---
title: "AI Chatbots vs Medical Residents in Chest Disease Clinical Reasoning: ChatGPT-4 and Gemini Compari"
id: "pubmed-41979097"
canonical_url: "https://medichelpline.com/clinical-feed/pubmed-41979097"
content_type: "clinical_feed_article"
specialty: "Critical Care"
source_name: "PubMed / NCBI"
source_url: "https://pubmed.ncbi.nlm.nih.gov/41979097/"
doi: "10.4274/ThoracResPract.2026.2026-1-2"
published_at: "2026-09-07T00:00:00.000Z"
evidence_level: "Journal Article"
license: "CC-BY-NC-4.0 / Informational Use"
---
# AI Chatbots vs Medical Residents in Chest Disease Clinical Reasoning: ChatGPT-4 and Gemini Compari
## Provenance & Clinical Metadata
- **Canonical URL:** https://medichelpline.com/clinical-feed/pubmed-41979097
- **Specialty:** [Critical Care](https://medichelpline.com/clinical-feed/critical-care.md)
- **Primary Source:** PubMed / NCBI
- **Source URL:** [Original Journal Publication](https://pubmed.ncbi.nlm.nih.gov/41979097/)
- **DOI:** [10.4274/ThoracResPract.2026.2026-1-2](https://doi.org/10.4274%2FThoracResPract.2026.2026-1-2)
- **Published At:** 2026-09-07T00:00:00.000Z
- **Evidence Rating:** Journal Article
## Executive GIST (TL;DR)
- This cross-sectional study compared **AI large language models** (ChatGPT-4 and Gemini) with 28 chest-disease resident physicians at a tertiary-care university hospital in analyzing four clinical scenarios. - Clinical scenarios covered massive **pulmonary embolism**, **chronic obstructive pulmonary disease (COPD)**, **asthma**, and severe **pneumonia/sepsis**. - Responses from residents and AI models were scored by blinded experts using current guideline-based standards including **GOLD**, **GINA**, and **American Thoracic Society** criteria. - AI models achieved significantly higher overall scores than residents on structured questions testing theoretical knowledge, classification, and listing contraindications (P < 0.05). - Residents performed comparably to AI in emergency, results-oriented management tasks such as shock or immediate intervention, relying on practical, telegraphic answers. - AI provided a broader differential diagnosis spectrum, while residents favored concise, practice-focused responses. - Authors conclude that ChatGPT and Gemini show strong potential as **clinical decision-support** and educational assistants but should complement—not replace—human clinical reasoning and emergency management. - No conflicts of interest were declared by the authors. Full-text is linked via Galenos Publishing; PMID 41979097 and DOI 10.4274/ThoracResPract.2026.2026-1-2.
## Clinical Analysis & Structured Key Points
Clipboard, Search History, and several other advanced features are temporarily unavailable. [ Skip to main page content ](https://pubmed.ncbi.nlm.nih.gov/41979097/#article-details) ![U.S. flag](https://cdn.ncbi.nlm.nih.gov/coreutils/uswds/img/favicons/favicon-57.png) An official website of the United States government Here's how you know ![Dot gov](https://cdn.ncbi.nlm.nih.gov/coreutils/uswds/img/icon-dot-gov.svg) **The .gov means it’s official.** Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site. ![Https](https://cdn.ncbi.nlm.nih.gov/coreutils/uswds/img/icon-https.svg) **The site is secure.