Data‐driven staging and subtyping of genetic frontotemporal dementia using multi‐modal MRI
Bibliographic record
Abstract
Abstract Background Frontotemporal dementia is a highly heterogeneous disorder and neurodegeneration begins years prior to symptom onset, complicating disease understanding and treatment. Here we used an unsupervised machine learning algorithm to identify disease sub‐trajectories in genetic frontotemporal dementia. Method The contrastive trajectory inference (cTI, available at neuropm‐lab.com/neuropm‐box.html ) is a method to analyze temporal patterns in multi‐dimensional populational datasets, consisting of unsupervised feature selection, contrastive prinicipal component analysis and subject ordering to obtain individual disease severity scores and distinct subtypes. We applied the cTI to cross‐sectional MRI data (gray matter density, T1/T2 ratio, fALFF, gray matter fractional ansiotrophy and mean diffusivity) from 383 gene carriers (269 presymptomatic and 115 symptomatic) from the GENFI study (148 with C9orf72 expansions, 169 with GRN mutations, and 67 with MAPT mutations) and a control group of 253 non‐carriers. The cTI was applied to all modalities in combination and individually. We compared the obtained disease severity scores to the estimated years to onset (EYO; age ‐ mean age of onset in relatives), clinical, and neuropsychological test scores. cTI subtypes were compared to genetic variants, as gene variants have specific pathology and group‐level differences in neuroimaging. Result The cTI identified disease severity scores were significantly correlated with all clinical and neuropsychiatric tests (measuring behavioural symptoms, attention, memory, language, and executive function) for all modalities, in combination and individually, and for the EYO for all modalities except mean diffusivity. The combination of all modalities provided the best overall results (CBI: r = 0.581, p < 0.001; EYO: r = 0.321, p < 0.001) (figure 1). Among individual modalities, gray matter density performed best (CBI: r = 0.475, p < 0.001; EYO: r = 0.286, p < 0.001). The cTI did not recover the three genetic variants, instead assigning most gene carriers (> 80%) to subtype 1 (figure 2). The cTI distinguished non‐carriers from carriers (87% of non‐carriers are in subtype 2). Conclusion The cTI can identify disease severity in a heterogeneous sample of genetic FTD using only neuroimaging metrics. It is unable to uncover genetic variants, suggesting that genetic variants may have similar neuroimaging features at early presymptomatic stages.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".