Enhancing AI Chatbot Responses in Health Care: The SMART Prompt Structure in Head and Neck Surgery

Abstract Objective This study aims to evaluate the impact of prompt construction on the quality of artificial intelligence (AI) chatbot responses in the context of head and neck surgery. Study Design Observational and evaluative study. Setting An international collaboration involving 16 researchers...

Full description

Saved in:
Bibliographic Details
Main Authors: Luigi Angelo Vaira, Jerome R. Lechien, Vincenzo Abbate, Guido Gabriele, Andrea Frosolini, Andrea De Vito, Antonino Maniaci, Miguel Mayo‐Yáñez, Paolo Boscolo‐Rizzo, Alberto Maria Saibene, Fabio Maglitto, Giovanni Salzano, Gianluigi Califano, Stefania Troise, Carlos Miguel Chiesa‐Estomba, Giacomo De Riu
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:OTO Open
Subjects:
Online Access:https://doi.org/10.1002/oto2.70075
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850066643936346112
author Luigi Angelo Vaira
Jerome R. Lechien
Vincenzo Abbate
Guido Gabriele
Andrea Frosolini
Andrea De Vito
Antonino Maniaci
Miguel Mayo‐Yáñez
Paolo Boscolo‐Rizzo
Alberto Maria Saibene
Fabio Maglitto
Giovanni Salzano
Gianluigi Califano
Stefania Troise
Carlos Miguel Chiesa‐Estomba
Giacomo De Riu
author_facet Luigi Angelo Vaira
Jerome R. Lechien
Vincenzo Abbate
Guido Gabriele
Andrea Frosolini
Andrea De Vito
Antonino Maniaci
Miguel Mayo‐Yáñez
Paolo Boscolo‐Rizzo
Alberto Maria Saibene
Fabio Maglitto
Giovanni Salzano
Gianluigi Califano
Stefania Troise
Carlos Miguel Chiesa‐Estomba
Giacomo De Riu
author_sort Luigi Angelo Vaira
collection DOAJ
description Abstract Objective This study aims to evaluate the impact of prompt construction on the quality of artificial intelligence (AI) chatbot responses in the context of head and neck surgery. Study Design Observational and evaluative study. Setting An international collaboration involving 16 researchers from 11 European centers specializing in head and neck surgery. Methods A total of 24 questions, divided into clinical scenarios, theoretical questions, and patient inquiries, were developed. These questions were entered into ChatGPT‐4o both with and without the use of a structured prompt format, known as SMART (Seeker, Mission, AI Role, Register, Targeted Question). The AI‐generated responses were evaluated by experienced head and neck surgeons using the Quality Analysis of Medical Artificial Intelligence instrument (QAMAI), which assesses accuracy, clarity, relevance, completeness, source quality, and usefulness. Results The responses generated using the SMART prompt scored significantly higher across all QAMAI dimensions compared to those without contextualized prompts. Median QAMAI scores for SMART prompts were 27.5 (interquartile range [IQR] 25‐29) versus 24 (IQR 21.8‐25) for unstructured prompts (P < .001). Clinical scenarios and patient inquiries showed the most significant improvements, while theoretical questions also benefited, but to a lesser extent. The AI's source quality improved notably with the SMART prompt, particularly in theoretical questions. Conclusion This study suggests that the structured SMART prompt format significantly enhances the quality of AI chatbot responses in head and neck surgery. This approach improves the accuracy, relevance, and completeness of AI‐generated information, underscoring the importance of well‐constructed prompts in clinical applications. Further research is warranted to explore the applicability of SMART prompts across different medical specialties and AI platforms.
format Article
id doaj-art-7ec48b8ad3a444c8b3768422e1e7908a
institution DOAJ
issn 2473-974X
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series OTO Open
spelling doaj-art-7ec48b8ad3a444c8b3768422e1e7908a2025-08-20T02:48:41ZengWileyOTO Open2473-974X2025-01-0191n/an/a10.1002/oto2.70075Enhancing AI Chatbot Responses in Health Care: The SMART Prompt Structure in Head and Neck SurgeryLuigi Angelo Vaira0Jerome R. Lechien1Vincenzo Abbate2Guido Gabriele3Andrea Frosolini4Andrea De Vito5Antonino Maniaci6Miguel Mayo‐Yáñez7Paolo Boscolo‐Rizzo8Alberto Maria Saibene9Fabio Maglitto10Giovanni Salzano11Gianluigi Califano12Stefania Troise13Carlos Miguel Chiesa‐Estomba14Giacomo De Riu15Maxillofacial Surgery Operative Unit, Department of Medicine, Surgery and Pharmacy University of Sassari Sassari ItalyDepartment of Surgery, Mons School of Medicine, UMONS Research Institute for Health Sciences and Technology University of Mons (UMons) Mons BelgiumHead and Neck Section, Department of Neurosciences, Reproductive and Odontostomatological Science Federico II University of Naples Naples ItalyMaxillofacial Surgery Unit, Department of Medical Biotechnologies University of Siena Siena ItalyMaxillofacial Surgery Unit, Department of Medical Biotechnologies University of Siena Siena ItalyDepartment of Medicine, Surgery and Pharmacy University of Sassari Sassari ItalyDepartment of Medicine and Surgery University of Enna Kore Enna ItalyOtorhinolaryngology, Head and Neck Surgery Department Complexo Hospitalario Universitario A Coruña (CHUAC) A Coruña SpainSection of Otolaryngology, Department of Medical, Surgical and Health Sciences University of Trieste Trieste ItalyOtolaryngology Unit, Department of Health Sciences, Santi Paolo e Carlo Hospital University