The AI chatbot ChatGPT could be more effective than human doctors in following treatment standards for depression, according to a study.
The technology could enhance decision making in primary care, researchers said, as it can adhere to recognized treatment standards without any gender or social class biases that may influence human doctors.
However, the researchers added that further work is needed to evaluate any potential risks or ethical issues that may arise from its use in practice.
A team in Israel provided two versions of ChatGPT – 3.5 and 4 – with brief descriptions of hypothetical patients exhibiting symptoms of depression during initial consultations.
The eight distinct characters varied in terms of gender, socioeconomic status, and depression severity.
The 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 about each hypothetical patient was inputted into ChatGPT 10 times, and its responses were compared to those of 1,249 French primary care doctors, 73% of whom were women.
For mild depression, ChatGPT-3.5 recommended psychotherapy in 95% of cases, and ChatGPT-4 in 97.5% of cases.
Primary care doctors, on the other hand, recommended it in only 4.3% of cases, opting for drugs 48% of the time, or a combination of psychotherapy and prescribed drugs 32.5% of the time.
For severe cases of depression, 44.5% of doctors recommended a combination of psychotherapy and prescribed drugs, while the two versions of ChatGPT recommended this approach in 72% and 100% of cases, respectively.
When it came to the type of medication recommended, ChatGPT favored the exclusive use of antidepressants in 74% and 68% of cases, while human doctors leaned towards a combination of antidepressants and anxiolytics/hypnotics in 67.4% of cases.
ChatGPT ‘has the potential to enhance decision making in primary healthcare’
The researchers stated that their findings, published in the journal Family Medicine and Community Health, demonstrated that ChatGPT “aligned well with accepted guidelines for managing 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 comply with clinical guidelines.
“The study suggests that ChatGPT… has the potential to enhance decision making in primary healthcare.”
However, they noted that 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”.