Home › Research › Lewy body dementia
Diagnostic Value of Large Language Model-Extracted Gross Brain Findings in Neurodegenerative Diseases
Ono, D.; Dickson, D. W.; Koga, S.. medRxiv (preprint), 2026-09-14
Topic: Brain proteins, microglia and lab models
Gross brain findings help guide differential diagnosis, but their diagnostic value across major neurodegenerative diseases remains incompletely characterized. We evaluated whether gross descriptions in autopsy reports could classify cases by final neuropathologic diagnosis. We analyzed 5,613 autopsy cases from the Mayo Clinic Brain Bank collected between 1998 and 2023, including seven diagnostic categories: Alzheimer disease (AD), Lewy body disease (LBD), combined AD and LBD (AD-LBD), frontotemporal lobar degeneration, corticobasal degeneration, progressive supranuclear palsy (PSP), and multiple system atrophy (MSA). A fine-tuned large language model (LLM) converted narrative gross descriptions into semi-quantitative scores for 39 features. Extraction accuracy was 0.95 in 200 manually annotated feature-level test examples. A CatBoost classifier used the extracted scores as input, whereas a second fine-tuned LLM used standardized textual descriptions of the same features. Both classifiers also included age at death, sex, and brain weight. Performance was evaluated in the same held-out test set of 562 cases. CatBoost achieved an accuracy of 0.73, a Cohens kappa of 0.65, and a macro-average area under the receiver operating characteristic curve of 0.92. The text-based LLM achieved an accuracy of 0.75 and a kappa of 0.68. Macro-average sensitivity was 0.66 for both models. PSP sensitivity was 0.92 with CatBoost and 0.93 with text-based LLM. Corresponding sensitivities were 0.87 and 0.92 for MSA, but only 0.21 and 0.03 for AD-LBD. Feature attribution analysis identified subthalamic nucleus atrophy and putaminal abnormalities as contributors to PSP and MSA predictions, respectively. Narrative gross descriptions contained diagnostic information, particularly for disorders with distinctive macroscopic patterns, whereas combined AD-LBD remained difficult to distinguish.
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
APA 7th
Ono, D., Dickson, D. W., & Koga, S. (2026). Diagnostic Value of Large Language Model-Extracted Gross Brain Findings in Neurodegenerative Diseases. medRxiv (preprint). https://doi.org/10.64898/2026.09.12.26362866
Vancouver
Ono D, Dickson DW, Koga S. Diagnostic Value of Large Language Model-Extracted Gross Brain Findings in Neurodegenerative Diseases. medRxiv (preprint). 2026. doi:10.64898/2026.09.12.26362866.
BibTeX
@article{ono2026-f0890d90,
author = {Ono, D. and Dickson, D. W. and Koga, S.},
title = {{Diagnostic Value of Large Language Model-Extracted Gross Brain Findings in Neurodegenerative Diseases}},
journal = {medRxiv (preprint)},
year = {2026},
doi = {10.64898/2026.09.12.26362866},
url = {https://doi.org/10.64898/2026.09.12.26362866}
}
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
- Macro-average sensitivity was 0.66 for both models.
- PSP sensitivity was 0.92 with CatBoost and 0.93 with text-based LLM.
- Corresponding sensitivities were 0.87 and 0.92 for MSA, but only 0.21 and 0.03 for AD-LBD.
- Feature attribution analysis identified subthalamic nucleus atrophy and putaminal abnormalities as contributors to PSP and MSA predictions, respectively.
- Narrative gross descriptions contained diagnostic information, particularly for disorders with distinctive macroscopic patterns, whereas combined AD-LBD remained difficult to distinguish.
Why it matters
This study found that large language models could extract gross brain findings from autopsy reports to help classify neurodegenerative diseases, with high sensitivity for PSP and MSA but low sensitivity for combined Alzheimer's and Lewy body disease. It is a diagnostic aid, not a treatment, cure, or prevention.
Study details
- Participants5,613
- Evidence strengthLow
How this study scored 16/100
Preprint — not yet peer-reviewed. It scored 29 on the same rubric, but non-peer-reviewed sources are capped at 16, so it shows as 16. Scored zero for study design, effect reported and randomised / blinded because the record does not state it. We have no data on impact for its field and year, so that was left out: it earned 27 of the 94 points we could judge it on, which is 29 out of 100.
| Component | Points | Why |
|---|---|---|
| Journal tier | 2 / 10 | Tier 4 — not a peer-reviewed journal (medRxiv (preprint)) |
| 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 | 3 / 4 | 5,613 participants |
| Effect reported | 0 / 3 | No effect size reported — scores zero (not stated in the record — scored 0) |
| Studied in people | 3 / 3 | Studied in people (participant count stated) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 0 / 7 | Cited 0 times (OpenAlex, 2026-10-10) |
| Citations per year | 0 / 5 | 0.0 citations a year over 2 year(s) since 2026 |
| 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 | 0 / 6 | No other study in this library cites it |
| Still being cited | 0 / 4 | Cited 0 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 2 / 4 | Last-listed author Shunsuke Koga: h-index 42 (OpenAlex, whole career) |
| Institution's track record | 2 / 3 | University of Pennsylvania: institution h-index 1,859 (OpenAlex) |
| Multi-centre collaboration | 2 / 3 | OpenAlex lists 6 institution(s) in 2 countries |
| Indexed in PubMed | 1 / 2 | Not in PubMed, but has a DOI |
| Free to read | 2 / 2 | Free to read |
| Points | 27 / 94 | Scored on 19 of 20 parts. We have no data for the rest, so they are left out: 27 of the 94 points we could judge it on is 29 out of 100. |
| Total | 29 / 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
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here.
Related studies in Lewy body dementia
Also tagged “bodies”
1,017 studies in the library carry the topic tag “bodies”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 1,017 tagged studies.