Distinct neurolinguistic signatures of patients with acquired neurological conditions:. An open library of clinically relevant linguistic biomarkers

Background: Differentiating language impairments caused by neurological conditions such as left hemisphere damage (LHD), right hemisphere damage (RHD), dementia, Mild Cognitive Impairment (MCI), and Traumatic Brain Injury (TBI) is a clinical challenge. Objective: This study utilizes automated computational analysis of spoken discourse to identify distinct linguistic profiles that can distinguish between these conditions and healthy individuals. Methods: One of the largest databases ever composed of linguistic biomarkers (291 language measures) calculated produced by 1,394 participants. Specifically, we analyzed the following participant groups: 536 individuals with aphasia secondary to LHD, 193 individuals with dementia, 107 individuals with MCI, 38 individuals with RHD, 58 individuals with TBI, and 498 Healthy Controls. Employing natural language processing (NLP) via the Open Brain AI platform (http://openbrainai.com), we extracted multiple linguistic features from the speech samples, including readability, lexical richness, phonology, morphology, syntax, and semantics. Results: Our analysis revealed distinct linguistic patterns for each condition. Individuals with LHD exhibited widespread language deficits, while those with dementia and MCI showed pervasive impairments in lexical and syntactic domains. In contrast, TBI and RHD were associated with more selective deficits. Conclusions: These findings highlight the potential of automated computational analysis to supply objective linguistic signatures, thereby improving differential diagnosis, patient monitoring, and the development of tailored intervention strategies for neurological disorders.