Automated detection of mild cognitive impairment and dementia from voice recordings: A natural language processing approach
- Boston University, MA (United States); OSTI
- Boston University, MA (United States)
- Boston University, MA (United States). School of Medicine
- Boston University, MA (United States). School of Medicine; Boston University, MA (United States). Framingham Heart Study
Automated computational assessment of neuropsychological tests would enable widespread, cost-effective screening for dementia. A novel natural language processing approach is developed and validated to identify different stages of dementia based on automated transcription of digital voice recordings of subjects’ neuropsychological tests conducted by the Framingham Heart Study (n = 1084). Transcribed sentences from the test were encoded into quantitative data and several models were trained and tested using these data and the participants’ demographic characteristics. Average area under the curve (AUC) on the held-out test data reached 92.6%, 88.0%, and 74.4% for differentiating Normal cognition from Dementia, Normal or Mild Cognitive Impairment (MCI) from Dementia, and Normal from MCI, respectively. The proposed approach offers a fully automated identification of MCI and dementia based on a recorded neuropsychological test, providing an opportunity to develop a remote screening tool that could be adapted easily to any language.
- Research Organization:
- Boston University, MA (United States); Fraunhofer USA Inc., Plymouth, MI (United States)
- Sponsoring Organization:
- Alzheimer's Association; American Heart Association; Boston University; Framingham Heart Study's National Heart, Lung, and Blood Institute; Karen Toffler Charitable Trust; National Institutes of Health (NIH); National Science Foundation (NSF); Office of Naval Research (ONR); USDOE; USDOE Advanced Research Projects Agency - Energy (ARPA-E)
- Grant/Contract Number:
- AR0001282; EE0009696
- OSTI ID:
- 1976265
- Alternate ID(s):
- OSTI ID: 1875204
- Journal Information:
- Alzheimer's & Dementia, Journal Name: Alzheimer's & Dementia Journal Issue: 3 Vol. 19; ISSN 1552-5260
- Publisher:
- WileyCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Tau Positron Emission Tomography for Predicting Dementia in Individuals With Mild Cognitive Impairment
Memory Concerns, Memory Performance and Risk of Dementia in Patients with Mild Cognitive Impairment
Journal Article
·
Sun Jun 09 20:00:00 EDT 2024
· JAMA Neurology
·
OSTI ID:2470703
Memory Concerns, Memory Performance and Risk of Dementia in Patients with Mild Cognitive Impairment
Journal Article
·
Sun Jul 13 20:00:00 EDT 2014
· PLoS ONE
·
OSTI ID:1627709