A five-point rebuttal to ‘Accelerometers, false positives/negatives and fall detection’

September 18, 2014 | by | 1 Comment

One of our most popular articles ever on TTA has been Tom Doris’ analysis of accelerometers in fall detection. His point of view is as a developer in digital health technology. For your consideration, we are posting this extended response from an executive experienced in deployment of both traditional PERS and now PERS with accelerometer-based fall detection in older adult populations.

Andy Schoonover is President of VRI, a leading provider of PERS, MPERS, and telehealth monitoring services founded in 1989. VRI currently actively monitors approximately 110,000 clients in the US–and a long-time TTA reader.

Tom Doris wrote a post on September 17th, laying out the problems with the use of accelerometers and fall detection devices especially in regards to PERS. After reading Tom’s post I felt compelled to respond with the following five points on why it’s important to continue to promote fall detection within PERS and MPERS.

1) In the 1 out of 100 case that my grandma falls and can’t physically press a button (sudden fainting due to hypoglycemia for example) would I prefer she have a regular PERS, which definitely won’t indicate a fall, or a PERS with fall detector which will more than likely indicate a fall? If it were my grandma I’d go with the “more than likely” option.

2) If my grandma had too many false positives then I’d ask her: you can use regular PERS with no fall detection or you can use PERS with fall detection where you will get called a couple more times per month. Which would you prefer? Hint: she’ll say fall detection. About 5 percent of our customers are annoyed by the false positives. (more…)

Accelerometers, false positives/negatives and fall detection

September 17, 2014 | by | 2 Comments

Tom Doris, KeepUs project founder and technical lead, responds to our recent post [TTA 28 Aug] critiquing Philips Lifeline with AutoAlert’s accelerometer and its possible failure to detect a fall which resulted in the death of a Massachusetts woman. His analysis concludes that accelerometers on their own are surprisingly inaccurate. The false positives/negatives may be minimal but they do exist, and they should not be the only indicator of a fall.

Mr Doris has a PhD in computer science and was formerly an R&D engineer at Intel. Earlier in TTA: 4 Oct 13, 22 July. 

Falling Down is a Surprisingly Hard Problem

More than 250,000 people suffer a hip fracture in the US every year. More than 20 percent will die within 12 months as a consequence of their fall. One in three who lived independently before the fracture will need at least a year of rehabilitation in a nursing home. While rehabilitation methods are improving, the single most important factor influencing the long-term outcome is the length of time between the fall and getting medical attention at a hospital. A few hours more or less makes the difference between life and death.

People are living longer, and current projections make it clear that elderly people will have to live independently in their own homes for as long as possible. You just can’t provide residential care for 20 percent of the population. Smartphones and wearable technology have the potential to dramatically improve eldercare. A relatively cheap smartphone can track activity and location. Modern platforms analyze the data in real-time over the internet and can, in theory, immediately spot when something is wrong and raise an alert.

The theory doesn’t always work however. (more…)