Summary: While there is clear potential for ChatGPT to be used in a clinical setting, the researchers say the AI algorithm may not yet be a reliable way to replace the family doctor, especially when it’s about making effective decisions about prescribing antibiotics for infections.
Source: University of Liverpool
Researchers at the University of Liverpool tested whether the AI-powered chatbot ChatGPT could be used to make decisions about prescribing antibiotics to patients.
In a letter published in The Lancet Infectious Diseasesacademics from the Institute of Systems, Molecular and Integrative Biology show that while artificial intelligence cannot yet replace the family physician, there is clear potential for technology to play a role in clinical practice.
The researchers presented ChatGPT with eight hypothetical infection scenarios that people would typically see their doctor about (such as a lung infection). They then assessed the advice delivered by the technology for its relevance, consistency and impact on patient safety.
The evaluation found that ChatGPT understood the scenarios and provided consistent answers, including disclaimers, and directed patients to sources of advice. He also seemed to understand the need to prescribe antibiotics only when there were signs of bacterial infection.
However, ChatGPT provided dangerous advice in complex scenarios and when important information was not explicitly provided.
Interestingly, the AI tended to focus on the type of antibiotic prescribed in each scenario rather than other factors, reflecting assumptions often initially made by physicians during the consultation.
Following the experiment, the researchers have now developed a checklist for the standards that AI must meet in order to be considered for use in clinical practice in the future.
Letter co-author Dr Alex Howard said: “It was fascinating to see the potential of artificial intelligence in healthcare demonstrated through this experiment testing ChatGPT’s ability to provide advice on antibiotic treatment.
“With the rise of antibiotic resistance posing a significant threat to global health, the ability of AI to provide accurate and safe treatment advice could revolutionize our approach to patient care. We look forward to continuing the exploring this technology and its implications for the future of healthcare.
About this ChatGPT and AI research news
Author: Press office
Source: University of Liverpool
Contact: Press Office – University of Liverpool
Picture: Image is in public domain
See also
Original research: Free access.
“ChatGPT and antimicrobial advice: the end of the doctor consultant in infection? by Alex Howard et al. Lancet Infectious Diseases
Abstract
ChatGPT and antimicrobial advice: the end of the doctor consultant in infection?
Generative artificial intelligence (AI) models have proliferated over the past 2 years. ChatGPT, a large language model (LLM) developed by OpenAI (San Francisco, CA), mimics natural language and solves cognitive problems by enhancing learning from online resources using human feedback.
Despite access to limited medical data, ChatGPT passed the medical licensing exam as a third-year undergraduate medical student and thus stimulated urgent discussions within medicine.
Stokel-Walker and van Noorden discuss the implications of generative AI for science and describe how ChatGPT “could answer some open medical questions almost as well as the average human physician, although it still has gaps and lacks of reliability”.