Facing up to depression over the phone

Last updated 13:11 27/02/2013
Roland Goecke
MELISSA ADAMS/Fairfax Australia

HOUSE CALL: The University of Canberra's Professor Roland Goecke worked with the Black Dog Institute to develop a breakthrough technology in depression diagnosis.

Relevant offers

Digital Living

Is VDSL broadband as quick as ultrafast broadband in New Zealand? Why America still controls its nuclear weapons with ancient floppy disks Microsoft to force people to stop using stupid passwords The dark side of live streaming that no one seems able to stop Timaru woman's dash-cam incident highlights the online need for speed More LinkedIn members' information leaked after 2012 security breach A start-up says it can uncover secrets by analysing faces Google and Levi's reveal their connected jean jacket GoPro's still looking for wings, even after Red Bull deal Scheme helping to drive technology at Marlborough primary schools

Depression sufferers may soon be monitoring the severity of their condition via smartphones and tablets using Australian-developed voice and facial recognition technology.

Researchers say the computer program, created in partnership with the mood disorder treatment and prevention organisation the Black Dog Institute, has brought them closer to an objective indicator of melancholic, or biologically determined, depression.

The University of Canberra's Dr Roland Goecke, an expert in human-computer interaction, worked with the institute to develop the program, which measures the indicators of melancholic depression including a lack of facial movement, slow speech and avoiding eye contact.

Using the program, a computer monitors the patient while they view images and video clips that commonly elicit certain emotional responses from people, and analyses their voices during interviews, and delivers a diagnosis based on the patient's reactions.

"One of the signs and symptoms of depression is that kind of interpersonal functioning is disturbed, and we are basically looking for those signs in an automated way," he said.

Institute researcher and clinician Professor Gordon Parker said initial clinical trials yielded a 90 per cent accuracy, whereas existing measures achieved an average of 65 per cent accuracy.

Professor Parker said technology would help doctors determine an appropriate treatment program for patients.

"By and large melancholic depression needs physical treatments like anti-depressive drugs, and many of the non-melancholic disorders don't need drugs," he said.

Professor Parker said it was difficult for patients with depression to objectively measure their symptoms, so using the program on their smartphones or other devices may help them identify when they needed to seek help.

It could also give doctors a clear indication of how patients were faring between appointments.

A clinical trial at the Black Dog Institute in Sydney tested the technology on 30 people suffering depression compared with a control group of 30, and found in 90 per cent of cases the voice and face recognition program gave the same diagnosis as two independent clinicians.

Stage two of the program will see the researchers develop a prototype which will be distributed to psychologists and general practitioners to assist with their initial diagnoses of depression.

The third stage will be developing the technology as a tool for patients to monitor their progress during treatment, on smart phones or other electronic devices.

The Black Dog Institute approached Dr Goecke about six years ago, looking to develop a more objective way of determining if a patient has melancholic, or biologically determined, depression.

Ad Feedback

- FFX Aus


Special offers

Featured Promotions

Sponsored Content