Artificial intelligence in otorhinolaryngology: current trends and application areas

European Archives of Oto-Rhino-Laryngology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 17, 2025

Abstract Purpose This study aims to perform a bibliometric analysis of scientific research on the use artificial intelligence (AI) in field Otorhinolaryngology (ORL), with specific focus identifying emerging AI trend topics within this discipline. Methods A total 498 articles ORL, published between 1982 and 2024, were retrieved from Web Science database. Various techniques, including keyword factor analysis, applied analyze data. Results The most prolific journal was European Archives Oto-Rhino-Laryngology ( n = 67). USA 200) China 61) productive countries AI-related ORL research. institutions Harvard University / Medical School 71). leading authors Lechien JR. 18) Rameau A. 17). frequently used keywords cochlear implant, head neck cancer, magnetic resonance imaging (MRI), hearing loss, patient education, diagnosis, radiomics, surgery, aids, laryngology ve otitis media. Recent trends otorhinolaryngology reflect dynamic focus, progressing hearing-related technologies such as aids implants earlier years, diagnostic innovations like audiometry, psychoacoustics, narrow band imaging. emphasis has recently shifted toward advanced applications MRI, computed tomography (CT) for conditions chronic rhinosinusitis, laryngology, Additionally, increasing attention been given quality life, prognosis, underscoring holistic approach treatment otorhinolaryngology. Conclusion significantly impacted especially therapeutic planning. With advancements MRI CT-based technologies, proven enhance disease detection management. future suggests promising path improving clinical decision-making, care, healthcare efficiency.

Language: Английский

---

Encouragement vs. liability: How prompt engineering influences ChatGPT-4's radiology exam performance

Clinical Imaging, Journal Year: 2024, Volume and Issue: 115, P. 110276 - 110276

Published: Sept. 6, 2024

Language: Английский

---

Natural language processing in plastic surgery patient consultations

Artificial Intelligence Surgery, Journal Year: 2025, Volume and Issue: 5(1), P. 46 - 52

Published: Jan. 10, 2025

Natural language processing (NLP) is the study of systems that allow machines to understand, interpret, and generate human language. With advent large models (LLMs), non-technical industries can also harness power NLP. This includes healthcare, specifically surgical care plastic surgery. manuscript an introductory review for surgeons understand current state future potential NLP in patient consultations. The integration into surgery consultations transform both documentation communication. These applications include information extraction, chart summarization, ambient transcription, coding, enhancing understanding, translation, a patient-facing chatbot. We discuss progress toward building these highlight their challenges. has personalize care, enhance satisfaction, improve workflows surgeons. Altogether, radically our model consultation one more patient-centered.

Language: Английский

---

Evaluating large language models as patient education tools for inflammatory bowel disease: A comparative study

World Journal of Gastroenterology, Journal Year: 2025, Volume and Issue: 31(6)

Published: Jan. 10, 2025

Inflammatory bowel disease (IBD) is a global health burden that affects millions of individuals worldwide, necessitating extensive patient education. Large language models (LLMs) hold promise for addressing information needs. However, LLM use to deliver accurate and comprehensible IBD-related medical has yet be thoroughly investigated. To assess the utility three LLMs (ChatGPT-4.0, Claude-3-Opus, Gemini-1.5-Pro) as reference point patients with IBD. In this comparative study, two gastroenterology experts generated 15 questions reflected common concerns. These were used evaluate performance LLMs. The answers provided by each model independently assessed using Likert scale focusing on accuracy, comprehensibility, correlation. Simultaneously, invited comprehensibility their answers. Finally, readability assessment was performed. Overall, achieved satisfactory levels completeness when answering questions, although varies. All investigated demonstrated strengths in providing basic such IBD definition well its symptoms diagnostic methods. Nevertheless, dealing more complex advice, medication side effects, dietary adjustments, complication risks, quality inconsistent between Notably, Claude-3-Opus better than other models. have potential educational tools IBD; however, there are discrepancies Further optimization development specialized necessary ensure accuracy safety provided.

Language: Английский

---

Assessment of decision-making with locally run and web-based large language models versus human board recommendations in otorhinolaryngology, head and neck surgery

European Archives of Oto-Rhino-Laryngology, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 10, 2025

Abstract Introduction Tumor boards are a cornerstone of modern cancer treatment. Given their advanced capabilities, the role Large Language Models (LLMs) in generating tumor board decisions for otorhinolaryngology (ORL) head and neck surgery is gaining increasing attention. However, concerns over data protection use confidential patient information web-based LLMs have restricted widespread adoption hindered exploration full potential. In this first study its kind we compared standard human multidisciplinary recommendations (MDT) against LLM (ChatGPT-4o) locally run (Llama 3) addressing concerns. Material methods Twenty-five simulated cases were presented to an MDT composed specialists from otorhinolaryngology, craniomaxillofacial surgery, medical oncology, radiology, radiation pathology. This team provided comprehensive analysis cases. The same input into ChatGPT-4o Llama 3 using structured prompts, concordance between LLMs' MDT’s was assessed. Four members evaluated terms adequacy (using six-point Likert scale) whether could influenced MDT's original recommendations. Results showed 84% (21 out 25 cases) demonstrated 92% (23 with distinguishing curative palliative treatment strategies. 64% (16/25) 60% (15/25) Llama, identified all first-line therapy options considered by MDT, though varying priority. therapies 52% (13/25), while offered homologous strategy 48% (12/25). Additionally, both models proposed at least one as top recommendation 28% (7/25). ratings yielded mean score 4.7 (IQR: 4–6) 4.3 3–5) 3. 17% assessments (33/200), indicated that potentially enhance decisions. Discussion demonstrates capability provide viable therapeutic ORL surgery. 3, operating locally, bypasses many issues shows promise clinical tool support However present, should augment rather than replace decision-making.