** The **https://** ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely. [ ![NIH NLM Logo](https://cdn.ncbi.nlm.nih.gov/coreutils/nwds/img/logos/AgencyLogo.svg) ](https://www.ncbi.nlm.nih.gov/) [Log in](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F41979097%2F) Show account info Close #### Account Logged in as: **username** * [Dashboard](https://www.ncbi.nlm.nih.gov/myncbi/) * [Publications](https://www.ncbi.nlm.nih.gov/myncbi/collections/bibliography/) * [Account settings](https://www.ncbi.nlm.nih.gov/account/settings/) * [Log out](https://www.ncbi.nlm.nih.gov/account/signout/?back_url=https%3A//pubmed.ncbi.nlm.nih.gov/41979097/) [Access keys](https://www.ncbi.nlm.nih.gov/guide/browsers/#ncbi_accesskeys) [NCBI Homepage](https://www.ncbi.nlm.nih.gov) [MyNCBI Homepage](https://pubmed.ncbi.nlm.nih.gov/myncbi/) [Main Content](https://pubmed.ncbi.nlm.nih.gov/41979097/#maincontent) [Main Navigation](https://pubmed.ncbi.nlm.nih.gov/41979097/) [ ![pubmed logo](https://cdn.ncbi.nlm.nih.gov/pubmed/c24ab723-7c80-48cd-9c68-022ded852586/core/images/pubmed-logo-blue.svg) ](https://pubmed.ncbi.nlm.nih.gov/) [ ](https://pubmed.ncbi.nlm.nih.gov/41979097/ "Show search bar") Search: [](https://pubmed.ncbi.nlm.nih.gov/41979097/ "Clear search input")Search [Advanced](https://pubmed.ncbi.nlm.nih.gov/advanced/) [ Clipboard ](https://pubmed.ncbi.nlm.nih.gov/clipboard/) [ User Guide ](https://pubmed.ncbi.nlm.nih.gov/help/) Save Email Send to * [ Clipboard ](https://pubmed.ncbi.nlm.nih.gov/41979097/) * [My Bibliography](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F41979097%2F%23open-bibliography-panel) * [Collections](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F41979097%2F%23open-collections-panel) * [Citation manager](https://pubmed.ncbi.nlm.nih.gov/41979097/) Display options Display options Format Abstract PubMed PMID ## Save citation to file Format: Summary (text) PubMed PMID Abstract (text) CSV Create file Cancel ## Email citation Email address has not been verified. Go to [ My NCBI account settings ](https://account.ncbi.nlm.nih.gov/settings/) to confirm your email and then refresh this page. To: Subject: Body: Format: Summary Summary (text) Abstract Abstract (text) MeSH and other data Send email Cancel ### Add to Collections * Create a new collection * Add to an existing collection Name your collection: Name must be less than 100 characters Choose a collection: Unable to load your collection due to an error [Please try again](https://pubmed.ncbi.nlm.nih.gov/41979097/) Add Cancel ### Add to My Bibliography * My Bibliography Unable to load your delegates due to an error [Please try again](https://pubmed.ncbi.nlm.nih.gov/41979097/) Add Cancel ## Your saved search Name of saved search: Search terms: [Test search terms](https://pubmed.ncbi.nlm.nih.gov/41979097/) Would you like email updates of new search results? Saved Search Alert Radio Buttons * Yes * No Email: ([change](https://www.ncbi.nlm.nih.gov/account/settings/)) Frequency: Monthly Weekly Daily Which day? The first Sunday The first Monday The first Tuesday The first Wednesday The first Thursday The first Friday The first Saturday The first day The first weekday Which day? Sunday Monday Tuesday Wednesday Thursday Friday Saturday Report format: Summary Summary (text) Abstract Abstract (text) PubMed Send at most: 1 item 5 items 10 items 20 items 50 items 100 items 200 items Send even when there aren't any new results Optional text in email: Save Cancel ## Create a file for external citation management software Create file Cancel ## Your RSS Feed Name of RSS Feed: Number of items displayed: 5 10 15 20 50 100 Create RSS Cancel RSS Link Copy ### Full text links [![Galenos Yayinevi full text link](https://cdn.ncbi.nlm.nih.gov/corehtml/query/egifs/http:--galenos.com.tr-icon-PUBMED-galenosyay.png) Galenos Yayinevi ](https://doi.org/10.4274/ThoracResPract.2026.2026-1-2 "See full text options at Galenos Yayinevi") [ Full text links ](https://pubmed.ncbi.nlm.nih.gov/41979097/) ### Actions Cite Collections Add to Collections * Create a new collection * Add to an existing collection Name your collection: Name must be less than 100 characters Choose a collection: Unable to load your collection due to an error [Please try again](https://pubmed.ncbi.nlm.nih.gov/41979097/) Add