Credits: Social Media
ChatGPT can assess common health issue better than real doctors, shows study
AI has multiple benefits, but seeking medical advice from a chatbot is not recommended. Still, a popular AI tool has proven more effective in assessing health issues among children compared to human doctors.
The relevance of artificial intelligence has largely extended to the health industry. In fact, scientists have developed an AI mode that can predict your time of death with “high accuracy.”
AI chatbots can assess common health issue in children
Respiratory issues are one of the most common illnesses among children with complex cases such as asthma, sleep-disordered breathing, breathlessness, and more.
As AI has displayed a tremendous ability to predict aspects concerning health and well-being, researchers took to comparing three popular chatbots with trainee doctors to find out who performs better in assessing “complex cases” of respiratory disorders.
The study published in The American Journal of ManagedCare notes that 6 experts in pediatric respiratory medicine provided 6 clinical scenarios of cases.
These were presented to 10 trainee doctors with less than 4 months of pediatric clinical experience and three popular AI bots – ChatGPT version 3.5, Googles Bard, and Microsoft Bings chatbot.
The trainee doctors got one hour to solve each case using resources from the internet except chatbots. “These cases did not have an immediately clear diagnosis, and existing guidelines or evidence did not provide a definitive answer,” notes the study.
The experts scored the final assessment of the illnesses out of 9 based on factors such as correctness, comprehensiveness, usefulness, and more.
The findings showed a higher score among the chatbots than the trainee doctors, who scored between 3 to 6 points.
ChatGPT outperforms all
Of all the AI chatbots, ChatGPT got the highest score of 7 out of 9 points, followed by Brad with the second-highest score of 6. Bing scored most same as trainee doctors with 3 to 5 points.
Despite the impressive results, experts say more research and testing is needed before using the technology in daily life. Hilary Pinnock, MD, chair of the ERS Education Council and professor of primary care respiratory medicine at The University of Edinburgh said:
“As the researchers have demonstrated, AI holds out the promise of a new way of working, but we need extensive testing of clinical accuracy and safety, pragmatic assessment of organizational efficiency, and exploration of the societal implications before we embed this technology in routine care.”
