Mitigating the Burden of meningitis outbreak; ChatGPT and Google Bard Recommendations for the general populations; general practitioners and pediatricians

Abstract

Introduction: ChatGPT and Bard are large language models, both are artificial intelligence designed to understand natural language and generate human-like responses to text-based inputs. The aim of this study is to assess the ChatGPT and Bard Recommendations for the general populations; general practitioners and pediatricians for reducing the burden of meningitis outbreaks. Methods: We asked ChatGPT PLUS and Bard, on 5 April 2023 for their advice and recommendations in controlling the meningitis outbreak, the same question was repeated three times, one for the general population, one for the general practitioners, and the last one for the pediatricians. The responses were recorded, compared assessed. Results: ChatGPT and Bard replied to the three questions with general advice including early recognition of the disease, insisting on the vaccination, strict hygiene, infection control strategy, and staying up to date about the latest developments regarding the outbreak. Conclusion: ChatGPT and Bard have the potential to be valuable tools for the general population during outbreaks of infectious diseases. However, advanced information for professionals might be impossible to be provided by ChatGPT PLUS and Google Bard at the time being.

Evaluating human resources management literacy: A performance analysis of ChatGPT and bard

“…Salazar et al [ 56 ] in Australia evaluate and compare the accuracy of ChatGPT, Google Bard, and Microsoft Bing Chat to differentiate between a medical emergency and a non-emergency and conclude that no real difference in performance exists between the three in detecting true emergencies and non-emergency cases. Salih et al [ 58 ] in Iraq assess the ChatGPT and Bard Recommendations for general practitioners and paediatricians for reducing meningitis outbreaks and conclude that there is not much difference between the potential of the two tools. Hans [ 65 ] in France compares ChatGPT and Bard in code generation and concludes that both exhibit similar levels of consistency in their performance and comparable efficiency in terms of memory usage and runtime.…”

“…Patil et al [ 54 ] compare the radiology knowledge of ChatGPT and Bard and conclude that both display reasonable radiology knowledge and should be used with conscious knowledge of their limitations. Studies have compared the performance of the LLMs to generate accurate responses to common myopia-related queries [ 55 ] to differentiate between medical emergency and non-emergency [ 56 ], to generate differential diagnoses in neurodegenerative disorders [ 57 ], and to generate recommendations that reduce meningitis outbreaks [ 58 ].…”