Detecting post-stroke aphasia using EEG-based neural envelope tracking of natural speech

Abstract

After a stroke, approximately one-third of patients suffer from aphasia, a language disorder that impairs communication ability. The standard behavioral tests used to diagnose aphasia are time-consuming, require subjective interpretation, and have low ecological validity. As a consequence, comorbid cognitive problems present in individuals with aphasia can bias test results, generating a discrepancy between test outcomes and everyday-life language abilities. Neural tracking of the speech envelope is a promising tool for investigating brain responses to natural speech. The envelope of speech is crucial for speech understanding, encompassing cues for detecting and segmenting linguistic units, e.g., phrases, words and phonemes. In this study, we aimed to test the potential of the neural envelope tracking technique for detecting language impairments in aphasia. We recorded EEG from 27 individuals with aphasia in the chronic phase after stroke and 22 healthy controls while they listened to a 25-minute story. We quantified neural envelope tracking in a broadband frequency range as well as in the delta, theta, alpha, beta, and gamma frequency bands using mutual information analysis. Besides group differences in neural tracking measures, we also tested its suitability for detecting aphasia at the individual level using a support vector machine classifier. We further investigated the required recording length for the classifier to detect aphasia and to obtain reliable outcomes. Individuals with aphasia displayed decreased neural envelope tracking compared to healthy controls in the broad, delta, theta, and gamma band, which is in line with the assumed role of these bands in auditory and linguistic processing of speech. Neural tracking in these frequency bands effectively captured aphasia at the individual level, with a classification accuracy of 84% and an area under the curve of 88%. Moreover, we demonstrated that high-accuracy detection of aphasia can be achieved in a time-efficient (5-7 minutes) and highly reliable manner (split-half reliability correlations between R=0.62 and R=0.96 across frequency bands). Our study shows that neural envelope tracking of natural speech is an effective biomarker for language impairments in post-stroke aphasia. We demonstrated its potential as a diagnostic tool with high reliability, individual-level detection of aphasia, and time-efficient assessment. This work represents a significant step towards more automatic, objective, and ecologically valid assessments of language impairments in aphasia.

Exploring neural tracking of acoustic and linguistic speech representations in individuals with post-stroke aphasia

“…Once neural tracking in aphasia is better understood, the application potential of this method could be manifold. A study that is currently in preparation found that IWA can be distinguished from healthy controls with 83% accuracy based on neural envelope tracking with mutual information of only 5 to 7 minutes of EEG data (De Clercq et al, 2023). Looking a step further into the future, an aphasia diagnosis based on processing levels of different speech representations could complement behavioral diagnosis and inform speech-language pathologists further which functions should be trained in therapy.…”

“…Moreover, the method could be useful in the acute phase after stroke, when behavioral diagnostic tests are too exhausting for patients. This would still have to be tested in a clinically more compatible experimental setting in the future, but work by De Clercq et al (2023) shows that only few minutes of recording time would be needed to get reliable data. Additionally, articulatory speech representations (e.g., mouth aperture, tongue protrusion (Mitra et al, 2010)) could be investigated to analyze effects of production impairments in aphasia during listening.…”

Neural substrates and behavioral relevance of speech envelope tracking: evidence from post-stroke aphasia

“…In response to narratives, individuals with post-stroke aphasia (IWA) display decreased neural tracking of the envelope and linguistic speech representations (Kries et al, 2023a;De Clercq et al, 2023a, 2024b. Neural tracking measures further predicted aphasia at the individual level (De Clercq et al, 2023b), with prediction accuracy almost entirely driven by envelope tracking rather than linguistic tracking (De Clercq et al, 2024b). These findings may suggest a role for envelope tracking in language-related processes, given its ability to detect a language disorder through reduced envelope tracking measures.…”

“…Among various disorders, neural tracking has found application in the study of aphasia, a language disorder commonly caused by a stroke in the language-dominant left hemisphere of the brain (Papathanasiou and Coppens, 2017). In response to narratives, individuals with post-stroke aphasia (IWA) display decreased neural tracking of the envelope and linguistic speech representations (Kries et al, 2023a;De Clercq et al, 2023a, 2024b. Neural tracking measures further predicted aphasia at the individual level (De Clercq et al, 2023b), with prediction accuracy almost entirely driven by envelope tracking rather than linguistic tracking (De Clercq et al, 2024b).…”

Functional connectivity of stimulus-evoked brain responses to natural speech in post-stroke aphasia

“…Despite the existing evidence of neural envelope tracking as a biomarker for diverse language disorders, [21][22][23][24] research on post-stroke aphasia to date remains limited. In our most recent works, we used temporal response functions (TRF) 25 and temporal mutual information functions (TMIF) 26,27 as measures of neural tracking. The first consists of a linear model, where weights represent the amplitude of the brain response to the stimulus at different latencies; the latter is a statistical approach also capturing non-linear relationships between the EEG and the stimulus, and provides a more thorough assessment of neural tracking.…”