Role of Machine Learning in Aging in Place Research
Author Information
Author(s): Park Sojung, Ahn Eunhye, Ahn Tae-Hyuk, Ahn SangNam, Park Soobin, Kwon Eunsun, Ahn Seoyeon, Yang Yuanyuan
Primary Institution: Washington University in St. Louis
Hypothesis
How can machine learning be applied to improve aging in place for older adults?
Conclusion
Machine learning models can predict health outcomes for older adults but often fail to address the needs of those with dementia or disabilities.
Supporting Evidence
- Machine learning is widely used in aging research, particularly in health monitoring and personalized care.
- Three main themes emerged: successful aging, managing depressive symptoms, and fostering social connectedness.
- The studies employed various ML techniques to predict health outcomes such as depression, cognitive decline, and functional disabilities.
Takeaway
This study looks at how computers can help older people live better at home, but they need to pay more attention to those who are not as healthy.
Methodology
The review examined 32 peer-reviewed studies using thematic analysis to identify key themes and applications of machine learning in aging in place.
Potential Biases
The focus on healthy, community-dwelling older adults may introduce biases affecting marginalized groups.
Limitations
The studies often lacked validation across diverse populations and primarily focused on healthy older adults, excluding those with dementia or disabilities.
Participant Demographics
Most studies focused on healthy, community-dwelling older adults.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website