Cancel Permalink Permalink Copy Display options Display options Format Abstract PubMed PMID ### Page navigation * [ Title & authors ](https://pubmed.ncbi.nlm.nih.gov/41979097/#heading) * [ Abstract ](https://pubmed.ncbi.nlm.nih.gov/41979097/#abstract) * [ Conflict of interest statement ](https://pubmed.ncbi.nlm.nih.gov/41979097/#conflict-of-interest) * [ LinkOut - more resources ](https://pubmed.ncbi.nlm.nih.gov/41979097/#linkout) Title & authors Abstract Conflict of interest statement LinkOut - more resources Thorac Res Pract Actions * [ Search in PubMed ](https://pubmed.ncbi.nlm.nih.gov/?term=%22Thorac+Res+Pract%22%5Bjour%5D&sort=date&sort_order=desc) * [ Search in NLM Catalog ](https://www.ncbi.nlm.nih.gov/nlmcatalog?term=%22Thorac+Res+Pract%22%5BTitle+Abbreviation%5D) * [ Add to Search ](https://pubmed.ncbi.nlm.nih.gov/41979097/) . 2026 Sep 7;27(5):275-279. doi: 10.4274/ThoracResPract.2026.2026-1-2. Epub 2026 Apr 14. # Comparison of AI-based Chatbot Performance in Analyzing Clinical Scenarios versus Medical Residents: A Novel Approach in Chest Diseases Education [Mehmet Hakan Bilgin](https://pubmed.ncbi.nlm.nih.gov/?term=Bilgin+MH&cauthor_id=41979097)[ 1 ](https://pubmed.ncbi.nlm.nih.gov/41979097/#full-view-affiliation-1 "Department of Chest Diseases, Van Yüzüncü Yıl University Faculty of Medicine, Van, Türkiye."), [Hamit Hakan Alp](https://pubmed.ncbi.nlm.nih.gov/?term=Alp+HH&cauthor_id=41979097)[ 2 ](https://pubmed.ncbi.nlm.nih.gov/41979097/#full-view-affiliation-2 "Department of Biochemistry, Van Yüzüncü Yıl University Faculty of Medicine, Van, Türkiye.") Affiliations Expand ### Affiliations * 1 Department of Chest Diseases, Van Yüzüncü Yıl University Faculty of Medicine, Van, Türkiye. * 2 Department of Biochemistry, Van Yüzüncü Yıl University Faculty of Medicine, Van, Türkiye. * PMID: **41979097** * DOI: [ 10.4274/ThoracResPract.2026.2026-1-2 ](https://doi.org/10.4274/thoracrespract.2026.2026-1-2) Free article Item in Clipboard # Comparison of AI-based Chatbot Performance in Analyzing Clinical Scenarios versus Medical Residents: A Novel Approach in Chest Diseases Education Mehmet Hakan Bilgin et al. Thorac Res Pract. 2026. Free article Show details Display options Display options Format Abstract PubMed PMID Thorac Res Pract Actions * [ Search in PubMed ](https://pubmed.ncbi.nlm.nih.gov/?term=%22Thorac+Res+Pract%22%5Bjour%5D&sort=date&sort_order=desc) * [ Search in NLM Catalog ](https://www.ncbi.nlm.nih.gov/nlmcatalog?term=%22Thorac+Res+Pract%22%5BTitle+Abbreviation%5D) * [ Add to Search ](https://pubmed.ncbi.nlm.nih.gov/41979097/) . 2026 Sep 7;27(5):275-279. doi: 10.4274/ThoracResPract.2026.2026-1-2. Epub 2026 Apr 14. ### Authors [Mehmet Hakan Bilgin](https://pubmed.ncbi.nlm.nih.gov/?term=Bilgin+MH&cauthor_id=41979097)[ 1 ](https://pubmed.ncbi.nlm.nih.gov/41979097/#short-view-affiliation-1 "Department of Chest Diseases, Van Yüzüncü Yıl University Faculty of Medicine, Van, Türkiye."), [Hamit Hakan Alp](https://pubmed.ncbi.nlm.nih.gov/?term=Alp+HH&cauthor_id=41979097)[ 2 ](https://pubmed.ncbi.nlm.nih.gov/41979097/#short-view-affiliation-2 "Department of Biochemistry, Van Yüzüncü Yıl University Faculty of Medicine, Van, Türkiye.") ### Affiliations * 1 Department of Chest Diseases, Van Yüzüncü Yıl University Faculty of Medicine, Van, Türkiye. * 2 Department of Biochemistry, Van Yüzüncü Yıl University Faculty of Medicine, Van, Türkiye. * PMID: **41979097** * DOI: [ 10.4274/ThoracResPract.2026.2026-1-2 ](https://doi.org/10.4274/thoracrespract.2026.2026-1-2) Item in Clipboard Full text links Cite Display options Display options Format Abstract PubMed PMID ## Abstract **Objective:** Rapid advancements in artificial intelligence (AI) technologies offer new opportunities in medical