Boosting LLM-assisted diagnosis: 10-minute LLM tutorial elevates radiology residents' performance in brain MRI interpretation.

Purpose: To evaluate the impact of a structured tutorial on the use of a large language model (LLM)-based search engine on radiology residents' performance in brain MRI differential diagnosis. Methods: In this study, nine radiology residents determined the three most likely differential diagnoses fo...

Full description

Bibliographic Details
Published in:Neuroradiology Vol. 67; no. 8; pp. 2069 - 2082
Main Authors: Kim, Su Hwan, Schramm, Severin, Wihl, Jonas, Raffler, Philipp, Tahedl, Marlene, Canisius, Julian, Luiken, Ina, Endrös, Lukas, Reischl, Stefan, Marka, Alexander, Walter, Robert, Schillmaier, Mathias, Zimmer, Claus, Wiestler, Benedikt, Hedderich, Dennis Martin
Format: pictorial research tables/charts randomized controlled trial Journal Article
Published: Springer Nature Aug2025
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=188477975&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 188477975
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        00283940
        NYZ
      jtl: Neuroradiology
      issn: 00283940
      maglogo: N
    pubinfo:
      dt: Aug2025
      vid: 67
      iid: 8
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        188477975
        185675488
        188477975
        188477975
        10.1007/s00234-025-03664-4
        188477975
      ppf: 2069
      ppct: 13
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Boosting LLM-assisted diagnosis: 10-minute LLM tutorial elevates radiology residents' performance in brain MRI interpretation.
      aug:
        au:
          Kim, Su Hwan
          Schramm, Severin
          Wihl, Jonas
          Raffler, Philipp
          Tahedl, Marlene
          Canisius, Julian
          Luiken, Ina
          Endrös, Lukas
          Reischl, Stefan
          Marka, Alexander
          Walter, Robert
          Schillmaier, Mathias
          Zimmer, Claus
          Wiestler, Benedikt
          Hedderich, Dennis Martin
        affil: https://ror.org/02kkvpp62 Institute of Diagnostic and Interventional Neuroradiology, Technical University of Munich, Munich, Germany
      sug:
        subj:
          Natural Language Processing Utilization
          Natural Language Processing Education
          Magnetic Resonance Imaging
          Competency Assessment
          Brain
          Radiology Service
          Interns and Residents
          Diagnosis, Computer Assisted
          Web Search Engines Utilization
          Job Performance Evaluation
          Diagnosis, Differential
          Human
          Internet Searching
          Artificial Intelligence
          Reading
          Confidence
          Summated Rating Scaling
          Workflow
          User-Computer Interface
          Chi Square Test
          Kruskal-Wallis Test
          Descriptive Statistics
          Confidence Intervals
          Analysis of Variance
          Questionnaires
          Mann-Whitney U Test
          Male
          Female
          Paired T-Tests
          Data Analysis Software
          Randomized Controlled Trials
          Random Assignment
          Pretest-Posttest Design
          Male
          Female
      ab: Purpose: To evaluate the impact of a structured tutorial on the use of a large language model (LLM)-based search engine on radiology residents' performance in brain MRI differential diagnosis. Methods: In this study, nine radiology residents determined the three most likely differential diagnoses for three sets of ten brain MRI cases with a challenging yet definite diagnosis. Each set was assessed (1) with the support of conventional internet search, (2) using an LLM-based search engine (© Perplexity AI) without prior tutorial, or (3) using the LLM-based search engine after a structured 10-minute tutorial. Reader responses were rated using a binary and numeric scoring system. Reading times and confidence levels (measured on a 5-point Likert scale) were recorded for each case. Search engine logs were examined to quantify user interaction metrics, and to identify hallucinations and misinterpretations in LLM responses. Results: Radiology residents achieved the highest accuracy when employing the LLM-based search engine following the tutorial, indicating the correct diagnosis among the top three differential diagnoses in 62.5% of cases (55/88). This was followed by the LLM-assisted workflow before the tutorial (44.8%; 39/87) and the conventional internet search workflow (32.2%; 28/87). The LLM tutorial led to significantly higher performance (binary scores: p = 0.042, numeric scores: p = 0.016) and confidence (p = 0.006) but resulted in no relevant differences in reading times. Hallucinations were found in 5.1% of LLM queries. Conclusion: Our findings demonstrate the considerable benefits that even low-effort educational interventions on LLMs can provide, highlighting their potential role in radiology training programs.
      pubtype: Academic Journal
      doctype:
        pictorial
        research
        tables/charts
        randomized controlled trial
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N