Technology to help dementia carers

Jorjix

Registered User
Apr 24, 2017
12
0
While we're on tech I would love to be able to monitor my relatives fluid intake (and urine output) - fairly convinced that they never drink water and so are often mildly dehydrated thus risking kidney and bladder problems.

I think monitoring should stop where we would all stop if actually present - this could be different places for different people but for most would be OK to know someone had got into bed or out of bed, or gone into bathroom, but not to go any further than that.

That would be very interesting, Houdini, we haven't thought of dehydration. It's relatively easy to track using video monitoring, as well as being an important metric and a starting point for different affections.

I agree that people should be able to stop the cameras whenever they want and also be free to configure the system according to their needs.

To move our project forward and further investigate what people think about video monitoring for preventive medicine we created a website. Please have a look if you have 1 minute and it would be very useful to get your feedback: http://machinemedicine.com/

Thanks again!
 

Kevinl

Registered User
Aug 24, 2013
6,064
0
Salford
Well, man trips over dog lead, on TV You've Been Framed pays £250 for a clip like that but I can see nothing other than a box (possibly added later) to indicate the fall risk. The dog walked in front of him and he tripped over the lead, happens in the park everyday, he was distracted with whatever was in his hand keys or something took his eye off the ball. A younger person may not fallen having better reflexes, but I see younger people do a similar thing when they're walking the dog and texting.
K
 

Jorjix

Registered User
Apr 24, 2017
12
0
Well, man trips over dog lead, on TV You've Been Framed pays £250 for a clip like that but I can see nothing other than a box (possibly added later) to indicate the fall risk.
K

The video was filmed in a hospital in Canada. In this particular example, the falls prevention system is looking at walking patterns (gait speed, stride length, pose, centre of balance...), comparing them to what's expected and notifying staff when there's a high risk or when it detects a fall. The example video might not be the best because there's not much time to alert somebody and the man falling is with a relative who can help him get up or alert the medical staff. That's a useful callout and I might look into changing it with a better scenario.

Needless to say that this, as you very well observed, is not a product, but merely an algorithm that shows how an artificial intelligence system can indeed follow people the same way the human eye would and infer complex events from simple CCTV.
The hard part for us now is to imagine what type of metrics we can capture in order to help carers, medical staff and the patients themselves.

In your opinion, what do you expect to see extracted from the video data in order for the proposal to make a compelling case? Maybe displaying the mobility metrics we're computing, along with the box and the falls detection message?
Any suggestion is highly appreciated.