Path: EDN Asia >> News Centre >> Medical >> Mood sensing tech uses GPS to detect depression
Medical Share print

Mood sensing tech uses GPS to detect depression

29 Feb 2016  | Patrick Mannion

Share this page with your friends

However, the findings were extremely encouraging: An extensive evaluation shows that, for most of the users, these personalised models are able to accurately detect changes in the PHQ score exploiting only mobility metrics. It is worth noting that, after a training phase, these models are able to monitor the depressive state of individuals without requiring a direct interaction with the device.

This is huge. There is much research underway within the pervasive and ubiquitous computing community to find ways to use smartphone data to detect and predict psychological states and mental health conditions. The authors point to many of these in their literature references, including detecting and monitoring of bipolar disorder. However, the authors state four distinct differences between their work and prior research: 1) Much of that prior research focuses on mood or stress detection, and not on the 'analysis and prediction of variations of the depressive states of the individual;' 2) Most of the cited works require user interaction; 3) This research is predictive, proposing a mechanism to forecast depressive states from mobility data; and 4) In the case of bipolar disorder research, the subjects had been diagnosed. Here, the subjects were picked from the general population with only a few suffering from severe depression, so the technique can be applied to monitor the PHQ score of someone not suffering depression and watch for an early diagnosis if the condition does appear.

State machines

Figure 2: State machines used to select the location sampling rate (a) and the location provider (b). S = static; M = moving; U = undecided

Next step: real-world applications

The findings are only a starting point: the next step is application-oriented projects in the field of digital mobile interventions. These interventions can come about through phone calls from healthcare officers or more 'traditional' physical interactions.

The team also envisions the integration of more context awareness, whether it be through other sensors, such as accelerometers, or through SMS logs. Of course, that raises a general privacy issue, as well as a problem specific to depression sufferers that makes the condition all the more insidious: sufferers don't actually want to be monitored, or interacted with, and especially not 'intervented.' Overcoming that obstacle is another kind of problem to be researched.

In the meantime, if you're thinking of an application or a design that can apply the research, they are working on a generic training model built on the data collected that might be used to remove the need of a training phase in the deployment of the application. It's always nice to get a good deal, but this may be a better use of GPS technology and battery power than flashing 'Save 20 per cent now at...'


 First Page Previous Page 1 • 2


Want to more of this to be delivered to you for FREE?

Subscribe to EDN Asia alerts and receive the latest design ideas and product news in your inbox.

Got to make sure you're not a robot. Please enter the code displayed on the right.

Time to activate your subscription - it's easy!

We have sent an activate request to your registerd e-email. Simply click on the link to activate your subscription.

We're doing this to protect your privacy and ensure you successfully receive your e-mail alerts.


Add New Comment
Visitor (To avoid code verification, simply login or register with us. It is fast and free!)
*Verify code:
Tech Impact

Regional Roundup
Control this smart glass with the blink of an eye
K-Glass 2 detects users' eye movements to point the cursor to recognise computer icons or objects in the Internet, and uses winks for commands. The researchers call this interface the "i-Mouse."

GlobalFoundries extends grants to Singapore students
ARM, Tencent Games team up to improve mobile gaming


News | Products | Design Features | Regional Roundup | Tech Impact