education. The aim of this study is to compare the performance of large language models, specifically ChatGPT-4 and Gemini, in analyzing clinical scenarios with that of chest diseases research assistants (residents), and to evaluate their potential roles in medical education. **Material and methods:** This cross-sectional, comparative study included 28 resident physicians working in the department of chest diseases at a tertiary-care university hospital. Four clinical scenarios involving diagnoses of massive pulmonary embolism, chronic obstructive pulmonary disease, asthma, and severe pneumonia/sepsis were presented to both participants and AI models (ChatGPT-4 and Gemini). Responses were scored by blinded experts based on current guidelines (Global Initiative for Chronic Obstructive Lung Disease, Global Initiative for Asthma, American Thoracic Society). **Results:** AI models achieved significantly higher scores than residents, particularly on structured questions requiring theoretical knowledge, classification skills, and the listing of contraindications (_P_ < 0.05). However, it was observed that residents achieved success levels similar to those of AI models in situations requiring emergency intervention (e.g., shock management) through practical, results-oriented approaches. While AI models provided a broader spectrum in differential diagnosis, residents preferred "telegraphic" and practice-oriented responses. **Conclusion:** ChatGPT and Gemini have significant potential as clinical decision-support systems and educational assistants. However, rather than replacing human factors in clinical reasoning and emergency management, they should be positioned as complementary tools that accelerate physicians' access to theoretical knowledge. **Keywords:** Education; artificial intelligence; clinical; clinical reasoning; decision support systems; diagnosis; differential; humans; medical. Copyright© 2026 The Author(s). Published by Galenos Publishing House on behalf of Turkish Thoracic Society. [PubMed Disclaimer](https://pubmed.ncbi.nlm.nih.gov/disclaimer/) ## Conflict of interest statement No conflict of interest was declared by the authors. ## LinkOut - more resources * ### Full Text Sources * [ Galenos Yayinevi ](https://doi.org/10.4274/ThoracResPract.2026.2026-1-2) **Full text links** [x] [![Galenos Yayinevi full text link](https://cdn.ncbi.nlm.nih.gov/corehtml/query/egifs/http:--galenos.com.tr-icon-PUBMED-galenosyay.png) Galenos Yayinevi ](https://doi.org/10.4274/ThoracResPract.2026.2026-1-2 "See full text options at Galenos Yayinevi") [x] Cite Copy Download .nbib .nbib Format: AMA APA MLA NLM **Send To** * [Clipboard](https://pubmed.ncbi.nlm.nih.gov/41979097/) * [Email](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F41979097%2F%23open-email-panel) * [Save](https://pubmed.ncbi.nlm.nih.gov/41979097/) * [My Bibliography](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F41979097%2F%23open-bibliography-panel) * [Collections](https://account.ncbi.nlm.nih.gov/?back_url=https%3A%2F%2Fpubmed.ncbi.nlm.nih.gov%2F41979097%2F%23open-collections-panel) * [Citation Manager](https://pubmed.ncbi.nlm.nih.gov/41979097/) [x] NCBI Literature Resources [MeSH](https://www.ncbi.nlm.nih.gov/mesh/) [PMC](https://www.ncbi.nlm.nih.gov/pmc/) [Bookshelf](https://www.ncbi.nlm.nih.gov/books) [Disclaimer](https://pubmed.ncbi.nlm.nih.gov/disclaimer/) The PubMed wordmark and PubMed logo are registered trademarks of the U.S. Department of Health and Human Services (HHS). Unauthorized use of these marks is strictly prohibited. Follow NCBI [ Twitter ](https://twitter.com/ncbi) [ Facebook ](https://www.facebook.com/ncbi.nlm) [ LinkedIn ](https://www.linkedin.com/company/ncbinlm) [ GitHub ](https://github.com/ncbi) [ ](https://ncbiinsights.ncbi.nlm.nih.gov/) [Connect with NLM](https://www.nlm.nih.gov/socialmedia/index.html) * [ Twitter ](https://twitter.com/NLM_NIH) * [ SM-Facebook ](https://www.facebook.com/nationallibraryofmedicine) * [ SM-Youtube ](https://www.youtube.com/user/NLMNIH) National Library of Medicine [8600 Rockville Pike Bethesda, MD 20894](https://www.google.com/maps/place/8600+Rockville+Pike,+Bethesda,+MD+20894/@38.9959508,-77.101021,17z/data=!3m1!4b1!4m5!3m4!1s0x89b7c95e25765ddb:0x19156f88b27635b8!8m2!3d38.9959508!4d-77.0988323) [Web Policies](https://www.nlm.nih.gov/web_policies.html) [FOIA](https://www.nih.gov/institutes-nih/nih-office-director/office-communications-public-liaison/freedom-information-act-office) [HHS Vulnerability Disclosure](https://www.hhs.gov/vulnerability-disclosure-policy/index.html) [Help](https://support.nlm.nih.gov/?pagename=pubmed%3Apubmed%3Aabstract%3ANONE) [Accessibility](https://www.nlm.nih.gov/accessibility.html) [Careers](https://www.nlm.nih.gov/careers/careers.html) * [NLM](https://www.nlm.nih.gov/) * [NIH](https://www.nih.gov/) * [HHS](https://www.hhs.gov/) * [USA.gov](https://www.usa.gov/) ![](https://pubmed.ncbi.nlm.nih.gov/stat?browserheight=600&browserwidth=1080&colorDepth=24&connection_effectivetype=4g&connection_type=&cookieSize=307&cookieenabled=true&is_browser_supported=true&jsevent=domready&language_code=en-US&log_category=literature&log_displayeduids=41979097&log_icons_present=true&log_op=retrieve&log_source_db=pubmed&myncbi_signed_in=false&ncbi_algorithm=&ncbi_app=pubmed&ncbi_cost_center=pubmed&ncbi_db=pubmed&ncbi_featured_srcdb=&ncbi_nwds=yes&ncbi_nwds_ver=1.2.5&ncbi_pcid=&ncbi_pdid=abstract&ncbi_phid=3F83000118D463D500003926C5C946E5.1.m_3&ncbi_program=&ncbi_timesinceload=11&ncbi_timesincenavstart=1108&ncbi_uid=41979097&pagename=pubmed%3Apubmed%3Aabstract%3ANONE&pinger_in_iframe=false&screenavailheight=600&screenavailwidth=1080&screenheight=600&screenwidth=1080&server=pubmed.ncbi.nlm.nih.gov&sgSource=native&sgversion=0.42.0&sgversion_hotfix=0&sgversion_major=0&sgversion_minor=42&spa_index=0)
## Related Clinical Research

- [Mitochondrial Fatty Acid Oxidation and Its Regulatory Role in Respiratory Diseases](https://medichelpline.com/clinical-feed/pubmed-42275921.md) (DOI: 10.1016/j.intimp.2026.116995)
- [Precision Nanomedicine for Pulmonary Diseases: Nanoparticle Design to Clinical Translation](https://medichelpline.com/clinical-feed/pubmed-42675037.md) (DOI: 10.1038/s41392-026-02982-0)
- [Nasal transcriptomics identify five asthma endotypes including T2‑low profiles in Puerto Rican and](https://medichelpline.com/clinical-feed/medrxiv-18-nasal-transcriptomics-characterize-t-helper-t-2-low-asthma-endotypes-in-a-study.md)
- [Triglyceride-Glucose (TyG) Index and Mortality in Non-Diabetic Fibrotic Lung Disease on Antifibrot](https://medichelpline.com/clinical-feed/plos-one-1-association-between-triglyceride-glucose-index-and-all-cause-mortality-in-non.md)
- [Inhaled ARO-RAGE siRNA for pulmonary inflammation: first-in-human randomized trial](https://medichelpline.com/clinical-feed/nature-2-inhaled-sirna-therapy-targeting-rage-for-pulmonary-inflammation-a-first-in.md)

## Navigation
- [← Back to Critical Care Feed](https://medichelpline.com/clinical-feed/critical-care.md)
- [← All Clinical Specialties](https://medichelpline.com/clinical-feed.md)
## Medical & Regulatory Disclaimer

> [!CAUTION]
> MedicHelpline content is structured for research, educational, and professional discovery purposes. It does not constitute individual medical advice, clinical diagnosis, or treatment recommendations.
> Always verify dosing, contraindications, and regulatory alerts against official product labeling and primary regulatory sources before clinical decision-making.