Predicting follow‐up diagnosis of individuals presenting with uncertain sporadic bvFTD diagnosis
Bibliographic record
Abstract
BACKGROUND: Delays in the diagnosis of sporadic behavioral variant of frontotemporal dementia (s-bvFTD) are hindering clinical care and trial enrolment. This delay is attributed to the clinical heterogeneity of s-bvFTD and its overlap with primary psychiatric disorders (PPD). The DIPPA-FTD consortium aims to improve early diagnosis by including individuals with late-onset behavioral change with ambiguous diagnoses that might turn out to be s-bvFTD. Here, we aimed to predict the follow-up diagnosis of these ambiguous cases by applying principal component analysis (PCA) from baseline clinical assessment. METHOD: In a subset (ambiguous=16, s-bvFTD=33, PPD=57) of the ongoing DIPPA-FTD study (de Boer et al., JAD:2024;97(2):963-973), We applied PCA to baseline clinical data, including Addenbrooke's Cognitive Examination-III (ACEIII), Beck Depression Inventory-II (BDI-II), Ekman-35, FTDvsPPD Checklist, Social Norm Questionnaire (SNQ) and Trail Making Test A+B (TMT). We compared Principal Components (PCs) between diagnostic groups, and associations with clinician-rated diagnostic certainty were assessed. Optimal number of k=2 for final clustering was determined using the elbow method on k-means clustering of all 11 PCs. Data-driven clusters and follow-up diagnosis were used to evaluate diagnostic prediction accuracy. RESULT: The first principal component (PC1) explained 43.8% of the variance. Loadings of PC1 are shown in Figure 1. Significant differences were found in PC1 scores between bvFTD, PPD, and Ambiguous cases (all p <0.05, adjusted for multiple testing). Cluster 1 (PC1 mean sore 2.76) consisted predominantly of s-bvFTD cases (78.1%), while cluster 2 (PC1 mean score -1.19) predominantly consisted of PPD cases (73.0%). PC1 and PC2 were selected for a cluster plot (Figure 2). Higher PC1 scores correlated with greater diagnostic certainty for s-bvFTD, while lower PC1 scores indicated higher certainty for PPD (r = 0.74, p <0.001). Among n = 34 thus far known follow-up cases, six ambiguous cases from cluster 2 switched to PPD after one year; two ambiguous cases in cluster 1 and one ambiguous case in cluster 2 remained ambiguous at follow-up; none switched to s-bvFTD (see Figure 3). CONCLUSION: In this pilot, a data-driven approach identified baseline profiles for s-bvFTD and PPD, potentially aiding in an early accurate diagnosis of individuals presenting with late-life behavioral change.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".