Depression speech app can diagnose condition in 60 seconds
Scientists have created an app that can detect depression in less than a minute by listening to a person’s voice.
An algorithm combines information on a speaker’s tone of voice, their volume and how often they pause in speech to make a conclusion.
Researchers at Semmelweis University in Budapest built the technology, which is not yet available to download, that requires a participant to read aloud a passage of Aesop's fable "The North Wind and the Sun".
It was found to be able to detect depression accurately on up to 84 per cent of occasions.
Experts believe the condition is widely undiagnosed and the new tool could be used on smartphones to quickly and easily detect depression.
"For a long time, researchers have been trying to define non-invasive biomarkers - objectively measurable characteristics - that can help recognise depression earlier and speed up diagnosis,” said Dr Bálint Hajduska-Dér, the app's developer.
"There now is a consensus that patients' altered speech could be one of these biomarkers."
Depressed patients are more monotonous
Dr Gábor Kiss, the app's co-developer, added: "The speech of depressed patients usually becomes more monotonous and quieter; they pause more often."
Researchers used voice samples of 218 depressed and healthy people (144 women, 74 men) reading a short, 10-sentence version of "The North Wind and the Sun", which is favoured in speech-analysis as it contains a wide variety of sounds.
The passage typically took 50 to 60 seconds to read and allowed scientists to discover participants' depression risk and whether they smoked, took any medication or had a speech condition.
Researchers then analysed the characteristics in each speech sample, including sound spectrum, voice dynamics and rhythm.
The app screened depressed patients with 84 per cent accuracy when compared with a professional clinician’s opinion, and 76 per cent accuracy when using self-reported data.
Dr Kiss added: "We proved that with the help of acoustic biomarkers, depression could be recognised earlier, and an automated decision-making software would be a highly beneficial diagnostic tool.
"It could be used in general medical practices and in the form of easily available, low-cost mobile or web applications."
'Earlier diagnosis can boost patient journeys'
Dr Hajduska-Dér added: "Patient journeys could be shortened and accelerated with the early recognition of depression based on voice-analysis.
"Those affected could receive the appropriate treatment sooner if a family doctor, with the help of the app, considered that the patient might be depressed, even if they have mainly physical symptoms such as abdominal or back pain.
"The inclusion of artificial intelligence, therefore, has the potential to improve the quality of life and reduce the time and costs spent in care."
The application could also be used to monitor patient improvement and measure the effectiveness of various therapies, the team believe.
Beyond depression, the app is also able to screen for signs of Parkinson's disease and dysphonia, such as oral and laryngeal tumours or other functional disorders affecting speech.
The study is published in the journal Frontiers in Psychiatry.