This PET study has revealed the neural system involved in implicit face, proper-name and object name processing during an explicit visual 'same' versus 'different' matching task. Within the identified system, some areas were equally active irrespective of modality (faces or names) or type of stimuli (famous and non-famous) while other areas exhibited differential effects. Our findings support the hypothesis that faces and names involve differential pre-semantic processing prior to accessing a common neural system of stored knowledge of personal identity which overlaps with the one associated with object knowledge. The areas specialized for the perceptual analysis of faces (irrespective of whether they are famous or non-famous) are the right lingual and bilateral fusiform gyri, while the areas specialized for famous stimuli (irrespective of whether they are faces or names) spread from the left anterior temporal to the left temporoparietal regions. One specific area, the more lateral portion of the left anterior middle temporal gyrus, showed increased activation for famous faces relative to famous proper names and for famous proper names relative to common names. The differential responsiveness of this region when processing familiar people suggests functional segregation of either personal attributes or, more likely, the demands placed on processes that retrieve stored knowledge when stimuli have highly similar visual features but unique semantic associations.

Introduction Automated speech analysis has emerged as a scalable, cost‐effective tool to identify persons with Alzheimer's disease dementia (ADD). Yet, most research is undermined by low interpretability and specificity. Methods Combining statistical and machine learning analyses of natural speech data, we aimed to discriminate ADD patients from healthy controls (HCs) based on automated measures of domains typically affected in ADD: semantic granularity (coarseness of concepts) and ongoing semantic variability (conceptual closeness of successive words). To test for specificity, we replicated the analyses on Parkinson's disease (PD) patients. Results Relative to controls, ADD (but not PD) patients exhibited significant differences in both measures. Also, these features robustly discriminated between ADD patients and HC, while yielding near‐chance classification between PD patients and HCs. Discussion Automated discourse‐level semantic analyses can reveal objective, interpretable, and specific markers of ADD, bridging well‐established neuropsychological targets with digital assessment tools.

We describe results that show the effectiveness of machine learning in the automatic diagnosis of certain neurodegenerative diseases, several of which alter speech and language production. We analyzed audio from 9 control subjects and 30 patients diagnosed with one of three subtypes of Frontotemporal Lobar Degeneration. From this data, we extracted features of the audio signal and the words the patient used, which were obtained using our automated transcription technologies. We then automatically learned models that predict the diagnosis of the patient using these features. Our results show that learned models over these features predict diagnosis with accuracy significantly better than random. Future studies using higher quality recordings will likely improve these results.

Key Points Question Can widely available measures of atrophy on magnetic resonance imaging increase diagnostic certainty of underlying frontotemporal lobar degeneration (FTLD) and estimate clinical deterioration in the behavioral variant of frontotemporal dementia (bvFTD)? Findings This diagnostic/prognostic study investigated the clinical utility of 5 validated visual atrophy scales (VAS) and the Magnetic Resonance Parkinsonism Index. When combined, VAS showed excellent diagnostic performance for differentiating between bvFTD with high and low confidence of FTLD and for the estimation of longitudinal clinical deterioration, whereas the Magnetic Resonance Parkinsonism Index was increased in bvFTD with underlying 4-repeat tauopathies. Meaning These findings suggest that, in bvFTD, VAS can be used to increase diagnostic certainty of underlying FTLD and estimate longitudinal clinical deterioration.