Predicting Accidents of Older Adults with Dementia Using Technology
Author Information
Author(s): Lee Kyung Hee, Yang Eunjin, Lee Ji Yeon, Cho Aeyoung
Primary Institution: Yonsei University
Hypothesis
Can machine learning models predict accidents among older adults living with dementia using assistive technologies?
Conclusion
The study found that machine learning models can effectively predict different types of accidents in older adults with dementia, helping to improve safety and support for caregivers.
Supporting Evidence
- The Gradient Boosting Model excelled in predicting physical impact and night-time behaviors.
- CatBoost performed best for risky behaviors.
- Important features for predicting accidents varied by type, including caregiver's age and cognitive function.
Takeaway
This study shows that technology can help predict when older people with dementia might have accidents, which can keep them safer at home.
Methodology
Data were collected from older adults with dementia and their caregivers, and machine learning models were developed to predict accident subgroups.
Participant Demographics
Older adults living with dementia and their family caregivers in South Korea.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website