View in EDS PDF Full Text

ChatGPT versus human authors: A comparative study of concept maps for clinical reasoning training with virtual patients.

Saved in:
Bibliographic Details
Title: ChatGPT versus human authors: A comparative study of concept maps for clinical reasoning training with virtual patients.
Authors: Szydlak, Renata1 (AUTHOR) renata.szydlak@uj.edu.pl, Kiyak, Yavuz Selim2 (AUTHOR), Hege, Inga3 (AUTHOR), Górski, Stanisław4 (AUTHOR), Linglart, Lea5,6 (AUTHOR), Shchudrova, Tetiana7 (AUTHOR), Torre, Dario8 (AUTHOR), Kononowicz, Andrzej A.1 (AUTHOR)
Source: Medical Teacher. Apr2026, Vol. 48 Issue 4, p712-720. 9p.
Subject Terms: *Artificial intelligence, *Teaching aids, *Educational tests & measurements, *Decision making, *Learning, *Research bias, *Information retrieval, *Clinical competence, *Concepts, *Computer assisted instruction, *Comparative studies, *Educational attainment, *Inter-observer reliability, Medical logic, Psychology of physicians, T-test (Statistics), Research funding, Research evaluation, Natural language processing, Judgment sampling, Diagnosis, Descriptive statistics, Simulated patients, Statistics, Data analysis software, User interfaces
Abstract: Purpose: This study investigates whether ChatGPT can generate clinically accurate and pedagogically valuable maps for clinical reasoning (CR) training. The aim is to assess its potential as a tool for supporting the creation of high-quality educational resources for CR training. Materials and methods: We selected 10 diverse virtual patients (VPs) from the European iCoViP project. For each case, CR concept maps were generated by a custom ChatGPT model and compared to expert-created maps available in the CASUS VP system. The comparison encompassed structural metrics (number of concepts, connections, and graph density), clinical content quality (clinical expert evaluation of concept and connection validity), and pedagogical utility (medical educator assessment of clarity, abstraction, and progression). Statistical analysis included Student's t-tests and interrater reliability using weighted Cohen's kappa. Results: ChatGPT-generated maps contained significantly more concepts and connections than expert maps, indicating higher structural complexity (p < 0.001), though graph density did not differ significantly. Clinician evaluations showed comparable clinical content quality across both groups, with no statistically significant differences in concept or connection ratings. The educational review revealed that while ChatGPT maps offered comprehensive information, they lacked abstraction, prioritization, and contextual alignment, occasionally exceeding the optimal cognitive load for learners. Conclusions: ChatGPT can reliably generate concept maps that match expert-level clinical accuracy. However, limitations in educational clarity and usability underscore the need for expert refinement. With appropriate oversight, large language models (LLMs) such as ChatGPT can support efficient development of learning resources for CR education. [ABSTRACT FROM AUTHOR]
Copyright of Medical Teacher is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Education Research Complete
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: ehh
DbLabel: Education Research Complete
An: 192434770
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: ChatGPT versus human authors: A comparative study of concept maps for clinical reasoning training with virtual patients.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Szydlak%2C+Renata%22&quot;&gt;Szydlak, Renata&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; renata.szydlak@uj.edu.pl&lt;/i&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Kiyak%2C+Yavuz+Selim%22&quot;&gt;Kiyak, Yavuz Selim&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Hege%2C+Inga%22&quot;&gt;Hege, Inga&lt;/searchLink&gt;&lt;relatesTo&gt;3&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22G&#243;rski%2C+Stanisław%22&quot;&gt;G&#243;rski, Stanisław&lt;/searchLink&gt;&lt;relatesTo&gt;4&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Linglart%2C+Lea%22&quot;&gt;Linglart, Lea&lt;/searchLink&gt;&lt;relatesTo&gt;5,6&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Shchudrova%2C+Tetiana%22&quot;&gt;Shchudrova, Tetiana&lt;/searchLink&gt;&lt;relatesTo&gt;7&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Torre%2C+Dario%22&quot;&gt;Torre, Dario&lt;/searchLink&gt;&lt;relatesTo&gt;8&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Kononowicz%2C+Andrzej+A%2E%22&quot;&gt;Kononowicz, Andrzej A.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22Medical+Teacher%22&quot;&gt;Medical Teacher&lt;/searchLink&gt;. Apr2026, Vol. 48 Issue 4, p712-720. 9p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Artificial+intelligence%22&quot;&gt;Artificial intelligence&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Teaching+aids%22&quot;&gt;Teaching aids&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Educational+tests+%26+measurements%22&quot;&gt;Educational tests &amp; measurements&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Decision+making%22&quot;&gt;Decision making&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Learning%22&quot;&gt;Learning&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Research+bias%22&quot;&gt;Research bias&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Information+retrieval%22&quot;&gt;Information retrieval&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Clinical+competence%22&quot;&gt;Clinical competence&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Concepts%22&quot;&gt;Concepts&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Computer+assisted+instruction%22&quot;&gt;Computer assisted instruction&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Comparative+studies%22&quot;&gt;Comparative studies&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Educational+attainment%22&quot;&gt;Educational attainment&lt;/searchLink&gt;&lt;br /&gt;*&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Inter-observer+reliability%22&quot;&gt;Inter-observer reliability&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Medical+logic%22&quot;&gt;Medical