A syntax-lexicon trade-off in language production

Using explainable artificial intelligence to identify linguistic biomarkers of amyloid pathology in primary progressive aphasia

Introduction

Recent success has been achieved in Alzheimer's disease (AD) clinical trials targeting amyloid beta (β), demonstrating a reduction in the rate of cognitive decline. However, testing methods for amyloid-β positivity are currently costly or invasive, motivating the development of accessible screening approaches to steer patients toward appropriate diagnostic tests. Here, we employ a pre-trained language model (Distil-RoBERTa) to identify amyloid-β positivity from a short, connected speech sample. We further use explainable AI (XAI) methods to extract interpretable linguistic features that can be employed in clinical practice.

Methods

We obtained language samples from 74 patients with primary progressive aphasia (PPA) across its three variants. Amyloid-β positivity was established through the analysis of cerebrospinal fluid, amyloid PET, or autopsy. 51% of the sample was amyloid-positive. We trained Distil-RoBERTa for 16 epochs with a batch size of 6 and a learning rate of 5e-5, and used the LIME algorithm to train interpretation models to interpret the trained classifier's inference conditions.

Results

Over ten runs of 10-fold cross-validation, the classifier achieved a mean accuracy of 92%, SD = 0.01. Interpretation models were able to capture the classifier's behavior well, achieving an accuracy of 97% against classifier predictions, and uncovering several novel speech patterns that may characterize amyloid-β positivity.

Discussion

Our work improves previous research which indicates connected speech is a useful diagnostic input for prediction of the presence of amyloid-β in patients with PPA. Further, we leverage XAI techniques to reveal novel linguistic features that can be tested in clinical practice in the appropriate subspecialty setting. Computational linguistic analysis of connected speech shows great promise as a novel assessment method in patients with AD and related disorders.

Automatic classification of AD pathology in FTD phenotypes using natural speech

INTRODUCTION

Screening for Alzheimer's disease neuropathologic change (ADNC) in individuals with atypical presentations is challenging but essential for clinical management. We trained automatic speech-based classifiers to distinguish frontotemporal dementia (FTD) patients with ADNC from those with frontotemporal lobar degeneration (FTLD).

METHODS

We trained automatic classifiers with 99 speech features from 1 minute speech samples of 179 participants (ADNC = 36, FTLD = 60, healthy controls [HC] = 89). Patients' pathology was assigned based on autopsy or cerebrospinal fluid analytes. Structural network-based magnetic resonance imaging analyses identified anatomical correlates of distinct speech features.

RESULTS

Our classifier showed 0.88 ± $ \pm $ 0.03 area under the curve (AUC) for ADNC versus FTLD and 0.93 ± $ \pm $ 0.04 AUC for patients versus HC. Noun frequency and pause rate correlated with gray matter volume loss in the limbic and salience networks, respectively.

DISCUSSION

Brief naturalistic speech samples can be used for screening FTD patients for underlying ADNC in vivo. This work supports the future development of digital assessment tools for FTD.

HIGHLIGHTS

We trained machine learning classifiers for frontotemporal dementia patients using natural speech. We grouped participants by neuropathological diagnosis (autopsy) or cerebrospinal fluid biomarkers. Classifiers well distinguished underlying pathology (Alzheimer's disease vs. frontotemporal lobar degeneration) in patients. We identified important features through an explainable artificial intelligence approach. This work lays the groundwork for a speech-based neuropathology screening tool.

Language Abnormalities in Alzheimer's Disease Arise from Reduced Informativeness: A Cross-Linguistic Study in English and Persian

INTRODUCTION

This research investigates the psycholinguistic origins of language impairments in Alzheimer's Disease (AD), questioning if these impairments result from language-specific structural disruptions or from a universal deficit in generating meaningful content.

METHODS

Cross-linguistic analysis was conducted on language samples from 184 English and 52 Persian speakers, comprising both AD patients and healthy controls, to extract various language features. Furthermore, we introduced a machine learning-based metric, Language Informativeness Index (LII), to quantify informativeness.

RESULTS

Indicators of AD in English were found to be highly predictive of AD in Persian, with a 92.3% classification accuracy. Additionally, we found robust correlations between the typical linguistic abnormalities of AD and language emptiness (low LII) across both languages.

DISCUSSION

Findings suggest AD linguistics impairments are attributed to a core universal difficulty in generating informative messages. Our approach underscores the importance of incorporating biocultural diversity into research, fostering the development of inclusive diagnostic tools.

Language uncovers visuospatial dysfunction in posterior cortical atrophy: a natural language processing approach

Introduction

Posterior Cortical Atrophy (PCA) is a syndrome characterized by a progressive decline in higher-order visuospatial processing, leading to symptoms such as space perception deficit, simultanagnosia, and object perception impairment. While PCA is primarily known for its impact on visuospatial abilities, recent studies have documented language abnormalities in PCA patients. This study aims to delineate the nature and origin of language impairments in PCA, hypothesizing that language deficits reflect the visuospatial processing impairments of the disease.

