution listed in OpenAlex — left out of this score |
| Multi-centre collaboration | — / 3 | Institutions not listed — left out of this score |
| Indexed in PubMed | 1 / 2 | Not in PubMed, but has a DOI |
| Free to read | 0 / 2 | Behind a paywall — scores zero |
| Points | 15 / 62 | Scored on 12 of 20 parts. We have no data for the rest, so they are left out: 15 of the 62 points we could judge it on is 24 out of 100. |
| Total | 24 / 100 | Capped to 16 because this is not a peer-reviewed article. |
What each of these 20 components measures, and what this score is not →
Read the original
Free copy unknown: no free-copy check has an answer for this record yet. That does not mean it is paywalled.
Related studies in Digital health tools
Also tagged “convolutional”
205 studies in the library carry the topic tag “convolutional”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 205 tagged studies.