2024-01-04| R&DTechnology

Revolutionary Wristband Sensor Technology Predicts Alzheimer’s Risk

by Sinead Huang
Share To

Japanese researchers at Oita University and pharmaceutical company Eisai Co., Ltd. have achieved a milestone in Alzheimer’s disease (AD) research. They’ve unveiled the world’s first machine learning model designed to predict the accumulation of amyloid beta (Aβ) in the brain, a crucial indicator of AD. What makes this development extraordinary is the utilization of a wristband sensor, allowing for non-invasive and convenient data collection.

Innovative Integration of Biological and Lifestyle Data

Unlike previous studies focusing on cognitive tests, blood tests, and brain imaging, this research uniquely incorporates “biological data” and “lifestyle data” to predict brain Aβ accumulation. By integrating information from wristband sensors, including physical activity, sleep patterns, and heart rate, with lifestyle data gathered through medical consultations, such as daily routines and background information, the model achieves a comprehensive understanding of an individual’s risk factors.

The study, detailed in the online edition of Alzheimer’s Research & Therapy, involved a cohort of elderly individuals without dementia. Over a three-year period, 122 participants with mild cognitive impairment wore wristband sensors, providing continuous data. The machine learning model, incorporating support vector machine, Elastic Net, and logistic regression, demonstrated an impressive Area Under the Curve (AUC) of 0.79. This suggests the model’s effectiveness in predicting amyloid positivity, offering an accessible and cost-effective screening method.

Implications for Alzheimer’s Research and Future Developments

The implications of this research extend beyond the immediate breakthrough. With Alzheimer’s prevalence rising, especially in aging societies like Japan, the development of predictive tools becomes increasingly crucial. The newly developed model not only offers a less invasive alternative to existing detection methods but also presents an opportunity to identify individuals with pre-symptomatic mild cognitive impairment. The integration of algorithms revealed common factors contributing to Aβ accumulation prediction, paving the way for further refinements and broader applications in dementia research.

This revolutionary predictive model marks a significant leap forward in Alzheimer’s research, emphasizing the importance of innovative technologies in the quest for early detection and intervention. The intersection of machine learning, wearable devices, and medical data opens up new possibilities for addressing the challenges posed by neurodegenerative diseases.

© All rights reserved. Collaborate with us:
Related Post
Preventive Medicine for Neurodegeneration on the Rise: New Breakthrough in Routine Blood Testing for Alzheimer’s Disease
GeneOnline’s Pick – Top 10 Global Industry News Stories in 2023 (Part 2)
GeneOnline’s Pick: Top 10 Global Biotech News Stories in 2023
APAC Leading the Industry in Adoptive Cell Therapy – Trials, Economic Growth, and Pioneering Companies
Taiwan’s Biotech and Pharma Delegation: Innovations Take Center Stage at BIO 2024
Breaking Ground in Alzheimer’s with 10 Cutting-Edge Treatments Paving the Way in 2024
Merck Buys EyeBio for $3B and Shares Global Policy Perspectives During BIO in San Diego
Johnson & Johnson’s Bispecific Antibodies for Atopic Dermatitis and Talks of Biotech Partnerships at BIO 2024
Merck’s KEYNOTE-522 Success; BMS Licenses PRX019, Prothena Gets $80M
SINBON and MAKALOT partner to drive cross-industry textile wearable adoption
Scroll to Top