Language: Английский

---

Evaluating ChatGPT-4o as a decision support tool in multidisciplinary sarcoma tumor boards: heterogeneous performance across various specialties

Frontiers in Oncology, Journal Year: 2025, Volume and Issue: 14

Published: Jan. 17, 2025

Since the launch of ChatGPT in 2023, large language models have attracted substantial interest to be deployed health care sector. This study evaluates performance ChatGPT-4o as a support tool for decision-making multidisciplinary sarcoma tumor boards. We created five patient cases mimicking real-world scenarios and prompted issue board decisions. These recommendations were independently assessed by panel, consisting an orthopedic surgeon, plastic radiation oncologist, radiologist, pathologist. Assessments graded on Likert scale from 1 (completely disagree) 5 agree) across categories: understanding, therapy/diagnostic recommendation, aftercare summarization, effectiveness. The mean score was 3.76, indicating moderate Surgical specialties received highest score, with 4.48, while diagnostic (radiology/pathology) performed considerably better than oncology specialty, which poorly. provides initial insights into use prompt-engineered decision tools regarding surgical best struggled give valuable advice other tested specialties. Clinicians should understand both advantages limitations this technology effective integration clinical practice.

Language: Английский

---

“Artificial Intelligence - Carrying us into the Future”: A Study of Older Adults’ Perceptions of LLM-Based Chatbots

International Journal of Human-Computer Interaction, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 24

Published: March 24, 2025

Language: Английский

---

Assessing large language models as assistive tools in medical consultations for Kawasaki disease

Frontiers in Artificial Intelligence, Journal Year: 2025, Volume and Issue: 8

Published: March 31, 2025

Kawasaki disease (KD) presents complex clinical challenges in diagnosis, treatment, and long-term management, requiring a comprehensive understanding by both parents healthcare providers. With advancements artificial intelligence (AI), large language models (LLMs) have shown promise supporting medical practice. This study aims to evaluate compare the appropriateness comprehensibility of different LLMs answering clinically relevant questions about KD assess impact prompting strategies. Twenty-five were formulated, incorporating three strategies: No (NO), Parent-friendly (PF), Doctor-level (DL). These input into LLMs: ChatGPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro. Responses evaluated based on appropriateness, educational quality, comprehensibility, cautionary statements, references, potential misinformation, using Information Quality Grade, Global Scale (GQS), Flesch Reading Ease (FRE) score, word count. Significant differences found among terms response accuracy, (p < 0.001). provided highest proportion completely correct responses (51.1%) achieved median GQS score (5.0), outperforming GPT-4o (4.0) (3.0) significantly. FRE (31.5) assessed as comprehensible (80.4%). Prompting strategies significantly affected LLM responses. Sonnet with DL had rate (81.3%), while PF yielded most acceptable (97.3%). Pro showed minimal variation across prompts but excelled (98.7% under prompting). indicates that great providing information KD, their use requires caution due quality inconsistencies misinformation risks. discrepancies existed offered best comprehensibility. is recommended for seeking information. As AI evolves, expanding research refining crucial ensure reliable, high-quality

Language: Английский

---

Harnessing advanced large language models in otolaryngology board examinations: an investigation using python and application programming interfaces

European Archives of Oto-Rhino-Laryngology, Journal Year: 2025, Volume and Issue: unknown

Published: April 25, 2025

Abstract Purpose This study aimed to explore the capabilities of advanced large language models (LLMs), including OpenAI’s GPT-4 variants, Google’s Gemini series, and Anthropic’s Claude in addressing highly specialized otolaryngology board examination questions. Additionally, included a longitudinal assessment GPT-3.5 Turbo, which was evaluated using same set questions one year ago identify changes its performance over time. Methods We utilized question bank comprising 2,576 multiple-choice single-choice from German online education platform tailored for certification preparation. The were submitted 11 different LLMs, models, through Application Programming Interfaces (APIs) Python scripts, facilitating efficient data collection processing. Results GPT-4o demonstrated highest accuracy among all particularly excelling categories such as allergology head neck tumors. While showed competitive performance, they generally lagged behind variants. A comparison Turbo’s revealed significant decline past year. Newer LLMs displayed varied levels, with consistently yielding higher than across models. Conclusion newer show strong potential medical content, observed time underscores necessity continuous evaluation. highlights critical need ongoing optimization API usage improve applications certification.

Language: Английский

---

Applications of Natural Language Processing in Otolaryngology: A Scoping Review

The Laryngoscope, Journal Year: 2025, Volume and Issue: unknown

Published: May 1, 2025

To review the current literature on applications of natural language processing (NLP) within field otolaryngology. MEDLINE, EMBASE, SCOPUS, Cochrane Library, Web Science, and CINAHL. The preferred reporting Items for systematic reviews meta-analyzes extension scoping checklist was followed. Databases were searched from date inception up to Dec 26, 2023. Original articles application language-based models otolaryngology patient care research, regardless publication date, included. studies classified under 2011 Oxford CEBM levels evidence. One-hundred sixty-six papers with a median year 2024 (range 1982, 2024) Sixty-one percent (102/166) used ChatGPT published in 2023 or 2024. Sixty NLP clinical education decision support, 42 education, 14 electronic medical record improvement, 5 triaging, 4 trainee monitoring, 3 telemedicine, 1 translation. For 37 extraction, classification, analysis data, 17 thematic analysis, evaluating scientific reporting, manuscript preparation. role is evolving, passing OHNS board simulations, though its requires improvement. shows potential post-treatment monitoring. effective at extracting data unstructured large sets. There limited research administrative tasks. Guidelines use are critical.

Language: Английский

---