Enhancing AI Chatbot Responses in Healthcare: The SMART Prompt Structure in Head and Neck Surgery DOI Creative Commons
Luigi Angelo Vaira, Jérôme R. Lechien, Vincenzo Abbate

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 23, 2024

Abstract Objective. To evaluate the impact of prompt construction on quality AI chatbot responses in context head and neck surgery. Study design. Observational evaluative study. Setting. 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 inputted ChatGPT-4o both with without use a structured format, known as SMART (Seeker, Mission, Role, Register, Targeted Question). The AI-generated evaluated by experienced surgeons using QAMAI instrument, which assesses accuracy, clarity, relevance, completeness, source quality, usefulness. Results. generated scored significantly higher across all dimensions compared to those contextualized prompts. Median scores for prompts 27.5 (IQR 25–29) versus 21.8–25) unstructured (p < 0.001). Clinical scenarios inquiries showed most significant improvements, while also benefited but lesser extent. AI's improved notably prompt, particularly questions. Conclusions. study suggests that format enhances This approach improves completeness information, underscoring importance well-constructed applications. Further research is warranted explore applicability different medical specialties platforms.

Language: Английский

Advantages and limitations of large language models for antibiotic prescribing and antimicrobial stewardship DOI Creative Commons
Daniele Roberto Giacobbe, Cristina Marelli,

Byomkesh Manna

et al.

npj Antimicrobials and Resistance, Journal Year: 2025, Volume and Issue: 3(1)

Published: Feb. 27, 2025

Antibiotic prescribing requires balancing optimal treatment for patients with reducing antimicrobial resistance. There is a lack of standardization in research on using large language models (LLMs) supporting antibiotic prescribing, necessitating more efforts to identify biases and misinformation their outputs. Educating future medical professionals these aspects crucial ensuring the proper use LLMs providing deeper understanding strengths limitations.

Language: Английский

Citations

1
Enhancing AI Chatbot Responses in Health Care: The SMART Prompt Structure in Head and Neck Surgery DOI Creative Commons
Luigi Angelo Vaira, Jérôme R. Lechien, Vincenzo Abbate

et al.

OTO Open, Journal Year: 2025, Volume and Issue: 9(1)

Published: Jan. 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.

Language: Английский

Citations

0
Comparing Large Language Models for antibiotic prescribing in different clinical scenarios: which perform better? DOI Creative Commons
Andrea De Vito, Nicholas Geremia, Davide Fiore Bavaro

et al.

Clinical Microbiology and Infection, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

Citations

0
The Role of ChatGPT and AI Chatbots in Optimizing Antibiotic Therapy: A Comprehensive Narrative Review DOI Creative Commons

Ninel Iacobus Antonie,

Gina Gheorghe, Vlad Ionescu

et al.

Antibiotics, Journal Year: 2025, Volume and Issue: 14(1), P. 60 - 60

Published: Jan. 9, 2025

Background/Objectives: Antimicrobial resistance represents a growing global health crisis, demanding innovative approaches to improve antibiotic stewardship. Artificial intelligence (AI) chatbots based on large language models have shown potential as tools support clinicians, especially non-specialists, in optimizing therapy. This review aims synthesize current evidence the capabilities, limitations, and future directions for AI enhancing selection patient outcomes. Methods: A narrative was conducted by analyzing studies published last five years across databases such PubMed, SCOPUS, Web of Science, Google Scholar. The focused research discussing AI-based chatbots, stewardship, clinical decision systems. Studies were evaluated methodological soundness significance, findings synthesized narratively. Results: Current highlights ability assist guideline-based recommendations, medical education, enhance decision-making. Promising results include satisfactory accuracy preliminary diagnostic prescriptive tasks. However, challenges inconsistent handling nuances, susceptibility unsafe advice, algorithmic biases, data privacy concerns, limited validation underscore importance human oversight refinement. Conclusions: complement stewardship efforts promoting appropriate use improving Realizing this will require rigorous trials, interdisciplinary collaboration, regulatory clarity, tailored improvements ensure their safe effective integration into practice.

Language: Английский

Citations

0
Performance of ChatGPT-4o in the diagnostic workup of fever among returning travelers requiring hospitalization: a validation study DOI
Dana Yelin,

Neta Shirin,

Ian A. Harris

et al.

