American Journal of Otolaryngology, Год журнала: 2024, Номер unknown, С. 104557 - 104557
Опубликована: Дек. 1, 2024
Язык: Английский
European Archives of Oto-Rhino-Laryngology, Год журнала: 2024, Номер 281(11), С. 6123 - 6131
Опубликована: Май 4, 2024
The widespread diffusion of Artificial Intelligence (AI) platforms is revolutionizing how health-related information disseminated, thereby highlighting the need for tools to evaluate quality such information. This study aimed propose and validate Quality Assessment Medical (QAMAI), a tool specifically designed assess health provided by AI platforms.
Язык: Английский
Процитировано
22
Diagnostics, Год журнала: 2024, Номер 14(8), С. 839 - 839
Опубликована: Апрель 18, 2024
In the evolving field of maxillofacial surgery, integrating advanced technologies like Large Language Models (LLMs) into medical practices, especially for trauma triage, presents a promising yet largely unexplored potential. This study aimed to evaluate feasibility using LLMs triaging complex cases by comparing their performance against expertise tertiary referral center.
Язык: Английский
Процитировано
16
European Archives of Oto-Rhino-Laryngology, Год журнала: 2024, Номер 281(5), С. 2547 - 2552
Опубликована: Март 16, 2024
Язык: Английский
Процитировано
11
Otolaryngology, Год журнала: 2024, Номер 171(3), С. 667 - 677
Опубликована: Май 8, 2024
To review the current literature on application, accuracy, and performance of Chatbot Generative Pre-Trained Transformer (ChatGPT) in Otolaryngology-Head Neck Surgery. PubMED, Cochrane Library, Scopus. A comprehensive applications ChatGPT otolaryngology was conducted according to Preferred Reporting Items for Systematic Reviews Meta-analyses statement. provides imperfect patient information or general knowledge related diseases found In clinical practice, despite suboptimal performance, studies reported that model is more accurate providing diagnoses, than suggesting most adequate additional examinations treatments vignettes real cases. has been used as an adjunct tool improve scientific reports (referencing, spelling correction), elaborate study protocols, take student resident exams reporting several levels accuracy. The stability responses throughout repeated questions appeared high but many some hallucination events, particularly references. date, are limited generating disease treatment information, improvement management lack comparison with other large language models main limitation research. Its ability analyze images not yet investigated although upper airway tract ear important step diagnosis common ear, nose, throat conditions. This may help otolaryngologists conceive new further
Язык: Английский
Процитировано
9
Journal of Surgical Research, Год журнала: 2025, Номер 307, С. 129 - 138
Опубликована: Фев. 27, 2025
Язык: Английский
Процитировано
1
European Archives of Oto-Rhino-Laryngology, Год журнала: 2023, Номер 281(4), С. 2105 - 2114
Опубликована: Ноя. 22, 2023
Язык: Английский
Процитировано
21
European Archives of Oto-Rhino-Laryngology, Год журнала: 2024, Номер 281(4), С. 2051 - 2053
Опубликована: Фев. 26, 2024
Otolaryngology stands on the precipice of an era innovation, poised to integrate Artificial Intelligence (AI) and chatbots into its research framework.AI has potential use vast datasets improve precision in diagnosis, early detection diseases, treatment planning, patient monitoring.Machine learning algorithms can analyze vocal nuances beyond human perception, allowing for earlier intervention improved outcomes.Moreover, could revolutionize interaction.In postoperative care or during management chronic otolaryngological disorders, chatbots, such as ChatGPT (OpenAI, San Francisco, USA), facilitate real-time symptom tracking deliver instant advice.This not only enhances compliance but also bridges communication gap outside clinical environment.Furthermore, AI-powered tools sift through literature, propose hypotheses, even predict
Язык: Английский
Процитировано
5
Journal of Medicine Surgery and Public Health, Год журнала: 2024, Номер 2, С. 100078 - 100078
Опубликована: Фев. 27, 2024
The integration of AI-powered ChatGPT in oral and maxillofacial surgery marks a transformative shift healthcare, enhancing diagnostics, treatment planning, patient communication, surgical training. Its rapid analysis vast datasets ensures precise, personalized diagnoses strategies, minimizing risks improving outcomes. facilitates virtual consultations, educates patients, serves as real-time assistant during procedures, while AI-driven simulations refine the skills aspiring surgeons secure environment. Despite challenges like data privacy algorithm validation, ongoing research promises to bolster AI's role surgery. Overall, ChatGPT's incorporation reshapes surgery, promising heightened precision, efficiency, care quality, ultimately revolutionizing practices well-being.
Язык: Английский
Процитировано
5
OTO Open, Год журнала: 2025, Номер 9(1)
Опубликована: Янв. 1, 2025
Abstract Objective This study aims to evaluate the impact of prompt construction on quality artificial intelligence (AI) chatbot responses in context head and neck surgery. Study Design Observational evaluative study. Setting An international collaboration involving 16 researchers from 11 European centers specializing Methods A total 24 questions, divided into clinical scenarios, theoretical patient inquiries, were developed. These questions entered ChatGPT‐4o both with without use a structured format, known as SMART (Seeker, Mission, AI Role, Register, Targeted Question). The AI‐generated evaluated by experienced surgeons using Quality Analysis Medical Artificial Intelligence instrument (QAMAI), which assesses accuracy, clarity, relevance, completeness, source quality, usefulness. Results generated scored significantly higher across all QAMAI dimensions compared those contextualized prompts. Median scores for prompts 27.5 (interquartile range [IQR] 25‐29) versus (IQR 21.8‐25) unstructured ( P < .001). Clinical scenarios inquiries showed most significant improvements, while also benefited, but lesser extent. AI's improved notably prompt, particularly questions. Conclusion suggests that format enhances approach improves completeness information, underscoring importance well‐constructed applications. Further research is warranted explore applicability different medical specialties platforms.
Язык: Английский
Процитировано
0
Otolaryngology, Год журнала: 2025, Номер unknown
Опубликована: Март 19, 2025
Abstract Objective Pediatric otorhinolaryngology (ORL) addresses complex conditions in children, requiring a tailored approach for patients and families. With artificial intelligence (AI) gaining traction medical applications, this study evaluates the quality of information provided by large language models (LLMs) comparison to clinicians, identifying strengths limitations field pediatric ORL. Study Design Comparative blinded study. Setting Controlled research environment using LLMs. Methods Fifty‐four items increasing difficulty, namely 18 theoretical questions, clinical scenarios, patient were posed ChatGPT‐3.5, ‐4.0, ‐4o, Claude‐3, Gemini, Perplexity, Copilot, second‐year resident, an expert The Quality Analysis Medical Artificial Intelligence (QAMAI) tool was used evaluation panel members from Young Otolaryngologists Group Italian Society ORL International Federation Societies. Results LLMs performed comparably specialist standardized with Bing Copilot achieving highest QAMAI scores. However, AI responses lacked transparency citing reliable sources less effective addressing patient‐centered questions. Poor interrater agreement among reviewers highlighted challenges distinguishing human‐generated AI‐generated responses. Rhinology topics received scores, whereas laryngology questions showed lower performance. Conclusion show promise as supportive resources ORL, particularly learning cases. significant remain, including source contextual communication interactions. Human oversight is essential mitigate risks. Future developments should focus on refining capabilities evidence‐based empathetic support both clinicians
Язык: Английский
Процитировано
0