article · Frontiers in Psychiatry
Artificial intelligence language models have attracted growing interest as potential tools to assist in psychiatric care and patient support. An evaluation using three simulated patient scenarios assessed the reliability, safety, and effectiveness of ChatGPT in managing mental health complaints. All three imaginary cases shared identical symptoms of sleep disruption, but featured different underlying clinical conditions. For the simplest case, the model produced relatively appropriate, non-specific guidance that could offer limited utility. However, as clinical complexity increased, the recommendations became inappropriate and potentially dangerous. Although the system responded rapidly and simulated empathy effectively, it failed to ask follow-up questions to collect vital diagnostic information and could not exercise clinical judgment. The technology remains far from capable of providing safe, accurate guidance for mental health assessments or clinical interventions.
Rising public interest in artificial intelligence tools for healthcare creates risks if automated systems are used without adequate safeguards. Demonstrating that conversational models can deliver inappropriate advice in complex psychiatric scenarios highlights vital safety concerns for vulnerable individuals. The findings underscore that conversational language models cannot currently substitute for qualified human practitioners in evaluating and managing mental health disorders.
The findings show that conversational artificial intelligence models are at an early research stage and remain far from ready for commercial use as clinical assistants or automated therapy tools. Digital health developers aiming to support psychiatric practitioners or patients must address critical safety flaws, particularly the absence of interactive diagnostic enquiry and clinical reasoning, before these technologies can be applied safely in commercial healthcare products.
AI-generated from the published abstract. Always read the original work before citing.
Background: Psychiatry is a specialized field of medicine that focuses on the diagnosis, treatment, and prevention of mental health disorders. With advancements in technology and the rise of artificial intelligence (AI), there has been a growing interest in exploring the potential of AI language models systems, such as Chat Generative Pre-training Transformer (ChatGPT), to assist in the field of psychiatry. Objective: Our study aimed to evaluates the effectiveness, reliability and safeness of ChatGPT in assisting patients with mental health problems, and to assess its potential as a collaborative tool for mental health professionals through a simulated interaction with three distinct imaginary patients. Methods: Three imaginary patient scenarios (cases A, B, and C) were created, representing different mental health problems. All three patients present with, and seek to eliminate, the same chief complaint (i.e., difficulty falling asleep and waking up frequently during the night in the last 2°weeks). ChatGPT was engaged as a virtual psychiatric assistant to provide responses and treatment recommendations. Results: In case A, the recommendations were relatively appropriate (albeit non-specific), and could potentially be beneficial for both users and clinicians. However, as complexity of clinical cases increased (cases B and C), the information and recommendations generated by ChatGPT became inappropriate, even dangerous; and the limitations of the program became more glaring. The main strengths of ChatGPT lie in its ability to provide quick responses to user queries and to simulate empathy. One notable limitation is ChatGPT inability to interact with users to collect further information relevant to the diagnosis and management of a patient's clinical condition. Another serious limitation is ChatGPT inability to use critical thinking and clinical judgment to drive patient's management. Conclusion: As for July 2023, ChatGPT failed to give the simple medical advice given certain clinical scenarios. This supports that the quality of ChatGPT-generated content is still far from being a guide for users and professionals to provide accurate mental health information. It remains, therefore, premature to conclude on the usefulness and safety of ChatGPT in mental health practice.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3389/fpsyt.2023.1277756
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