logic&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Psychology+of+physicians%22&quot;&gt;Psychology of physicians&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22T-test+%28Statistics%29%22&quot;&gt;T-test (Statistics)&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Research+funding%22&quot;&gt;Research funding&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Research+evaluation%22&quot;&gt;Research evaluation&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Natural+language+processing%22&quot;&gt;Natural language processing&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Judgment+sampling%22&quot;&gt;Judgment sampling&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Diagnosis%22&quot;&gt;Diagnosis&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Descriptive+statistics%22&quot;&gt;Descriptive statistics&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Simulated+patients%22&quot;&gt;Simulated patients&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Statistics%22&quot;&gt;Statistics&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Data+analysis+software%22&quot;&gt;Data analysis software&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22User+interfaces%22&quot;&gt;User interfaces&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Purpose: This study investigates whether ChatGPT can generate clinically accurate and pedagogically valuable maps for clinical reasoning (CR) training. The aim is to assess its potential as a tool for supporting the creation of high-quality educational resources for CR training. Materials and methods: We selected 10 diverse virtual patients (VPs) from the European iCoViP project. For each case, CR concept maps were generated by a custom ChatGPT model and compared to expert-created maps available in the CASUS VP system. The comparison encompassed structural metrics (number of concepts, connections, and graph density), clinical content quality (clinical expert evaluation of concept and connection validity), and pedagogical utility (medical educator assessment of clarity, abstraction, and progression). Statistical analysis included Student&#39;s t-tests and interrater reliability using weighted Cohen&#39;s kappa. Results: ChatGPT-generated maps contained significantly more concepts and connections than expert maps, indicating higher structural complexity (p &lt; 0.001), though graph density did not differ significantly. Clinician evaluations showed comparable clinical content quality across both groups, with no statistically significant differences in concept or connection ratings. The educational review revealed that while ChatGPT maps offered comprehensive information, they lacked abstraction, prioritization, and contextual alignment, occasionally exceeding the optimal cognitive load for learners. Conclusions: ChatGPT can reliably generate concept maps that match expert-level clinical accuracy. However, limitations in educational clarity and usability underscore the need for expert refinement. With appropriate oversight, large language models (LLMs) such as ChatGPT can support efficient development of learning resources for CR education. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;Copyright of Medical Teacher is the property of Taylor &amp; Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder&#39;s express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.&lt;/i&gt; (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=ehh&AN=192434770
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/0142159X.2025.2583403
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 9
        StartPage: 712
    Subjects:
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Teaching aids
        Type: general
      – SubjectFull: Educational tests & measurements
        Type: general
      – SubjectFull: Decision making
        Type: general
      – SubjectFull: Learning
        Type: general
      – SubjectFull: Research bias
        Type: general
      – SubjectFull: Information retrieval
        Type: general
      – SubjectFull: Clinical competence
        Type: general
      – SubjectFull: Concepts
        Type: general
      – SubjectFull: Computer assisted instruction
        Type: general
      – SubjectFull: Comparative studies
        Type: general
      – SubjectFull: Educational attainment
        Type: general
      – SubjectFull: Inter-observer reliability
        Type: general
      – SubjectFull: Medical logic
        Type: general
      – SubjectFull: Psychology of physicians
        Type: general
      – SubjectFull: T-test (Statistics)
        Type: general
      – SubjectFull: Research funding
        Type: general
      – SubjectFull: Research evaluation
        Type: general
      – SubjectFull: Natural language processing
        Type: general
      – SubjectFull: Judgment sampling
        Type: general
      – SubjectFull: Diagnosis
        Type: general
      – SubjectFull: Descriptive statistics
        Type: general
      – SubjectFull: Simulated patients
        Type: general
      – SubjectFull: Statistics
        Type: general
      – SubjectFull: Data analysis software
        Type: general
      – SubjectFull: User interfaces
        Type: general
    Titles:
      – TitleFull: ChatGPT versus human authors: A comparative study of concept maps for clinical reasoning training with virtual patients.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Szydlak, Renata
      – PersonEntity:
          Name:
            NameFull: Kiyak, Yavuz Selim
      – PersonEntity:
          Name:
            NameFull: Hege, Inga
      – PersonEntity:
          Name:
            NameFull: Górski, Stanisław
      – PersonEntity:
          Name:
            NameFull: Linglart, Lea
      – PersonEntity:
          Name:
            NameFull: Shchudrova, Tetiana
      – PersonEntity:
          Name:
            NameFull: Torre, Dario
      – PersonEntity:
          Name:
            NameFull: Kononowicz, Andrzej A.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 0142159X
          Numbering:
            – Type: volume
              Value: 48
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: Medical Teacher
              Type: main
ResultId 1