Journal of Travel Medicine, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 17, 2025

Febrile illness in returned travelers presents a diagnostic challenge non-endemic settings. Chat generative pretrained transformer (ChatGPT) has the potential to assist medical tasks, yet its performance clinical settings rarely been evaluated. We conducted preliminary validation assessment of ChatGPT-4o's workup fever returning travelers. retrieved records hospitalized with during 2009-2024. The scenarios these cases at time presentation emergency department were prompted ChatGPT-4o, using detailed uniform format. model was further four consistent questions concerning differential diagnosis and recommended workup. To avoid training, we kept blinded final diagnosis. Our primary outcome success rates predicting (gold standard) when requested specify top 3 diagnoses. Secondary outcomes single most likely diagnosis, all necessary diagnostics. also assessed ChatGPT-4o as tool for malaria qualitatively evaluated failures. predicted 68% (95% CI 59-77%), 78% 69-85%), 83% 74-89%) 114 cases, three diagnoses, possible respectively. showed sensitivity 100% 93-100%) specificity 94% 85-98%) malaria. failed provide 18% (20/114) primarily by failing predict globally endemic infections (16/21, 76%). demonstrated high accuracy real-life febrile presenting department, especially Model training is expected yield an improved facilitate decision-making field.

Language: Английский

Citations

0
Assessing the clinical support capabilities of ChatGPT 4o and ChatGPT 4o mini in managing lumbar disc herniation DOI Creative Commons
Suning Wang, Ying Wang, Linlin Jiang

et al.

European journal of medical research, Journal Year: 2025, Volume and Issue: 30(1)

Published: Jan. 22, 2025

Language: Английский

Citations

0
Antibiotics and Artificial Intelligence: Clinical Considerations on a Rapidly Evolving Landscape DOI Creative Commons
Daniele Roberto Giacobbe, Sabrina Guastavino, Cristina Marelli

et al.

Infectious Diseases and Therapy, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 15, 2025

The growing interest in leveraging artificial intelligence (AI) tools for healthcare decision-making extends to improving antibiotic prescribing. Large language models (LLMs), a type of AI trained on extensive datasets from diverse sources, can process and generate contextually relevant text. While their potential enhance patient outcomes is significant, implementing LLM-based support prescribing complex. Here, we specifically expand the discussion this crucial topic by introducing three interconnected perspectives: (1) distinctive commonalities, but also conceptual differences, between use LLMs as assistants scientific writing supporting real-world practice; (2) possibility nuances expertise paradox; (3) peculiarities risk error when considering complex tasks such

Language: Английский

Citations

0
Chain of thought reasoning in enhancing infectious disease diagnosis and microbiological analysis DOI

Alberto Rizzo,

Andrea De Vito,

Riccardo Lucis

et al.

American Journal of Infection Control, Journal Year: 2025, Volume and Issue: 53(3), P. 411 - 412

Published: Feb. 24, 2025

Language: Английский

Citations

0
Response letter: Role of chain-of-thought reasoning in enhancing infectious disease diagnostics DOI
Mahmud Omar, Dana Brin, Benjamin S. Glicksberg

et al.

American Journal of Infection Control, Journal Year: 2025, Volume and Issue: 53(3), P. 412 - 412

Published: Feb. 24, 2025

Language: Английский

Citations

0
Can we rely on artificial intelligence to guide antimicrobial therapy? A systematic literature review DOI Creative Commons
Sulwan Algain, Alexandre R. Marra, Takaaki Kobayashi

et al.

Antimicrobial Stewardship & Healthcare Epidemiology, Journal Year: 2025, Volume and Issue: 5(1)

Published: Jan. 1, 2025

Abstract Background: Artificial intelligence (AI) has the potential to enhance clinical decision-making, including in infectious diseases. By improving antimicrobial resistance prediction and optimizing antibiotic prescriptions, these technologies may support treatment strategies address critical gaps healthcare. This study evaluates effectiveness of AI guiding appropriate prescriptions for diseases through a systematic literature review. Methods: We conducted review studies evaluating (machine learning or large language models) used guidance on prescribing antibiotics disease cases. Searches were performed PubMed, CINAHL, Embase, Scopus, Web Science, Google Scholar articles published up October 25, 2024. Inclusion criteria focused assessing performance practice, with outcomes related management decision-making. Results: Seventeen machine as part decision systems (CDSS). They improved optimized use. Six models guide therapy; they had higher error rates, patient safety risks, needed precise prompts ensure accurate responses. Conclusions: AI, particularly integrated into CDSS, holds promise enhancing decision-making management. However, currently lack reliability required complex applications. The indispensable role specialists remains ensuring accurate, personalized, safe strategies. Rigorous validation regular updates are essential before successful integration practice.

Language: Английский

Citations

0