Clinical Manifestations

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.

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.

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).

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.