A conversation with ChatGPT about community-acquired pneumonia

Abstract

To the Editor

ChatGPT is an artificial intelligence (AI) driven language model that uses deep learning techniques to produce human-like responses to natural language inputs [1]. It was developed by Open AI in November 2022 and belongs to the family of generative pre-training transformer (GPT) models. It is considered to be one of the largest publicly available language models [1]. The application of ChatGPT in fields such as medicine, where complex thinking and analysis are needed is uncertain and raises multiple ethical concerns [2]. The performance of ChatGPT in the context of difficult real-life scenarios is not clear, especially in a field such as medicine, where complex mental work is required [2]. ChatGPT has been receiving extensive attention lately, and it is expected that the general public will start using it to explore information about certain diseases in medicine. A study published in the Journal of American Medical Association (JAMA) in 2023, concluded that ChatGPT generated quality and empathetic responses to patient questions posted in an online forum [3].

Community-acquired pneumonia is a leading cause of hospitalization and death in the United States with approximately 6 million cases reported each year [4]. It is an infection of the pulmonary parenchyma that occurs acutely in a patient who has acquired the infection in the community [4]. It is diagnosed based on the presence of compatible symptoms and signs, with evidence of new infiltration in imaging studies [4]. With the increased public awareness about certain health conditions, individuals in the community are likely to use new technologies such as ChatGPT to answer questions related to these conditions. Table 1 outlines a conversation comprised of six questions between a common person and ChatGPT about community-acquired pneumonia.

Table 1 A conversation with ChatGPT about community-acquired pneumonia

Full size table

We have observed from this conversation, that ChatGPT generates easy-to-understand and largely correct answers to questions it is asked. It was able to accurately list all the possible microorganisms that can cause community-acquired pneumonia and was able to provide the names of specific bacteria that are well-known to cause this infection: “The most common bacterial causes of CAP include Streptococcus pneumoniae (pneumococcus), Haemophilus influenzae, Mycoplasma pneumoniae, Legionella pneumophila, and Chlamydophila pneumoniae”. It also provided realistic information about the symptoms of the infection: “It’s important to note that not everyone with CAP will experience all of these symptoms, and the severity can vary widely. Additionally, individuals with certain underlying health conditions, such as chronic lung disease or immunodeficiency, may present with atypical or more severe symptoms”. However, the challenge associated with the use of this tool, is that its responses are not verified and not authenticated, because no references are cited that will help validate or support the information provided [5].

Language learning models such as ChatGPT will undoubtedly revolutionize clinical information retrieval in the future; however, it is limited by the fact that responses generated are unauthenticated and can vary in response to minor changes in input. ChatGPT can provide assistance to physicians in providing empathetic good quality information about diseases via online platforms and consultations. However, physicians should contribute to this technological advancement by ensuring the accuracy of the information provided by ChatGPT and cross-referencing it with medical literature, in order to ensure the dissemination of accurate and verified medical information.

We would recommend further research in order to quantify the accuracy and reliability of ChatGPT-generated responses to patient questions. Furthermore, physicians may also collaborate with each other to develop a new artificial intelligence software, that will be able to generate high-quality cross-referenced and verified responses to patient queries. This will help ensure the dissemination of accurate medical information to the public.

No datasets were generated or analysed during the current study.

AI:

Artificial intelligence

GPT:

Generative pre-training transformer

JAMA:

Journal of American Medical Association

1. Dave T, Athaluri SA, Singh S (2023) ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations. Front Artif Intell 6:1169595. https://doi.org/10.3389/frai.2023.1169595. Published 2023 May 4

   Article PubMed PubMed Central Google Scholar

2. Cascella M, Montomoli J, Bellini V, Bignami E (2023) Evaluating the feasibility of ChatGPT in healthcare: an analysis of multiple clinical and research scenarios. J Med Syst 47(1):33. https://doi.org/10.1007/s10916-023-01925-4. Published 2023 Mar 4

   Article PubMed PubMed Central Google Scholar

3. Ayers JW, Poliak A, Dredze M et al (2023) Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum. JAMA Intern Med 183(6):589–596. https://doi.org/10.1001/jamainternmed.2023.1838

   Article PubMed PubMed Central Google Scholar

4. File TM Jr, Ramirez JA (2023) Community-acquired pneumonia. N Engl J Med 389(7):632–641. https://doi.org/10.1056/NEJMcp2303286

   Article PubMed Google Scholar

5. Deoghare S (2023) An interesting conversation with ChatGPT about acne vulgaris. Indian Dermatol Online J 15(1):137–140. https://doi.org/10.4103/idoj.idoj_77_23. Published 2023 Nov 7

   Article PubMed PubMed Central Google Scholar

Download references

Not applicable

Not applicable.

Authors and Affiliations

1. Hospital Medicine Department, Integrated Hospital Care Institute, Cleveland Clinic Abu-Dhabi, Abu-Dhabi, United Arab Emirates

   Mohamed Kamal Mansour

Authors

1. Mohamed Kamal MansourView author publications

   You can also search for this author in PubMed Google Scholar

Contributions

Mohamed Kamal Mansour has made substantial contributions to the conception, design of the work, drafting the work and substantively revising it. He approved the submitted version. He agreed both to be personally accountable for his own contributions and to ensure that questions related to the accuracy or integrity of any part of the work, are appropriately investigated, resolved, and the resolution documented in the literature. He wrote the entire manuscript text and prepare d the table.

Corresponding author

Correspondence to Mohamed Kamal Mansour.

Ethics approval and consent to participate

Not applicable.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Reprints and permissions

Cite this article

Mansour, M.K. A conversation with ChatGPT about community-acquired pneumonia. Egypt J Bronchol 18, 66 (2024). https://doi.org/10.1186/s43168-024-00318-6

Download citation

• Received: 07 July 2024

• Accepted: 14 August 2024

• Published: 19 August 2024

• DOI: https://doi.org/10.1186/s43168-024-00318-6

Share this article

Anyone you share the following link with will be able to read this content:

Get shareable link

Sorry, a shareable link is not currently available for this article.

Copy to clipboard

Provided by the Springer Nature SharedIt content-sharing initiative