AI-assisted decision-making in mild traumatic brain injury

<h3>Objective</h3><p dir="ltr">This study evaluates the potential use of ChatGPT in aiding clinical decision-making for patients with mild traumatic brain injury (TBI) by assessing the quality of responses it generates for clinical care.</p><h3>Methods</h3&...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Yavuz Yigit (17788490) (author)
مؤلفون آخرون: Mahmut Firat Kaynak (22282825) (author), Baha Alkahlout (21781963) (author), Shabbir Ahmed (5712863) (author), Serkan Günay (21781960) (author), Asim Enes Ozbek (22282828) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513513505947648
author Yavuz Yigit (17788490)
author2 Mahmut Firat Kaynak (22282825)
Baha Alkahlout (21781963)
Shabbir Ahmed (5712863)
Serkan Günay (21781960)
Asim Enes Ozbek (22282828)
author2_role author
author
author
author
author
author_facet Yavuz Yigit (17788490)
Mahmut Firat Kaynak (22282825)
Baha Alkahlout (21781963)
Shabbir Ahmed (5712863)
Serkan Günay (21781960)
Asim Enes Ozbek (22282828)
author_role author
dc.creator.none.fl_str_mv Yavuz Yigit (17788490)
Mahmut Firat Kaynak (22282825)
Baha Alkahlout (21781963)
Shabbir Ahmed (5712863)
Serkan Günay (21781960)
Asim Enes Ozbek (22282828)
dc.date.none.fl_str_mv 2025-03-12T09:00:00Z
dc.identifier.none.fl_str_mv 10.1186/s12873-024-01159-8
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/AI-assisted_decision-making_in_mild_traumatic_brain_injury/30173491
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
ChatGPT
Traumatic Brain Injury
Emergency Medicine
Artificial Intelligence
Readability
Clinical Decision Support
dc.title.none.fl_str_mv AI-assisted decision-making in mild traumatic brain injury
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <h3>Objective</h3><p dir="ltr">This study evaluates the potential use of ChatGPT in aiding clinical decision-making for patients with mild traumatic brain injury (TBI) by assessing the quality of responses it generates for clinical care.</p><h3>Methods</h3><p dir="ltr">Seventeen mild TBI case scenarios were selected from PubMed Central, and each case was analyzed by GPT-4 (March 21, 2024, version) between April 11 and April 20, 2024. Responses were evaluated by four emergency medicine specialists, who rated the ease of understanding, scientific adequacy, and satisfaction with each response using a 7-point Likert scale. Evaluators were also asked to identify critical errors, defined as mistakes in clinical care or interpretation that could lead to morbidity or mortality. The readability of GPT-4’s responses was also assessed using the Flesch Reading Ease and Flesch-Kincaid Grade Level tools.</p><h3>Results</h3><p dir="ltr">There was no significant difference in the ease of understanding between responses with and without critical errors (<i>p</i>= 0.133). However, responses with critical errors significantly reduced satisfaction and scientific adequacy (<i>p</i>< 0.001). GPT-4 responses were significantly more difficult to read than the case descriptions (<i>p</i>< 0.001).</p><h3>Conclusion</h3><p dir="ltr">GPT-4 demonstrates potential utility in clinical decision-making for mild TBI management, offering scientifically appropriate and comprehensible responses. However, critical errors and readability issues limit its immediate implementation in emergency settings without oversight by experienced medical professionals.</p><h2>Other Information</h2><p dir="ltr">Published in: BMC Emergency Medicine<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1186/s12873-024-01159-8" target="_blank">https://dx.doi.org/10.1186/s12873-024-01159-8</a></p>
eu_rights_str_mv openAccess
id Manara2_31724cbc62c310cfde8b1308b74681ab
identifier_str_mv 10.1186/s12873-024-01159-8
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30173491
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling AI-assisted decision-making in mild traumatic brain injuryYavuz Yigit (17788490)Mahmut Firat Kaynak (22282825)Baha Alkahlout (21781963)Shabbir Ahmed (5712863)Serkan Günay (21781960)Asim Enes Ozbek (22282828)Biomedical and clinical sciencesClinical sciencesHealth sciencesHealth services and systemsInformation and computing sciencesArtificial intelligenceChatGPTTraumatic Brain InjuryEmergency MedicineArtificial IntelligenceReadabilityClinical Decision Support<h3>Objective</h3><p dir="ltr">This study evaluates the potential use of ChatGPT in aiding clinical decision-making for patients with mild traumatic brain injury (TBI) by assessing the quality of responses it generates for clinical care.</p><h3>Methods</h3><p dir="ltr">Seventeen mild TBI case scenarios were selected from PubMed Central, and each case was analyzed by GPT-4 (March 21, 2024, version) between April 11 and April 20, 2024. Responses were evaluated by four emergency medicine specialists, who rated the ease of understanding, scientific adequacy, and satisfaction with each response using a 7-point Likert scale. Evaluators were also asked to identify critical errors, defined as mistakes in clinical care or interpretation that could lead to morbidity or mortality. The readability of GPT-4’s responses was also assessed using the Flesch Reading Ease and Flesch-Kincaid Grade Level tools.</p><h3>Results</h3><p dir="ltr">There was no significant difference in the ease of understanding between responses with and without critical errors (<i>p</i>= 0.133). However, responses with critical errors significantly reduced satisfaction and scientific adequacy (<i>p</i>< 0.001). GPT-4 responses were significantly more difficult to read than the case descriptions (<i>p</i>< 0.001).</p><h3>Conclusion</h3><p dir="ltr">GPT-4 demonstrates potential utility in clinical decision-making for mild TBI management, offering scientifically appropriate and comprehensible responses. However, critical errors and readability issues limit its immediate implementation in emergency settings without oversight by experienced medical professionals.</p><h2>Other Information</h2><p dir="ltr">Published in: BMC Emergency Medicine<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1186/s12873-024-01159-8" target="_blank">https://dx.doi.org/10.1186/s12873-024-01159-8</a></p>2025-03-12T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1186/s12873-024-01159-8https://figshare.com/articles/journal_contribution/AI-assisted_decision-making_in_mild_traumatic_brain_injury/30173491CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/301734912025-03-12T09:00:00Z
spellingShingle AI-assisted decision-making in mild traumatic brain injury
Yavuz Yigit (17788490)
Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
ChatGPT
Traumatic Brain Injury
Emergency Medicine
Artificial Intelligence
Readability
Clinical Decision Support
status_str publishedVersion
title AI-assisted decision-making in mild traumatic brain injury
title_full AI-assisted decision-making in mild traumatic brain injury
title_fullStr AI-assisted decision-making in mild traumatic brain injury
title_full_unstemmed AI-assisted decision-making in mild traumatic brain injury
title_short AI-assisted decision-making in mild traumatic brain injury
title_sort AI-assisted decision-making in mild traumatic brain injury
topic Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
ChatGPT
Traumatic Brain Injury
Emergency Medicine
Artificial Intelligence
Readability
Clinical Decision Support