AI chatbots could help doctors treat depression, researchers suggest, after study with ChatGPT | Science and technology news


AI chatbot ChatGPT could be better at following treatment standards for depression than human doctors, a study suggests.

The technology could improve decision-making in primary care, researchers said, as it is able to follow recognized standards of care without any gender or social class biases, which are sometimes a factor between people.

But more work is needed to assess any potential risks or ethical issues that could arise from its use in practice, the researchers added.

A team in Israel provided two versions of ChatGPT – 3.5 and 4 – brief descriptions of hypothetical patients showing symptoms of depression during initial consultations.

There were eight different grades, which varied by gender, socio-economic status and severity of depression.

Symptoms included sadness, sleep problems and loss of appetite in the three weeks leading up to the appointment, as well as a diagnosis of mild to moderate depression.

The information of each hypothetical patient was entered into ChatGPT 10 times, and its responses were compared with 1,249 French primary care physicians, 73% of whom were women.

More about artificial intelligence

For mild depression, ChatGPT-3.5 recommended psychotherapy in 95% of cases and ChatGPT-4 in 97.5% of cases.

However, primary care physicians recommended it only 4.3% of the time, choosing drugs 48% of the time or psychotherapy plus prescription medication 32.5% of the time.

For severe cases of depression, 44.5% of physicians recommended psychotherapy plus prescribed medication, while the two versions of ChatGPT recommended this method in 72% and 100% of cases, respectively.

When it came to the type of medication recommended, ChatGPT favored exclusive use of antidepressants in 74% and 68% of cases, while doctors favored a mix of antidepressants and anxiolytics/hypnotics in 67.4% of cases.

Read more:
ChatGPT creator expresses concern over ‘under-regulation’
UK judge admits he used ‘jolly useful’ ChatGPT to write judgement

Please use the Chrome browser for a more accessible video player

Is AI an existential threat?

ChatGPT ‘has potential to improve decision-making in primary care’

The researchers said their findings, published in the journal Family Medicine and Community Health, showed that ChatGPT “fits well with accepted guidelines for the management of mild and severe depression, without showing the gender or socioeconomic biases observed among primary care physicians”.

They added: “ChatGPT-4 demonstrated greater precision in adjusting treatment to adhere to clinical guidelines.

“The study suggests that ChatGPT… has the potential to improve decision-making in primary care.”

But they said despite the potential benefits of using AI chatbots such as ChatGPT, “further research is needed to refine AI recommendations for severe cases and to consider potential risks and ethical issues”.


Leave a Reply

Your email address will not be published. Required fields are marked *