Assessment of the Reliability and Clinical Applicability of ChatGPT’s Responses to Patients’ Common Queries About Rosacea DOI Creative Commons
Sihan Yan, Dan Du, Xu Liu

et al.

Patient Preference and Adherence, Journal Year: 2024, Volume and Issue: Volume 18, P. 249 - 253

Published: Jan. 1, 2024

Objective: Artificial intelligence chatbot, particularly ChatGPT (Chat Generative Pre-trained Transformer), is capable of analyzing human input and generating human-like responses, which shows its potential application in healthcare. People with rosacea often have questions about alleviating symptoms daily skin-care, suitable for to response. This study aims assess the reliability clinical applicability 3.5 responding patients' common queries evaluate extent ChatGPT's coverage dermatology resources. Methods: Based on a qualitative analysis literature from patients, we extracted 20 greatest concerns, covering four main categories: treatment, triggers diet, skincare, special manifestations rosacea. Each question was inputted into separately three rounds question-and-answer conversations. The generated answers will be evaluated by experienced dermatologists postgraduate degrees over five years experience dermatology, their practice. Results: results indicate that reviewers unanimously agreed achieved high 92.22% 97.78% Additionally, almost all were applicable supporting patient education, ranging 98.61% 100.00%. consistency expert ratings excellent (all significance levels less than 0.05), coefficient 0.404 content 0.456 practicality, indicating significant level agreement among ratings. Conclusion: exhibits artificial tool education. Keywords: intelligence, ChatGPT, rosacea, education

Language: Английский

Benchmarking large language models’ performances for myopia care: a comparative analysis of ChatGPT-3.5, ChatGPT-4.0, and Google Bard DOI
Zhi Wei Lim, Krithi Pushpanathan,

Samantha Min Er Yew

et al.

EBioMedicine, Journal Year: 2023, Volume and Issue: 95, P. 104770 - 104770

Published: Aug. 23, 2023

Language: Английский

Citations

192

A Systematic Review and Meta-Analysis of Artificial Intelligence Tools in Medicine and Healthcare: Applications, Considerations, Limitations, Motivation and Challenges DOI Creative Commons
Hussain A. Younis, Taiseer Abdalla Elfadil Eisa, Maged Nasser

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(1), P. 109 - 109

Published: Jan. 4, 2024

Artificial intelligence (AI) has emerged as a transformative force in various sectors, including medicine and healthcare. Large language models like ChatGPT showcase AI’s potential by generating human-like text through prompts. ChatGPT’s adaptability holds promise for reshaping medical practices, improving patient care, enhancing interactions among healthcare professionals, patients, data. In pandemic management, rapidly disseminates vital information. It serves virtual assistant surgical consultations, aids dental simplifies education, disease diagnosis. A total of 82 papers were categorised into eight major areas, which are G1: treatment medicine, G2: buildings equipment, G3: parts the human body areas disease, G4: G5: citizens, G6: cellular imaging, radiology, pulse images, G7: doctors nurses, G8: tools, devices administration. Balancing role with judgment remains challenge. systematic literature review using PRISMA approach explored healthcare, highlighting versatile applications, limitations, motivation, challenges. conclusion, diverse applications demonstrate its innovation, serving valuable resource students, academics, researchers Additionally, this study guide, assisting field alike.

Language: Английский

Citations

92

Overview of Chatbots with special emphasis on artificial intelligence-enabled ChatGPT in medical science DOI Creative Commons
Chiranjib Chakraborty, Soumen Pal, Manojit Bhattacharya

et al.

Frontiers in Artificial Intelligence, Journal Year: 2023, Volume and Issue: 6

Published: Oct. 31, 2023

The release of ChatGPT has initiated new thinking about AI-based Chatbot and its application drawn huge public attention worldwide. Researchers doctors have started the promise AI-related large language models in medicine during past few months. Here, comprehensive review highlighted overview their current role medicine. Firstly, general idea Chatbots, evolution, architecture, medical use are discussed. Secondly, is discussed with special emphasis medicine, architecture training methods, diagnosis treatment, research ethical issues, a comparison other NLP illustrated. article also limitations prospects ChatGPT. In future, these will immense healthcare. However, more needed this direction.

Language: Английский

Citations

61

Multidisciplinary collaboration: key players in successful implementation of ChatGPT and similar generative artificial intelligence in manufacturing, finance, retail, transportation, and construction industry DOI Open Access
Nitin Liladhar Rane

Published: Oct. 17, 2023

The emergence of generative artificial intelligence (AI), exemplified by ChatGPT, has fundamentally transformed numerous sectors amplifying operational efficiency, output, and customer satisfaction. However, effectively integrating such sophisticated AI systems, especially in manufacturing, finance, retail, transportation, construction, demands concerted efforts from cross-functional teams. This investigation delves into the indispensable role played these teams ensuring seamless integration ChatGPT akin technologies across diverse fields. In research underscores vital significance collaboration between specialists, industrial engineers, production managers to optimize manufacturing processes, preemptive maintenance, quality assurance. finance sector, study highlights essential synergy data scientists, regulatory experts, financial analysts harness ChatGPT's complete potential automating tasks, detecting fraud, providing personalized interactions. For retail industry, this accentuates necessity collaborative marketing strategists, user experience designers, developers utilizing for targeted campaigns, virtual shopping assistants, instantaneous support. It explores how can facilitate assimilation boost engagement, inventory management, predict consumer trends, thereby propelling business growth competitive advantage. transportation imperative planners, software developers, experts leveraging efficient route planning, predictive vehicle real-time logistics oversight. construction importance cohesive among architects, civil programmers project design enhancement, risk mitigation. By promoting collaboration, effective communication, cross-domain expertise, are instrumental harnessing transformative AI, industries toward a more efficient, sustainable, technologically advanced future.