Methods

We compared the language samples of 25 patients with PCA with age-matched cognitively normal (CN) individuals across two distinct tasks: a visually-dependent picture description and a visually-independent job description task. We extracted word frequency, word utterance latency, and spatial relational words for this comparison. We then conducted an in-depth analysis of the language used in the picture description task to identify specific linguistic indicators that reflect the visuospatial processing deficits of PCA.

Results

Patients with PCA showed significant language deficits in the visually-dependent task, characterized by higher word frequency, prolonged utterance latency, and fewer spatial relational words, but not in the visually-independent task. An in-depth analysis of the picture description task further showed that PCA patients struggled to identify certain visual elements as well as the overall theme of the picture. A predictive model based on these language features distinguished PCA patients from CN individuals with high classification accuracy.

Discussion

The findings indicate that language is a sensitive behavioral construct to detect visuospatial processing abnormalities of PCA. These insights offer theoretical and clinical avenues for understanding and managing PCA, underscoring language as a crucial marker for the visuospatial deficits of this atypical variant of Alzheimer's disease.

Using Generative Artificial Intelligence to Classify Primary Progressive Aphasia from Connected Speech

Neurodegenerative dementia syndromes, such as Primary Progressive Aphasias (PPA), have traditionally been diagnosed based in part on verbal and nonverbal cognitive profiles. Debate continues about whether PPA is best subdivided into three variants and also regarding the most distinctive linguistic features for classifying PPA variants. In this study, we harnessed the capabilities of artificial intelligence (AI) and natural language processing (NLP) to first perform unsupervised classification of concise, connected speech samples from 78 PPA patients. Large Language Models discerned three distinct PPA clusters, with 88.5% agreement with independent clinical diagnoses. Patterns of cortical atrophy of three data-driven clusters corresponded to the localization in the clinical diagnostic criteria. We then used NLP to identify linguistic features that best dissociate the three PPA variants. Seventeen features emerged as most valuable for this purpose, including the observation that separating verbs into high and low-frequency types significantly improves classification accuracy. Using these linguistic features derived from the analysis of brief connected speech samples, we developed a classifier that achieved 97.9% accuracy in predicting PPA subtypes and healthy controls. Our findings provide pivotal insights for refining early-stage dementia diagnosis, deepening our understanding of the characteristics of these neurodegenerative phenotypes and the neurobiology of language processing, and enhancing diagnostic evaluation accuracy.

Language Uncovers Visuospatial Dysfunction in Posterior Cortical Atrophy: A Natural Language Processing Approach

Introduction

Posterior Cortical Atrophy (PCA) is a syndrome characterized by a progressive decline in higher-order visuospatial processing, leading to symptoms such as space perception deficit, simultanagnosia, and object perception impairment. While PCA is primarily known for its impact on visuospatial abilities, recent studies have documented language abnormalities in PCA patients. This study aims to delineate the nature and origin of language impairments in PCA, hypothesizing that language deficits reflect the visuospatial processing impairments of the disease.

Methods

We compared the language samples of 25 patients with PCA with age-matched cognitively normal (CN) individuals across two distinct tasks: a visually-dependent picture description and a visually-independent job description task. We extracted word frequency, word utterance latency, and spatial relational words for this comparison. We then conducted an in-depth analysis of the language used in the picture description task to identify specific linguistic indicators that reflect the visuospatial processing deficits of PCA.

Results

Patients with PCA showed significant language deficits in the visually-dependent task, characterized by higher word frequency, prolonged utterance latency, and fewer spatial relational words, but not in the visually-independent task. An in-depth analysis of the picture description task further showed that PCA patients struggled to identify certain visual elements as well as the overall theme of the picture. A predictive model based on these language features distinguished PCA patients from CN individuals with high classification accuracy.

Discussion

The findings indicate that language is a sensitive behavioral construct to detect visuospatial processing abnormalities of PCA. These insights offer theoretical and clinical avenues for understanding and managing PCA, underscoring language as a crucial marker for the visuospatial deficits of this atypical variant of Alzheimer's disease.

Measuring Sentence Information via Surprisal: Theoretical and Clinical Implications in Nonfluent Aphasia

OBJECTIVE

Nonfluent aphasia is characterized by simplified sentence structures and word-level abnormalities, including reduced use of verbs and function words. The predominant belief about the disease mechanism is that a core deficit in syntax processing causes both structural and word-level abnormalities. Here, we propose an alternative view based on information theory to explain the symptoms of nonfluent aphasia. We hypothesize that the word-level features of nonfluency constitute a distinct compensatory process to augment the information content of sentences to the level of healthy speakers. We refer to this process as lexical condensation.

METHODS

We use a computational approach based on language models to measure sentence information through surprisal, a metric calculated by the average probability of occurrence of words in a sentence, given their preceding context. We apply this method to the language of patients with nonfluent primary progressive aphasia (nfvPPA; n = 36) and healthy controls (n = 133) as they describe a picture.

