TL;DR
Turn your wind-down time into listening time
- Thousands of audiobooks, podcasts and originals
- Listen on your phone, tablet or Echo — also offline
- Cancel anytime
Researchers from Virginia Commonwealth University and Emory University tested HomePal, a home sensor system, in 70 independently living adults aged 65 and older over three months. The project is examining whether patterns in movement, sleep, daily activities and phone use correspond with loneliness assessments; it has not established that the system can diagnose loneliness.
Researchers from Virginia Commonwealth University and Emory University have tested a home sensor system called HomePal in the homes of 70 adults aged 65 and older, studying whether changes in everyday behavior could help identify possible loneliness or social withdrawal. The three-month prototype study is still evaluating the system against participants’ reported feelings; the researchers say it is intended to flag patterns for follow-up, not to diagnose loneliness.
HomePal combines commercially available and custom sensors to passively record aspects of life at home. The system tracks movement and door activity, estimates television use through smart plugs, monitors sleep, and gathers information about phone-call patterns. It also uses smart speakers to collect speech-related data. The researchers say these signals may help identify changes in routines or social contact that could be associated with loneliness.
The team deployed the prototype for three months in metro Atlanta among older adults living independently. It plans to compare sensor readings with loneliness assessments conducted every two weeks. Researchers are using an AI model to examine which behavioral patterns align with the assessments and to evaluate how accurately the model reflects those reported experiences.
The study, published in the journal Assessment, is titled “Development of an AI-Enabled Remote Loneliness Assessment System for Older Adults Using Behavioral and Speech Data From IoT Sensors and Smart Speakers.” The report does not provide a validated accuracy result or show that HomePal has been shown to improve care. The researchers say they are still analyzing the data and adjusting the system.
A Possible Signal Between Visits
Loneliness can be difficult for clinicians to recognize during appointments, especially if a patient does not raise the issue. A system that tracks everyday patterns could, if later validated, give a care team another reason to check in when a person’s routines or social contact change. That could be relevant to family members and health professionals supporting older adults who live on their own.
For now, the study establishes a research approach, not a clinical tool. Sensor readings such as less movement, more television use, disrupted sleep or fewer phone calls can have many explanations. They do not by themselves establish that someone is lonely. Researchers would need to show that the system’s flags reliably correspond to reported loneliness and are useful in practice before they could guide care decisions.
As an affiliate, we earn on qualifying purchases.
How HomePal Connects Sensors and Surveys
The project brings together behavioral sensing and self-reported assessments. Researcher Chung, a former VCU School of Nursing professor, led the loneliness assessments, while the engineering team is developing the data analysis. Comparing the two sources is meant to test whether patterns recorded at home relate to what participants say about how they feel.
Lead author Mohamed Kamel said the team is looking for everyday signs that an older adult may be experiencing loneliness or social withdrawal. Researcher Nadeem described the process as collecting and analyzing data, building models, and then checking their accuracy against the traditional survey approach. The researchers’ stated goal is eventually a system that could be installed in a home much like a security setup and provide a daily score or trend for a person or caregiver to review.
The team has also raised privacy as a design consideration. Nadeem said HomePal could be adapted to use sensors that operate and store data on local networks, and that decisions could be made about what information is shared. These are described as possible system options; the report does not establish that all current data are stored locally or that the prototype is already available as a consumer product.
“The main idea is to see whether everyday behavior at home can give early signs that an older adult may be experiencing loneliness or social withdrawal.”
— Mohamed Kamel, VCU computer science Ph.D. student and lead author
Accuracy and Privacy Still Under Study
The report does not say how closely HomePal’s readings matched loneliness assessments, how often the system might incorrectly flag a person, or whether its signals can distinguish loneliness from other reasons for changes in sleep, movement or phone use. The researchers are still analyzing the data and have not reported a confirmed detection threshold or clinical performance measure.
It is also unclear what data-sharing and storage arrangements would apply to a future product. The team says local storage and limits on caregiver access may be possible, but the report does not specify a finalized privacy design. The prototype’s results should not be treated as evidence that a sensor score can determine an individual’s emotional state.
Researchers Continue Model Testing
The team plans to continue analyzing the sensor data alongside the biweekly loneliness assessments, refining its AI models and adjusting the sensors as it learns which signals may be useful. A central next step is to report how accurately the models correspond with participants’ survey responses.
The researchers have described a possible future commercial system that could provide a daily score or trend for an older adult or caregiving team. The source does not give a launch date, confirm that such a product is in development for sale, or say when further results will be published. Any future use would depend on evidence about accuracy, practical value and privacy protections.
Key Questions
What is HomePal?
HomePal is a research prototype combining home sensors and connected devices to record patterns such as movement, sleep, television use, speech-related data and phone calls.
Has HomePal been shown to diagnose loneliness?
No. Researchers say they are studying patterns that may be linked to loneliness and could merit follow-up. The report does not provide evidence that the system can diagnose an individual.
Who took part in the study?
The prototype was deployed for three months in the homes of 70 adults aged 65 and older who were living independently in the metro Atlanta area.
How will the researchers evaluate the system?
They plan to compare sensor data with loneliness assessments collected every two weeks and use an AI model to test how behavioral patterns align with participants’ reported feelings.
What is known about HomePal’s privacy protections?
The researchers say the system could be adapted to use local storage and allow control over what is shared with caregivers. The report does not detail a final privacy setup for a commercial product.
Source: rss
Fall Picks
fall essentials
As an affiliate, we earn on qualifying purchases.