of Milan Milan ItalyMaxillo‐Facial Surgery Unit University of Bari “Aldo Moro” Bari ItalyHead and Neck Section, Department of Neurosciences, Reproductive and Odontostomatological Science Federico II University of Naples Naples ItalyDepartment of Neurosciences, Reproductive and Odontostomatological Science Federico II University of Naples Naples ItalyHead and Neck Section, Department of Neurosciences, Reproductive and Odontostomatological Science Federico II University of Naples Naples ItalyDepartment of Otorhinolaryngology–Head and Neck Surgery Hospital Universitario Donostia San Sebastian SpainMaxillofacial Surgery Operative Unit, Department of Medicine, Surgery and Pharmacy University of Sassari Sassari ItalyAbstract Objective This study aims to evaluate the impact of prompt construction on the quality of artificial intelligence (AI) chatbot responses in the context of head and neck surgery. Study Design Observational and evaluative study. Setting An international collaboration involving 16 researchers from 11 European centers specializing in head and neck surgery. Methods A total of 24 questions, divided into clinical scenarios, theoretical questions, and patient inquiries, were developed. These questions were entered into ChatGPT‐4o both with and without the use of a structured prompt format, known as SMART (Seeker, Mission, AI Role, Register, Targeted Question). The AI‐generated responses were evaluated by experienced head and neck surgeons using the Quality Analysis of Medical Artificial Intelligence instrument (QAMAI), which assesses accuracy, clarity, relevance, completeness, source quality, and usefulness. Results The responses generated using the SMART prompt scored significantly higher across all QAMAI dimensions compared to those without contextualized prompts. Median QAMAI scores for SMART prompts were 27.5 (interquartile range [IQR] 25‐29) versus 24 (IQR 21.8‐25) for unstructured prompts (P < .001). Clinical scenarios and patient inquiries showed the most significant improvements, while theoretical questions also benefited, but to a lesser extent. The AI's source quality improved notably with the SMART prompt, particularly in theoretical questions. Conclusion This study suggests that the structured SMART prompt format significantly enhances the quality of AI chatbot responses in head and neck surgery. This approach improves the accuracy, relevance, and completeness of AI‐generated information, underscoring the importance of well‐constructed prompts in clinical applications. Further research is warranted to explore the applicability of SMART prompts across different medical specialties and AI platforms.https://doi.org/10.1002/oto2.70075AIartificial intelligenceChatGPTmaxillofacial surgeryotorhinolaryngologyprompt engineering
spellingShingle Luigi Angelo Vaira
Jerome R. Lechien
Vincenzo Abbate
Guido Gabriele
Andrea Frosolini
Andrea De Vito
Antonino Maniaci
Miguel Mayo‐Yáñez
Paolo Boscolo‐Rizzo
Alberto Maria Saibene
Fabio Maglitto
Giovanni Salzano
Gianluigi Califano
Stefania Troise
Carlos Miguel Chiesa‐Estomba
Giacomo De Riu
Enhancing AI Chatbot Responses in Health Care: The SMART Prompt Structure in Head and Neck Surgery
OTO Open
AI
artificial intelligence
ChatGPT
maxillofacial surgery
otorhinolaryngology
prompt engineering
title Enhancing AI Chatbot Responses in Health Care: The SMART Prompt Structure in Head and Neck Surgery
title_full Enhancing AI Chatbot Responses in Health Care: The SMART Prompt Structure in Head and Neck Surgery
title_fullStr Enhancing AI Chatbot Responses in Health Care: The SMART Prompt Structure in Head and Neck Surgery
title_full_unstemmed Enhancing AI Chatbot Responses in Health Care: The SMART Prompt Structure in Head and Neck Surgery
title_short Enhancing AI Chatbot Responses in Health Care: The SMART Prompt Structure in Head and Neck Surgery
title_sort enhancing ai chatbot responses in health care the smart prompt structure in head and neck surgery
topic AI
artificial intelligence
ChatGPT
maxillofacial surgery
otorhinolaryngology
prompt engineering
url https://doi.org/10.1002/oto2.70075
work_keys_str_mv AT luigiangelovaira enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT jeromerlechien enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT vincenzoabbate enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT guidogabriele enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT andreafrosolini enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT andreadevito enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT antoninomaniaci enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT miguelmayoyanez enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT paoloboscolorizzo enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT albertomariasaibene enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT fabiomaglitto enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT giovannisalzano enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT gianluigicalifano enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT stefaniatroise enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT carlosmiguelchiesaestomba enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery
AT giacomoderiu enhancingaichatbotresponsesinhealthcarethesmartpromptstructureinheadandnecksurgery