Home › Research › Digital health tools
Evaluating Large Language Model Diagnostic Classification in Neuropsychology
Hachem A, Chui C, Morgan ET, Bakre AS, Rolin S, Rios A, Davis J.. PsyArXiv, 2026-10-06
Topic: Brain imaging, connectivity and assessment
Model-inferred and reference diagnoses showed exact agreement rates from 18.8% to 56.2% with poor to slight chance-corrected agreement (Cohen’s κ = −.178 to .196). Classification errors across models were more often overclassification rather than underclassification. Using dichotomous cognitive status (i.e., normal versus impaired), seven of ten models showed sensitivity over 90% for identifying impairment, but specificity ranged from 0 to 60%. Workflow response time varied by model and was not associated with accuracy. Using unstructured and unannotated clinical interview data, general-purpose LLMs showed limited, model-dependent agreement with clinician diagnoses and a tendency to overclassify impairment. LLMs warrant further evaluation as tools that support clinical workflows, with revised prompting strategies and systematic efforts to improve classification.
Key findings
- Model-inferred and reference diagnoses showed exact agreement rates from 18.8% to 56.2% with poor to slight chance-corrected agreement (Cohen’s κ = −.178 to .196).
- Classification errors across models were more often overclassification rather than underclassification.
- Using dichotomous cognitive status (i.e., normal versus impaired), seven of ten models showed sensitivity over 90% for identifying impairment, but specificity ranged from 0 to 60%.
- Workflow response time varied by model and was not associated with accuracy.
- Using unstructured and unannotated clinical interview data, general-purpose LLMs showed limited, model-dependent agreement with clinician diagnoses and a tendency to overclassify impairment.
New to this subject? Start with our plain-English guide: Digital health →
Study details
- Effect size18.8% to 56.2%
- 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Preprint — not yet peer-reviewed.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 (PsyArXiv) |
| 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.
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. The record names 7 authors; APA and Vancouver show the first six, BibTeX and the downloads carry all of them. Check the citation against the original before you use it.
APA 7th
Hachem, A., Chui, C., Morgan, E. T., Bakre, A. S., Rolin, S., Rios, A., et al. (2026). Evaluating Large Language Model Diagnostic Classification in Neuropsychology. PsyArXiv. https://doi.org/10.31234/osf.io/6pmca_v1
Vancouver
Hachem A, Chui C, Morgan ET, Bakre AS, Rolin S, Rios A, et al. Evaluating Large Language Model Diagnostic Classification in Neuropsychology. PsyArXiv. 2026. doi:10.31234/osf.io/6pmca_v1.
BibTeX
@article{hachem2026-d0443277,
author = {Hachem, A. and Chui, C. and Morgan, E. T. and Bakre, A. S. and Rolin, S. and Rios, A. and Davis, J.},
title = {{Evaluating Large Language Model Diagnostic Classification in Neuropsychology}},
journal = {PsyArXiv},
year = {2026},
doi = {10.31234/osf.io/6pmca_v1},
url = {https://doi.org/10.31234/osf.io/6pmca_v1}
}