Artificial intelligence in assessment of neurogenic communication disorders in geriatric care: A literature review.

Purpose: With medical advancements contributing to increased life expectancy, the growing geriatric population has heightened the need for speech–language pathology services to address neurogenic communication impairments. Artificial intelligence (AI) offers promising opportunities to augment care a...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of the All India Institute of Speech & Hearing Vol. 44; no. 2; pp. 102 - 110
Autor principal: Vora, Juhi
Formato: review tables/charts Journal Article
Publicado: Wolters Kluwer India Pvt Ltd Jul-Dec2025
Acceso en línea:Ver este registro en EBSCOhost
Descripción
Sumario:Purpose: With medical advancements contributing to increased life expectancy, the growing geriatric population has heightened the need for speech–language pathology services to address neurogenic communication impairments. Artificial intelligence (AI) offers promising opportunities to augment care and meet this rising demand. The purpose of this review was to synthesize current evidence on the use of AI in assessing neurogenic communication disorders in older adults. By focusing on clinical applications such as automatic speech recognition (ASR) and related AI tools, this review highlights their potential to improve efficiency, accessibility, and accuracy in assessment, while also addressing challenges to successful clinical integration. Materials and Methods: A literature review was performed using the keywords AI, ASR, aphasia, apraxia, and dysarthria on several databases, including PubMed, Google Scholar, and ASHA Journals Academy. Results: This review summarizes current attempts at incorporating AI in automating the detection and diagnosis of neurogenic communication disorders, including dysarthria, aphasia, and apraxia of speech. Conclusion: AI shows promise in the speech therapy field, in assisting with screening and evaluation of neurogenic communication disorders. However, clinical integration of these tools is challenging given their limitations with culturally and linguistically diverse datasets and concerns with ethical bias and data privacy.