Academic Journal
View in EDS

Leveraging artificial intelligence to accelerate competency development in diagnostic reasoning of medical students.

Bibliographic Details
Title: Leveraging artificial intelligence to accelerate competency development in diagnostic reasoning of medical students.
Authors: Sur M; Pediatrics, Baylor College of Medicine and Texas Children's Hospital, Houston, TX, USA., Dissaneevate S; Pediatrics, Prince of Songkla University, Hat Yai, Thailand., Yuenyongviwat A; Pediatrics, Prince of Songkla University Faculty of Medicine, Hat Yai, Thailand., Ruangnapa K; Pediatrics, Prince of Songkla University, Hat Yai, Thailand., Liaw W; Pediatrics, University of Houston Tilman J. Fertitta Family College of Medicine, Houston, TX, USA., Boedeker P; Education, Innovation and Technology, Baylor College of Medicine, Houston, TX, USA., Kumar S; Pediatrics, Baylor College of Medicine, Houston, TX, USA., Rissmiller B; Pediatrics, Baylor College of Medicine, Houston, TX, USA., Thammasitboon S; Pediatrics, Baylor College of Medicine, Houston, TX, USA.
Source: Medical teacher [Med Teach] 2026 Oct; Vol. 48 (10), pp. 1699-1707. Date of Electronic Publication: 2026 Mar 17.
Publication Type: Journal Article; Randomized Controlled Trial
Language: English
Journal Info: Publisher: Informa Healthcare Country of Publication: England NLM ID: 7909593 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1466-187X (Electronic) Linking ISSN: 0142159X NLM ISO Abbreviation: Med Teach Subsets: MEDLINE
Imprint Name(s): Publication: London : Informa Healthcare
Original Publication: London, Update Publications.
MeSH Terms: Students, Medical*/psychology , Education, Medical, Undergraduate*/methods , Artificial Intelligence* , Clinical Competence* , Clinical Reasoning*, Diagnostic Errors/prevention & control ; Humans ; Male ; Female ; Thailand
Abstract: Introduction: Diagnostic errors remain a critical patient safety concern, yet teaching diagnostic reasoning is challenging due to its complex, context-specific nature. Traditional teaching methods emphasize analytical reasoning but often neglect non-analytical, pattern recognition processes that are grounded in script theory. Script theory highlights illness scripts-structured mental representations of diseases-as foundational to diagnostic expertise. Advances in artificial intelligence (AI) offer opportunities to support illness script formulation through personalized, scalable feedback. This study evaluated whether chatbot-enabled instruction and feedback improve medical students' illness script quality compared with conventional instruction techniques.
Methods: We conducted a parallel-group randomized controlled trial with 83 medical students at Prince of Songkla University, Hat Yai, Thailand. Participants were randomized to conventional instruction or chatbot-enabled instruction using Microsoft Copilot. Both groups received didactic instruction, followed by illness script formulation tasks at three timepoints: pre-test (T1), immediate post-test (T2), and post-intervention with new cases (T3). Illness scripts were assessed using the validated Illness Script Assessment Tool (ISAT), which evaluates structure, content, richness, and maturity. Data was analyzed using cumulative link mixed-effects models.
Results: Baseline illness script quality was comparable between groups. Chatbot-enabled instruction produced significantly greater improvements in script structure (OR 3.7), content (OR 3.3), and maturity (OR 2.9) at immediate post, with gains sustained at transfer testing for structure. Richness scores showed delayed improvement (OR 2.9). Composite ISAT scores confirmed durable improvements (OR 3.2 at T2; OR 2.7 at T3).
Discussion: Chatbot-enabled instruction accelerated and enhanced illness script development compared with conventional methods, operationalizing deliberate practice principles and making non-analytical reasoning teachable. By integrating structured pedagogy with scalable AI feedback, this approach reduces educator burden while fostering diagnostic expertise. Future multi-site studies should examine long-term retention, clinical transfer, and AI feedback fidelity to ensure reliability and equity.
