首页|Tongji University Reports Findings in Alzheimer Disease (Automatic speech analys is for detecting cognitive decline of older adults)
Tongji University Reports Findings in Alzheimer Disease (Automatic speech analys is for detecting cognitive decline of older adults)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Neurodegenerative Dise ases and Conditions - Alzheimer Disease is the subject of a report. According to news reporting originating from Shanghai, People’s Republic of China, by NewsRx correspondents, research stated, “Speech analysis has been expected to help as a screening tool for early detection of Alzheimer’s disease (AD) and mild-cognit ively impairment (MCI). Acoustic features and linguistic features are usually us ed in speech analysis.” Our news editors obtained a quote from the research from Tongji University, “How ever, no studies have yet determined which type of features provides better scre ening effectiveness, especially in the large aging population of China. Firstly, to compare the screening effectiveness of acoustic features, linguistic feature s, and their combination using the same dataset. Secondly, to develop Chinese au tomated diagnosis model using self-collected natural discourse data obtained fro m native Chinese speakers. A total of 92 participants from communities in Shangh ai, completed MoCA-B and a picture description task based on the Cookie Theft un der the guidance of trained operators, and were divided into three groups includ ing AD, MCI, and heathy control (HC) based on their MoCA-B score. Acoustic featu res (Pitches, Jitter, Shimmer, MFCCs, Formants) and linguistic features (part-of -speech, type-token ratio, information words, information units) are extracted. The machine algorithms used in this study included logistic regression, random f orest (RF), support vector machines (SVM), Gaussian Naive Bayesian (GNB), and k- Nearest neighbor (kNN). The validation accuracies of the same ML model using aco ustic features, linguistic features, and their combination were compared. The ac curacy with linguistic features is generally higher than acoustic features in tr aining. The highest accuracy to differentiate HC and AD is 80.77% achieved by SVM, based on all the features extracted from the speech data, while the highest accuracy to differentiate HC and AD or MCI is 80.43% achieved by RF, based only on linguistic features.”
ShanghaiPeople’s Republic of ChinaAs iaAlzheimer DiseaseDiagnostics and ScreeningHealth and MedicineLegal Iss uesNeurodegenerative Diseases and Conditions
NETL
NSTL
