Automatic Subtyping of Individuals with Primary Progressive Aphasia.

BACKGROUND: The classification of patients with primary progressive aphasia (PPA) into variants is time-consuming, costly, and requires combined expertise by clinical neurologists, neuropsychologists, speech pathologists, and radiologists. OBJECTIVE: The aim of the present study is to determine whether acoustic and linguistic variables provide accurate classification of PPA patients into one of three variants: nonfluent PPA, semantic PPA, and logopenic PPA. METHODS: In this paper, we present a machine learning model based on deep neural networks (DNN) for the subtyping of patients with PPA into three main variants, using combined acoustic and linguistic information elicited automatically via acoustic and linguistic analysis. The performance of the DNN was compared to the classification accuracy of Random Forests, Support Vector Machines, and Decision Trees, as well as to expert clinicians' classifications. RESULTS: The DNN model outperformed the other machine learning models as well as expert clinicians' classifications with 80% classification accuracy. Importantly, 90% of patients with nfvPPA and 95% of patients with lvPPA was identified correctly, providing reliable subtyping of these patients into their corresponding PPA variants. CONCLUSION: We show that the combined speech and language markers from connected speech productions can inform variant subtyping in patients with PPA. The end-to-end automated machine learning approach we present can enable clinicians and researchers to provide an easy, quick, and inexpensive classification of patients with PPA.

The use of spelling for variant classification in primary progressive aphasia: Theoretical and practical implications.

Currently, variant subtyping in primary progressive aphasia (PPA) requires an expert neurologist and extensive language and cognitive testing. Spelling impairments appear early in the development of the disorder, and the three PPA variants (non-fluent - nfvPPA; semantic - svPPA; logopenic - lvPPA) reportedly show fairly distinct spelling profiles. Given the theoretical and empirical evidence indicating that spelling may serve as a proxy for spoken language, the current study aimed to determine whether spelling performance alone, when evaluated with advanced statistical analyses, allows for accurate PPA variant classification. A spelling to dictation task (with real words and pseudowords) was administered to 33 PPA individuals: 17 lvPPA, 10 nfvPPA, 6 svPPA. Using machine learning classification algorithms, we obtained pairwise variant classification accuracies that ranged between 67 and 100%. In additional analyses that assumed no prior knowledge of each case's variant, classification accuracies ranged between 59 and 70%. To our knowledge, this is the first time that all the PPA variants, including the most challenging logopenic variant, have been classified with such high accuracy when using information from a single language task. These results underscore the rich structure of the spelling process and support the use of a spelling task in PPA variant classification.

Behavioural and neuropsychiatric disturbance in three clinical subtypes of frontotemporal dementia: A Clinical Research Center for Dementia of South Korea-FTD Study.

OBJECTIVES: To characterise the behavioural and neuropsychiatric disturbances of patients with three clinical subtypes of frontotemporal dementia (FTD): behavioural variant FTD (bvFTD), semantic dementia (SD) and progressive non-fluent aphasia (PNFA). METHODS: Consecutive series of 66 patients with bvFTD, 58 patients with SD and 21 patients with PNFA were compared using the Frontal Behavioural Inventory (FBI) and the Neuropsychiatric Inventory (NPI). RESULTS: Patients with bvFTD had more behavioural and neuropsychiatric disturbances than patients with PNFA based on the total scores of FBI and NPI. When comparing subtotal and item scores of FBI and NPI, there were some significant differences among three clinical subtypes of FTD. CONCLUSION: There are some distinct patterns of behavioural and neuropsychiatric disturbance among three clinical subtypes of FTD.

Towards a clearer definition of logopenic progressive aphasia.

