Summary of AI Can Detect Early Signs of Alzheimer’s in Speech Patterns – Before Symptoms Begin To Show:
Researchers at UT Southwestern Medical Center have found that AI-powered voice analysis could help in the early detection of Alzheimer’s and cognitive impairment. The study involved 206 people, 114 of whom met the criteria for mild cognitive decline and 92 who were unimpaired. Researchers used machine learning and natural language processing tools to assess speech patterns, mapped to commonly used biomarkers to determine their efficacy in measuring impairment. Researchers found that the digital voice biomarkers accurately detected mild cognitive impairment and Alzheimer’s disease status and progression, even when it could not be easily detected using standard cognitive assessments.
*****
Artificial Intelligence May Help Diagnose Alzheimer’s and Cognitive Impairment
A recent study conducted by researchers at the UT Southwestern Medical Center has found that artificial intelligence (AI) may help doctors diagnose Alzheimer’s and cognitive impairment in patients. The study, published in the Alzheimer’s Association journal, Diagnosis, Assessment & Disease Monitoring, used advanced machine learning and natural language processing tools to assess speech patterns in 206 people, of which 114 had a mild cognitive decline, and 92 were unimpaired. The study showed that AI can detect subtle changes in speech patterns, often not visible to the human ear.
Subtle Changes in Speech Provide Tell-tale Sign
The study focused on identifying subtle changes in language and audio patterns present in the early stages of Alzheimer’s disease. Participants recorded a 1- to the 2-minute description of artwork to approximate their conversational abilities and “study via artificial intelligence to determine speech motor control, idea density, grammatical complexity, and other speech features,” Ihab Hajjar, M.D., said.
Efficient Screening Tool
Dr. Hajjar said, “If confirmed with larger studies, the use of artificial intelligence and machine learning to study vocal recordings could provide primary care providers with an easy-to-perform screening tool for at-risk individuals.” The early detection of cognitive impairment and Alzheimer’s disease would help patients and families to plan for the future and clinicians to recommend promising lifestyle interventions.
Less Time Consuming
During the study, researchers spent less than 10 minutes capturing the patient’s voice recording, which is a fraction of the time required for traditional neuropsychological tests. Standard cognitive assessments typically take several hours to administer.
Future Prospects
Dr. Hajjar, who is continuing to collect voice recordings in Dallas as part of a follow-up study at UT Southwestern, believes that if AI-based screening tools are confirmed with more extensive studies, they could offer an efficient screening tool for primary care providers to detect cognitive impairment and Alzheimer’s disease in patients at risk.
Funding
This study’s research was supported by grants from the National Institutes of Health/National Institute on Aging (AG051633, AG057470-01, AG042127) and the Alzheimer’s Drug Discovery Foundation (20150603).
Final Thoughts
The ability to detect cognitive impairment and Alzheimer’s disease before symptoms appear is essential to ensure that patients and families have sufficient time to obtain the necessary healthcare support. The AI-based voice analysis technology may offer an easy-to-perform screening tool for primary care providers to detect cognitive impairment and Alzheimer’s disease, making it possible to diagnose patients in the early stages and provide the appropriate care.
