AI Shows Promise for Detecting Early Cognitive Decline through Speech Samples | Elson S. Floyd College of Medicine News
Publish Date: 2026-03-17 14:25:00
Source Domain: medicine.wsu.edu
- Artificial intelligence via speech analysis shows promise in detecting early cognitive decline, according to research from Washington State University’s Elson S. Floyd College of Medicine.
- A pilot study presented at the American Speech-Language-Hearing Association (ASHA) Convention found that a machine learning model can identify individuals with cognitive decline in about 75% of cases.
- Speech analysis has emerged as a noninvasive and cost-effective screening tool for mild cognitive impairment, a risk factor for Alzheimer’s disease and related dementias.
- Early detection is crucial for interventions that can improve quality of life and maintain independence; currently, many older adults only seek care when symptoms affect their daily functioning.
- The study involved six older adults with mild to moderate cognitive impairment and six without, who completed a word fluency task analyzed by a machine learning model to assess acoustic features.
- The machine learning model K-Nearest Neighbors (KNN) moderately predicted cognitive impairment, classifying nine out of 12 participants correctly.
- Researchers are planning a broader study to improve model accuracy and enhance accessibility to screening, especially in rural communities.
- Machine learning models could supplement clinicians’ assessments and enable worldwide analysis of millions of speech samples.