Contributed Indexing: Keywords: AI-enabled instruction; Illness scripts; diagnostic reasoning
Entry Date(s): Date Created: 20260317 Date Completed: 20261001 Latest Revision: 20261001
Update Code: 20261001
DOI: 10.1080/0142159X.2026.2641769
PMID: 41843425
Database: MEDLINE
FullText Text:
  Availability: 0
Header DbId: cmedm
DbLabel: MEDLINE
An: 41843425
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Leveraging artificial intelligence to accelerate competency development in diagnostic reasoning of medical students.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Sur+M%22">Sur M</searchLink>; Pediatrics, Baylor College of Medicine and Texas Children's Hospital, Houston, TX, USA.<br /><searchLink fieldCode="AU" term="%22Dissaneevate+S%22">Dissaneevate S</searchLink>; Pediatrics, Prince of Songkla University, Hat Yai, Thailand.<br /><searchLink fieldCode="AU" term="%22Yuenyongviwat+A%22">Yuenyongviwat A</searchLink>; Pediatrics, Prince of Songkla University Faculty of Medicine, Hat Yai, Thailand.<br /><searchLink fieldCode="AU" term="%22Ruangnapa+K%22">Ruangnapa K</searchLink>; Pediatrics, Prince of Songkla University, Hat Yai, Thailand.<br /><searchLink fieldCode="AU" term="%22Liaw+W%22">Liaw W</searchLink>; Pediatrics, University of Houston Tilman J. Fertitta Family College of Medicine, Houston, TX, USA.<br /><searchLink fieldCode="AU" term="%22Boedeker+P%22">Boedeker P</searchLink>; Education, Innovation and Technology, Baylor College of Medicine, Houston, TX, USA.<br /><searchLink fieldCode="AU" term="%22Kumar+S%22">Kumar S</searchLink>; Pediatrics, Baylor College of Medicine, Houston, TX, USA.<br /><searchLink fieldCode="AU" term="%22Rissmiller+B%22">Rissmiller B</searchLink>; Pediatrics, Baylor College of Medicine, Houston, TX, USA.<br /><searchLink fieldCode="AU" term="%22Thammasitboon+S%22">Thammasitboon S</searchLink>; Pediatrics, Baylor College of Medicine, Houston, TX, USA.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%227909593%22">Medical teacher</searchLink> [Med Teach] 2026 Oct; Vol. 48 (10), pp. 1699-1707. <i>Date of Electronic Publication: </i>2026 Mar 17.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article; Randomized Controlled Trial
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Informa+Healthcare%22">Informa Healthcare </searchLink><i>Country of Publication: </i>England <i>NLM ID: </i>7909593 <i>Publication Model: </i>Print-Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>1466-187X (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%220142159X%22">0142159X </searchLink><i>NLM ISO Abbreviation: </i>Med Teach <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Publication</i>: London : Informa Healthcare<br /><i>Original Publication</i>: London, Update Publications.
