Positron emission tomography (PET) amyloid imaging has become an important part of the diagnostic workup for patients with primary progressive aphasia (PPA) and uncertain underlying pathology.
Connected speech is a linguistic term that is quite a synonym of "conversation". Analysis of connected speech shows sound changes affecting linguistic units.
Here, scientists employ a semi-automated analysis of connected speech (CS) with a twofold objective.
- First, to determine if quantitative connected speech features can help select primary progressive aphasia (PPA) patients with a higher probability of a positive PET amyloid imaging result.
- Second, to examine the relevant group differences from a clinical perspective.
117 connected speech samples from a well-characterised cohort of PPA patients who underwent PET amyloid imaging were collected. Expert consensus established PET amyloid status for each patient, and 40% of the sample was amyloid positive.
The scientists found that leave-one-out cross-validation yields 77% classification accuracy (sensitivity: 74%, specificity: 79%).
Their results seem to confirm the potential of connected speech analysis as a screening tool. Discriminant connected speech features from lexical, syntactic, pragmatic, and semantic domains are discussed.