Logopenic progressive aphasia is the most recently described clinical variant of primary progressive aphasia (PPA), defined by impairment of lexical retrieval and sentence repetition. Unlike other PPA variants, the logopenic variant of PPA (lv-PPA) is commonly associated with Alzheimer's disease (AD), a fact that is relevant to the selection of patients for clinical trials and disease-modifying therapies. Despite the straightforward definition and coherent pathological association, the existence of lv-PPA has been challenged, as its distinction from AD or other PPA variants can be difficult. Despite these issues, lv-PPA patients display characteristic linguistic deficits, a pattern of brain atrophy, and possibly genetic susceptibility, which warrant considering this variant as a discrete AD endophenotype. More specific clinical and anatomical markers can strengthen the consistency of this syndrome.

MRI signatures of brain macrostructural atrophy and microstructural degradation in frontotemporal lobar degeneration subtypes.

Brain magnetic resonance imaging (MRI) studies have demonstrated regional patterns of brain macrostructural atrophy and white matter microstructural alterations separately in the three major subtypes of frontotemporal lobar degeneration (FTLD), which includes behavioral variant frontotemporal dementia (bvFTD), semantic dementia (SD), and progressive nonfluent aphasia (PNFA). This study was to investigate to what extent the pattern of white matter microstructural alterations in FTLD subtypes mirrors the pattern of brain atrophy, and to compare the ability of various diffusion tensor imaging (DTI) indices in characterizing FTLD patients, as well as to determine whether DTI measures provide greater classification power for FTLD than measuring brain atrophy. Twenty-five patients with FTLD (13 with bvFTD, 6 with SD, and 6 with PNFA) and 19 healthy age-matched control subjects underwent both structural MRI and DTI scans. Measurements of regional brain atrophy were based on T1-weighted MRI data and voxel-based morphometry. Measurements of regional white matter degradation were based on voxelwise as well as regions-of-interest tests of DTI variations, expressed as fractional anisotropy, axial diffusivity, and radial diffusivity. Compared to controls, bvFTD, SD, and PNFA patients each exhibited characteristic regional patterns of brain atrophy and white matter damage. DTI overall provided significantly greater accuracy for FTLD classification than brain atrophy. Moreover, radial diffusivity was more sensitive in assessing white matter damage in FTLD than other DTI indices. The findings suggest that DTI in general and radial diffusivity in particular are more powerful measures for the classification of FTLD patients from controls than brain atrophy.

[Aphasia and related impairments pertaining to FTLD].

FTLD consists of three clinical types: behavioural variant FTD, progressive non-fluent aphasia (PNFA) and semantic dementia (SD). The latter two types manifest aphasia. Thus, it is quite important to pertinently assess the symptoms of aphasia and related impairments for diagnosis of FTLD. The most important point for diagnosis of PNFA is existence of anarthria/apraxia of speech, which is a focal symptom of the left prefrontal gyrus and underlying white matter. With the progression of the disease word generation and comprehension is deteriorating. SD shows Gogi aphasia when the lesion have predilection of left temporal lober atrophy. We investigated 28 patients without any antecedents causing speech/language impairments, who developed primary progressive aphasia. All the patients underwent a routine neurological and neuropsychological examinations and related symptoms such as orofacial apraxia, frontal lobe signs, dysphasia and so on were assessed. The results indicated that 20 patients were diagnosed as PNFA, and they were subdivided into three clinical groups. One group developed naming impairment and orofacial apraxia in several years after onset, and followed with various frontal symptoms. Another group showed anterior opereculum syndromes within two years after onset. The third group retained pure anarthria/apraxia of speech for many years without any other symptoms.

Distinct brain perfusion pattern associated with CSF biomarkers profile in primary progressive aphasia.

