27 September 2023

Blue notes: How AI can diagnose depression by the sound of your voice

Start the conversation

Ella Vermeulen* says that new Artificial Intelligence can diagnose depression by the sound of a patient’s voice, making diagnosis simpler for doctors.

Image: metamorworks

Depression is a reality for many people, but due to the wide scope of symptoms and varying degrees of severity, it is often difficult to diagnose.

Researchers at MIT’s Computer Science and Artificial Intelligence Laboratory are attempting to combat this difficulty.

They aim to make diagnosis simpler for doctors and individuals by creating an algorithm that, when taught to a machine, can detect depression simply by listening to the tone of your voice.

The technology is in its infancy, so while it promises to be a wonderful tool, there are still some hurdles to overcome.

The algorithm is based on a study that used text and audio data from 142 interviews with patients, 30 of whom had been diagnosed with clinical depression, and the machine was able to correctly identify the other patients with a 77 per cent success rate.

Not bad for a first attempt!

Tuka Alhanai, an MIT researcher and one of the developers of the algorithm, told the Smithsonian: “If you want to deploy models in a scalable way, you want to minimise the amount of constraints you have on the data you’re using.”

“You want to deploy it in any regular conversation and have the model pick up, from the natural interaction, the state of the individual.”

Early signs are positive, but there is a chance that this kind of technology could prove detrimental to the public if placed in our hands too early.

A false reading could create serious ethical and personal problems.

Speaking to The Washington Post, Canadian doctor Adam Hofmann expressed his concern: “One’s mental health is a complex interplay of genetic, physical and environmental factors.”

“We know of the placebo and nocebo effects in medicine, when blind users of sugar pills experience either the positive or negative effects of a medicine because they have either the positive or negative expectations of it.”

“Being told you are unwell might literally make it so.”

While this type of product isn’t the first of its kind, it is a further reminder that there is a growing need to create technology that can better serve those struggling with mental and emotional disorders.

Woebot is another recently released app along the same lines.

It offers assistance to those suffering from anxiety and depression by acting as a middle-ground between talking to a real therapist and communicating with a basic chatbot.

Instead of responding in simple terms, the Woebot messaging app uses principles of cognitive-behavioural therapy to more appropriately reply to user comments such as “I feel useless today”.

The app offers quick conversations to help improve your mood and checks in with you throughout the day to see how you’re feeling.

Speaking more broadly about the use of technology in the mental health space, MIT researcher James Glass said: “We don’t view the technology making decisions instead of the clinician.”

“We view it as providing another input metric to the clinician.”

“They would still have access to all the current inputs they use.”

“This would just be giving them another tool in their toolbox.”

The more tools, the better.

* Ella Vermeulen is a contributor to Techly.

This article first appeared at www.techly.com.au.

Start the conversation

Be among the first to get all the Public Sector and Defence news and views that matter.

Subscribe now and receive the latest news, delivered free to your inbox.

By submitting your email address you are agreeing to Region Group's terms and conditions and privacy policy.