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Students%2C+Medical%22">Students, Medical*</searchLink>/<searchLink fieldCode="MM" term="%22Students%2C+Medical+psychology%22">psychology</searchLink> <br /><searchLink fieldCode="MM" term="%22Education%2C+Medical%2C+Undergraduate%22">Education, Medical, Undergraduate*</searchLink>/<searchLink fieldCode="MM" term="%22Education%2C+Medical%2C+Undergraduate+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Artificial+Intelligence%22">Artificial Intelligence*</searchLink> <br /><searchLink fieldCode="MM" term="%22Clinical+Competence%22">Clinical Competence*</searchLink> <br /><searchLink fieldCode="MM" term="%22Clinical+Reasoning%22">Clinical Reasoning*</searchLink><br /><searchLink fieldCode="MH" term="%22Diagnostic+Errors%22">Diagnostic Errors</searchLink>/<searchLink fieldCode="MH" term="%22Diagnostic+Errors+prevention+%26+control%22">prevention & control</searchLink> ; <searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Male%22">Male</searchLink> ; <searchLink fieldCode="MH" term="%22Female%22">Female</searchLink> ; <searchLink fieldCode="MH" term="%22Thailand%22">Thailand</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Introduction: Diagnostic errors remain a critical patient safety concern, yet teaching diagnostic reasoning is challenging due to its complex, context-specific nature. Traditional teaching methods emphasize analytical reasoning but often neglect non-analytical, pattern recognition processes that are grounded in script theory. Script theory highlights illness scripts-structured mental representations of diseases-as foundational to diagnostic expertise. Advances in artificial intelligence (AI) offer opportunities to support illness script formulation through personalized, scalable feedback. This study evaluated whether chatbot-enabled instruction and feedback improve medical students' illness script quality compared with conventional instruction techniques.<br />Methods: We conducted a parallel-group randomized controlled trial with 83 medical students at Prince of Songkla University, Hat Yai, Thailand. Participants were randomized to conventional instruction or chatbot-enabled instruction using Microsoft Copilot. Both groups received didactic instruction, followed by illness script formulation tasks at three timepoints: pre-test (T1), immediate post-test (T2), and post-intervention with new cases (T3). Illness scripts were assessed using the validated Illness Script Assessment Tool (ISAT), which evaluates structure, content, richness, and maturity. Data was analyzed using cumulative link mixed-effects models.<br />Results: Baseline illness script quality was comparable between groups. Chatbot-enabled instruction produced significantly greater improvements in script structure (OR 3.7), content (OR 3.3), and maturity (OR 2.9) at immediate post, with gains sustained at transfer testing for structure. Richness scores showed delayed improvement (OR 2.9). Composite ISAT scores confirmed durable improvements (OR 3.2 at T2; OR 2.7 at T3).<br />Discussion: Chatbot-enabled instruction accelerated and enhanced illness script development compared with conventional methods, operationalizing deliberate practice principles and making non-analytical reasoning teachable. By integrating structured pedagogy with scalable AI feedback, this approach reduces educator burden while fostering diagnostic expertise. Future multi-site studies should examine long-term retention, clinical transfer, and AI feedback fidelity to ensure reliability and equity.
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>AI-enabled instruction; Illness scripts; diagnostic reasoning
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260317 <i>Date Completed: </i>20261001 <i>Latest Revision: </i>20261001
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20261001
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1080/0142159X.2026.2641769
– Name: AN
  Label: PMID
  Group: ID
  Data: 41843425
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=41843425
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/0142159X.2026.2641769
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 1699
    Subjects:
      – SubjectFull: Diagnostic Errors prevention & control
        Type: general
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Male
        Type: general
      – SubjectFull: Female
        Type: general
      – SubjectFull: Thailand
        Type: general
      – SubjectFull: Students, Medical psychology
        Type: general
      – SubjectFull: Education, Medical, Undergraduate methods
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Clinical Competence
        Type: general
      – SubjectFull: Clinical Reasoning
        Type: general
    Titles:
      – TitleFull: Leveraging artificial intelligence to accelerate competency development in diagnostic reasoning of medical students.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Sur M
      – PersonEntity:
          Name:
            NameFull: Dissaneevate S
      – PersonEntity:
          Name:
            NameFull: Yuenyongviwat A
      – PersonEntity:
          Name:
            NameFull: Ruangnapa K
      – PersonEntity:
          Name:
            NameFull: Liaw W
      – PersonEntity:
          Name:
            NameFull: Boedeker P
      – PersonEntity:
          Name:
            NameFull: Kumar S
      – PersonEntity:
          Name:
            NameFull: Rissmiller B
      – PersonEntity:
          Name:
            NameFull: Thammasitboon S
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: 2026 Oct
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1466-187X
          Numbering:
            – Type: volume
              Value: 48
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Medical teacher
              Type: main
ResultId 1