OBJECTIVE: A new classification of primary progressive aphasia (PPA) was recently proposed to differentiate between non-fluent aphasia (NF-PPA), semantic variant of PPA (S-PPA) and logopenic aphasia (LPA) by their phenotypic presentations. CSF biomarkers (BM) may differentiate PPA with atypical Alzheimer's disease (AD) that presents with LPA from PPA with frontotemporal lobe degeneration that presents with either NF-PPA or S-PPA. Single photon emission computed tomography (SPECT) was used to investigate brain hypoperfusion differences among PPA subtypes according to their CSF AD profiles. METHODS: 34 PPA patients underwent lumbar puncture and brain perfusion SPECT. PPA patients were classified into two subgroups according to the Aß(42):tau ratio: PPA BM positive (with an AD CSF profile) and PPA BM negative (not having an AD CSF profile). The biological classification was made while blind to the phenotypical presentation. The brain perfusion profiles of the PPA subgroups were compared with those of 24 healthy subjects. RESULTS: PPA BM positive patients had left-side predominant hypoperfusion in the temporoparietal cortex that extended to the dorsolateral prefrontal cortex and perisylvian region while PPA BM negative patients had hypoperfusion that was predominant in the temporal poles (p<10(-4) corrected). CONCLUSION: Distinct hypoperfusion patterns in PPA BM positive and PPA BM negative patients were observed, similar to those that have been described for S-PPA and LPA. These results support using CSF biomarkers to classify PPA.

The non-fluent/agrammatic variant of primary progressive aphasia.

The non-fluent/agrammatic variant of primary progressive aphasia (naPPA) is a young-onset neurodegenerative disorder characterised by poor grammatical comprehension and expression and a disorder of speech sound production. In an era of disease-modifying treatments, the identification of naPPA might be an important step in establishing a specific cause of neurodegenerative disease. However, difficulties in defining the characteristic language deficits and heterogeneity in the anatomical distribution of disease in naPPA have led to controversy. Findings from imaging studies have linked an impairment of this uniquely human language capacity with disruption of large-scale neural networks centred in left inferior frontal and anterior superior temporal regions. Accordingly, the pathological burden of disease in naPPA is anatomically focused in these regions. Most cases of naPPA are associated with the spectrum of pathological changes found in frontotemporal lobar degeneration involving the microtubule-associated protein tau. Knowledge of these unique clinical-pathological associations should advance care for patients with this important class of neurodegenerative diseases while supplementing our knowledge of human cognitive neuroscience.

Syndromes of nonfluent primary progressive aphasia: a clinical and neurolinguistic analysis.

BACKGROUND: Despite recent work, the nosology of nonfluent primary progressive aphasia (PPA) remains unresolved. METHODS: We describe a clinical and neurolinguistic cross-sectional analysis of a cohort of 24 patients with nonfluent PPA. Patients were initially classified based on analysis of spontaneous speech into 4 groups: apraxia of speech (AOS)/agrammatism (10 patients); AOS/no agrammatism (4 patients); no AOS/agrammatism (3 patients); no AOS/no agrammatism (7 patients). These groups were further characterized using a detailed neurolinguistic and neuropsychological battery. Parkinsonism was present in 3/10 patients in the AOS/agrammatism group. All patients in the no AOS/agrammatism group had mutations in the progranulin (GRN) gene, while 5/7 cases in the no AOS/no agrammatism group had CSF findings compatible with Alzheimer disease. RESULTS: The groups without AOS showed more severe neurolinguistic impairments for a given disease stage, and sentence comprehension, speech repetition, and reading were impaired in all groups. Prolonged word-finding pauses and impaired single word comprehension were salient features in the no AOS/agrammatism group. Additional impairments of executive function and praxis were present in both groups with agrammatism, and impaired episodic memory was a feature of the no AOS/no agrammatism group. CONCLUSION: PPA with AOS is aligned with the syndrome previously designated progressive nonfluent aphasia; agrammatism may emerge as the syndrome evolves, or alternatively, the pure AOS group may be pathophysiologically distinct. PPA without AOS resembles the syndrome designated logopenic/phonologic aphasia; however, there is evidence for a distinct subsyndrome of GRN-associated aphasia. The findings provide a rationale for further longitudinal studies with pathologic correlation.