UT Southwestern Medical Center researchers found that AI-powered voice analysis can help identify Alzheimers and cognitive impairment in early stages, possibly supplying an efficient screening tool for main care providers if verified by larger research studies.
ODonnell Brain Institute scientist says findings might cause an easy screening test for early detection of cognitive disability.
New innovations that can record subtle changes in a clients voice might help doctors identify cognitive impairment and Alzheimers illness before signs begin to show, according to a UT Southwestern Medical Center scientist who led a research study published in the Alzheimers Association publication Diagnosis, Assessment & & Disease Monitoring.
” Our focus was on recognizing subtle language and audio modifications that are present in the really early stages of Alzheimers illness however not quickly identifiable by household members or a persons medical care doctor,” said Ihab Hajjar, M.D., Professor of Neurology at UT Southwesterns Peter ODonnell Jr.
Brain Institute. Researchers used innovative machine knowing and natural language processing (NLP) tools to examine speech patterns in 206 individuals– 114 who met the criteria for mild cognitive decrease and 92 who were unimpaired. The team then mapped those findings to typically utilized biomarkers to determine their efficacy in determining problems.
Study participants, who were registered in a research study program at Emory University in Atlanta, were provided a number of basic cognitive assessments before being asked to tape a spontaneous 1- to 2-minute description of artwork.
” The taped descriptions of the photo offered us with an approximation of conversational abilities that we could study by means of artificial intelligence to determine speech motor control, concept density, grammatical intricacy, and other speech features,” Dr. Hajjar said.
The research study group compared the individuals speech analytics to their cerebral spine fluid samples and MRI scans to determine how accurately the digital voice biomarkers detected both moderate cognitive impairment and Alzheimers disease status and progression.
” Prior to the advancement of maker learning and NLP, the detailed study of speech patterns in patients was very labor intensive and often not successful because the changes in the early phases are frequently undetectable to the human ear,” Dr. Hajjar stated. “This novel technique of screening carried out well in identifying those with mild cognitive impairment and more specifically in identifying patients with proof of Alzheimers disease– even when it can not be easily spotted utilizing standard cognitive evaluations.”
Throughout the study, scientists invested less than 10 minutes catching a patients voice recording. Standard neuropsychological tests typically take several hours to administer.
” If verified with larger studies, using synthetic intelligence and machine learning to study vocal recordings might provide medical care companies with an easy-to-perform screening tool for at-risk individuals,” Dr. Hajjar stated. “Earlier medical diagnoses would give patients and families more time to prepare for the future and offer clinicians higher flexibility in advising appealing lifestyle interventions.”
Recommendation: “Development of digital voice biomarkers and associations with cognition, cerebrospinal biomarkers, and neural representation in early Alzheimers illness” by Ihab Hajjar MD, MS, Maureen Okafor MD, MPH, Jinho D. Choi PhD, Elliot Moore II PhD, Anees Abrol PhD, Vince D. Calhoun PhD and Felicia C. Goldstein PhD, 5 February 2023, Diagnosis, Assessment & & Disease Monitoring.DOI: 10.1002/ dad2.12393.
Dr. Hajjar teamed up on this research study with a team of researchers at Emory, where he previously acted as Director of the Clinical Trial Unit of the Goizueta Alzheimers Disease Research Center before joining UTSW in 2022. He is continuing to collect voice recordings in Dallas as part of a follow-up study at UTSW being funded with a National Institutes of Health grant.
This research studys research study was supported by grants from the National Institutes of Health/National Institute on Aging (AG051633, AG057470-01, AG042127) and the Alzheimers Drug Discovery Foundation (20150603).
Dr. Hajjar holds the Pogue Family Distinguished University Chair in Alzheimers Disease Clinical Research and Care, in Memory of Maurine and David Weigers McMullan.
