On March 24, 2020, New York governor Andrew Cuomo sounded a dire alarm during a press conference amid an escalating COVID19 situation in his state. He then repeated on twitter: "My mother is not expendable. Your mother is not expendable. We will not put a dollar figure on human life."
COVID19 isolated many of us, but especially vulnerable are elderly and disabled family members who are left unattended for days or maybe even weeks in some states and countries with full military lockdown.
Remote home care is an emerging topic in the theme of healthy aging, but it is especially relevant in times of COVID19 isolation.
The holistic problem of home care is very complex and dynamically changing. We can’t solve it at once, but there are discrete steps we can take in the right direction. One specific area of home care is proactive and unobtrusive monitoring of the activities and the home environment of residents.
For example it is a well researched issue that falls can be a key indicator of health complications. In fact, falls are the leading cause of fatal and non-fatal injuries for older Americans. If there is no one present to observe a fall and take action, it may go unnoticed. Things can be even worse if the person is not able to move and recover on their own.
Other important health factors include eating patterns, exercise activities, medication compliance. Changes in voice may also mean trouble. Environmental risk factors include flooding in the house, gas leaks, smoke or fire.
When detected early, these risks can be mitigated with minimal intervention from family members or caregivers. Respectively if response is delayed, the severity of the problems escalates.
With all this said, an idea begins to form. If we are able to build an affordable, unintrusive system that detects early warning signs, it may improve healthy independent aging at home.
Fortunately there is a solid foundation of open source projects that provide the key building blocks for a secure, privacy preserving AI system that begins to solve these problems.
We have released a public Beta version that integrantes these building blocks and demonstrates feasibility. Given the positive community feedback, we are advancing the project further with participation in a series of COVID19 hackathons.
We need to work on these main areas:
Recruit volunteers in the home care community to test the system and provide feedback.
- Select more ML models to address open use cases such as fall detection, gas leaks and others.
- Work on implementing Federated Learning infrastructure to fine tune initial pre-trained models in a privacy preserving manner.
- Improve UX of the Progressive Web App.
If this topic resonates with you and you have cycles to spare for social good, join the team at The Global Hack this weekend or COVIDathon next month. If you don't have time to contribute, you can also sponsor the project on github with a $1 or $5 donation.
Top comments (0)