RESULTS

We found that nfvPPA patients produced sentences with the same sentence surprisal as healthy controls by using richer words in their structurally impoverished sentences. Furthermore, higher surprisal in nfvPPA sentences correlated with the canonical features of agrammatism: a lower function-to-all-word ratio, a lower verb-to-noun ratio, a higher heavy-to-all-verb ratio, and a higher ratio of verbs in -ing forms.

INTERPRETATION

Using surprisal enables testing an alternative account of nonfluent aphasia that regards its word-level features as adaptive, rather than defective, symptoms, a finding that would call for revisions in the therapeutic approach to nonfluent language production. ANN NEUROL 2023;94:647-657.

Automated analysis of written language in the three variants of primary progressive aphasia

Despite the important role of written language in everyday life, abnormalities in functional written communication have been sparsely investigated in primary progressive aphasia. Prior studies have analysed written language separately in each of the three variants of primary progressive aphasia-but have rarely compared them to each other or to spoken language. Manual analysis of written language can be a time-consuming process. We therefore developed a program that quantifies content units and total units in written or transcribed language samples. We analysed written and spoken descriptions of the Western Aphasia Battery picnic scene, based on a predefined content unit corpus. We calculated the ratio of content units to units as a measure of content density. Our cohort included 115 participants (20 controls for written, 20 controls for spoken, 28 participants with nonfluent variant primary progressive aphasia, 30 for logopenic variant and 17 for semantic variant). Our program identified content units with a validity of 99.7% (95%CI 99.5-99.8). All patients wrote fewer units than controls (P < 0.001). Patients with the logopenic variant (P = 0.013) and the semantic variant (0.004) wrote fewer content units than controls. The content unit-to-unit ratio was higher in the nonfluent and semantic variants than controls (P = 0.019), but no difference in the logopenic variant (P = 0.962). Participants with the logopenic (P < 0.001) and semantic (P = 0.04) variants produced fewer content units in written compared to spoken descriptions. All variants produced fewer units in written samples compared to spoken (P < 0.001). However, due to a relatively smaller decrease in written content units, we observed a larger content unit-to-unit ratio in writing over speech (P < 0.001). Written and spoken content units (r = 0.5, P = 0.009) and total units (r = 0.64, P < 0.001) were significantly correlated in patients with nonfluent variant, but this was not the case for logopenic or semantic. Considering all patients with primary progressive aphasia, fewer content units were produced in those with greater aphasia severity (Progressive Aphasia Severity Scale Sum of Boxes, r = -0.24, P = 0.04) and dementia severity (Clinical Dementia Rating scale Sum of Boxes, r = -0.34, P = 0.004). In conclusion, we observed reduced written content in patients with primary progressive aphasia compared to controls, with a preference for content over non-content units in patients with the nonfluent and semantic variants. We observed a similar 'telegraphic' style in both language modalities in patients with the nonfluent variant. Lastly, we show how our program provides a time-efficient tool, which could enable feedback and tracking of writing as an important feature of language and cognition.

Agrammatic output in non-fluent, including Broca's, aphasia as a rational behavior

Background

Speech of individuals with non-fluent, including Broca's, aphasia is often characterized as "agrammatic" because their output mostly consists of nouns and, to a lesser extent, verbs and lacks function words, like articles and prepositions, and correct morphological endings. Among the earliest accounts of agrammatic output in the early 1900s was the "economy of effort" idea whereby agrammatic output is construed as a way of coping with increases in the cost of language production. This idea resurfaced in the 1980s, but in general, the field of language research has largely focused on accounts of agrammatism that postulated core deficits in syntactic knowledge.

Aims

We here revisit the economy of effort hypothesis in light of increasing emphasis in cognitive science on rational and efficient behavior.

Main contribution

The critical idea is as follows: there is a cost per unit of linguistic output, and this cost is greater for patients with non-fluent aphasia. For a rational agent, this increase leads to shorter messages. Critically, the informative parts of the message should be preserved and the redundant ones (like the function words and inflectional markers) should be omitted. Although economy of effort is unlikely to provide a unifying account of agrammatic output in all patients-the relevant population is too heterogeneous and the empirical landscape too complex for any single-factor explanation-we argue that the idea of agrammatic output as a rational behavior was dismissed prematurely and appears to provide a plausible explanation for a large subset of the reported cases of expressive aphasia.

Conclusions

The rational account of expressive agrammatism should be evaluated more carefully and systematically. On the basic research side, pursuing this hypothesis may reveal how the human mind and brain optimize communicative efficiency in the presence of production difficulties. And on the applied side, this construal of expressive agrammatism emphasizes the strengths of some patients to flexibly adapt utterances in order to communicate in spite of grammatical difficulties; and focusing on these strengths may be more effective than trying to "fix" their grammar.