Artificial intelligence can identify subtle changes in speech patterns that indicate cognitive decline and Alzheimer’s illness before any symptoms show. According to a study that appeared in Alzheimer’s & Dementia: Diagnosis, Evaluation, and Disease Monitoring, speech patterns were analyzed using machine learning and natural language processing and then contrasted with MRI scans and samples of patients’ cerebral spinal fluid. This approach accurately detected mild cognitive impairment and identified individuals with evidence of Alzheimer’s. The use of AI and ML could provide primary care providers with an easy-to-perform screening tool for at-risk individuals.
Cognitive impairment and Alzheimer’s disease are debilitating conditions that affect millions of people worldwide. Diagnosing these conditions early can help patients and their families plan for the future, and clinicians can provide effective interventions. However, the early detection of cognitive impairment and Alzheimer’s disease remains challenging, as the early symptoms are often subtle and difficult to detect. In recent years, researchers have explored the use of artificial intelligence (AI) to help identify early markers of cognitive decline and Alzheimer’s disease, including changes in speech patterns. A new study published in Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring indicates that AI can help identify subtle changes in a patient’s voice and speech patterns, which may help clinicians diagnose cognitive impairment and Alzheimer’s disease before symptoms appear.
The study, led by Ihab Hajjar, MD, a Professor of Neurology at the University of Texas (UT) Southwestern’s Peter O’Donnell Jr. Brain Institute, focuses on identifying subtle language and audio changes that are present in the very early stages of Alzheimer’s disease but not easily recognizable by family members or an individual’s primary care physician. To achieve this goal, the research team used machine learning (ML) and natural language processing (NLP) to analyze the speech patterns of 206 people enrolled in a research program at Emory University, including 114 with mild cognitive decline and 92 deemed cognitively unimpaired.
From these patients, the researchers gathered information on their speech, cognitive functioning, neuroimaging, and cerebrospinal fluid-based Alzheimer’s biomarkers. One- to minute-long spontaneous recordings of people describing works of art were used to collect speech data. The recorded descriptions give a basic idea of conversational abilities, which the researchers may then evaluate with AI to spot characteristics like thought richness, motor control, and grammatical complexity.
The speech recordings were then analyzed using ML, and acoustic and lexical-semantic features were derived. These features were then compared to participants’ cerebral spinal fluid samples and MRI scans, allowing the researchers to map connections between the speech pattern changes, digital voice biomarkers, and other commonly used Alzheimer’s biomarkers. These comparisons were used to determine how accurately the digital voice biomarkers could detect mild cognitive impairment in addition to Alzheimer’s status and progression.
The approach performed well in detecting mild cognitive impairment and identifying participants with evidence of Alzheimer’s, even when such evidence could not be easily detected through the use of standard cognitive assessments. Using ML to analyze speech patterns could boost early detection of cognitive decline, the researchers explained, as studying speech patterns in patients is labor-intensive and often unsuccessful because of how such subtle changes in speech are often undetectable to the human ear. In this study, the research team spent less than 10 minutes capturing each patient’s voice recording, while traditional neuropsychological tests typically require several hours.
The researchers believe that if confirmed with larger studies, the use of AI and ML to study vocal recordings could provide primary care providers with an easy-to-perform screening tool for at-risk individuals. Early diagnoses would give patients and families more time to plan for the future and give clinicians greater flexibility in recommending promising lifestyle interventions.
This study is an example of how AI and ML can help drive Alzheimer’s research and care. Other institutions are also leveraging AI to drive Alzheimer’s research and care. In an interview with HealthITAnalytics, leadership from a new pilot program at Indiana University School of Medicine and Indiana University Health discussed how the project is leveraging AI-based digital screening tools to drive early detection of cognitive impairment in the primary care setting.