Language: Английский

Citations

47

Generative Pre-Trained Transformer-Empowered Healthcare Conversations: Current Trends, Challenges, and Future Directions in Large Language Model-Enabled Medical Chatbots DOI Creative Commons
James C. L. Chow, Valerie Wong, Kay Li

et al.

BioMedInformatics, Journal Year: 2024, Volume and Issue: 4(1), P. 837 - 852

Published: March 14, 2024

This review explores the transformative integration of artificial intelligence (AI) and healthcare through conversational AI leveraging Natural Language Processing (NLP). Focusing on Large Models (LLMs), this paper navigates various sections, commencing with an overview AI’s significance in role AI. It delves into fundamental NLP techniques, emphasizing their facilitation seamless conversations. Examining evolution LLMs within frameworks, discusses key models used healthcare, exploring advantages implementation challenges. Practical applications conversations, from patient-centric utilities like diagnosis treatment suggestions to provider support systems, are detailed. Ethical legal considerations, including patient privacy, ethical implications, regulatory compliance, addressed. The concludes by spotlighting current challenges, envisaging future trends, highlighting potential reshaping interactions.

Language: Английский

Citations

28

Enhancing User Experience With a Generative AI Chatbot DOI
Jeong Soo Kim, Minseong Kim, Tae Hyun Baek

et al.

International Journal of Human-Computer Interaction, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 13

Published: Feb. 13, 2024

With the rapid evolution of artificial intelligence (AI), this study aims to examine interplay among perceived usability, enjoyment, responsiveness, and intention continue using ChatGPT. Structural equation modeling (SEM) was used investigate our proposed model. We recruited 446 ChatGPT users through an online survey conducted on Connect platform, powered by CloudResearch. Perceived usability (β = 0.254) enjoyment 0.438) significantly influence satisfaction with However, responsiveness is not related attachment or satisfaction. Furthermore, we established that 0.405) 0.447) are pivotal in shaping users' intentions ChatGPT, providing insights into human–AI interactions. The practical implications findings suggest generative AI chatbots should be crafted a focus enjoyable, user-centered interfaces foster long-term user engagement. developers design conversation flows chatbot personas optimize experience.

Language: Английский

Citations

27

The Potential Applications and Challenges of ChatGPT in the Medical Field DOI Creative Commons
Yonglin Mu, Dawei He

International Journal of General Medicine, Journal Year: 2024, Volume and Issue: Volume 17, P. 817 - 826

Published: March 1, 2024

ChatGPT, an AI-driven conversational large language model (LLM), has garnered significant scholarly attention since its inception, owing to manifold applications in the realm of medical science. This study primarily examines merits, limitations, anticipated developments, and practical ChatGPT clinical practice, healthcare, education, research. It underscores necessity for further research development enhance performance deployment. Moreover, future avenues encompass ongoing enhancements standardization mitigating exploring integration applicability translational personalized medicine. Reflecting narrative nature this review, a focused literature search was performed identify relevant publications on ChatGPT's use process aimed at gathering broad spectrum insights provide comprehensive overview current state prospects domain. The objective is aid healthcare professionals understanding groundbreaking advancements associated with latest artificial intelligence tools, while also acknowledging opportunities challenges presented by ChatGPT.

Language: Английский

Citations

25

Google Gemini and Bard artificial intelligence chatbot performance in ophthalmology knowledge assessment DOI
Andrew Mihalache, Justin Grad, Nikhil S. Patil

et al.

Eye, Journal Year: 2024, Volume and Issue: 38(13), P. 2530 - 2535

Published: April 13, 2024

Language: Английский

Citations

25

Potential of Large Language Models in Health Care: Delphi Study DOI Creative Commons
Kerstin Denecke, Richard May, Octavio Rivera-Romero

et al.

Journal of Medical Internet Research, Journal Year: 2024, Volume and Issue: 26, P. e52399 - e52399

Published: April 19, 2024

Background A large language model (LLM) is a machine learning inferred from text data that captures subtle patterns of use in context. Modern LLMs are based on neural network architectures incorporate transformer methods. They allow the to relate words together through attention multiple sequence. have been shown be highly effective for range tasks natural processing (NLP), including classification and information extraction generative applications. Objective The aim this adapted Delphi study was collect researchers’ opinions how might influence health care strengths, weaknesses, opportunities, threats LLM care. Methods We invited researchers fields informatics, nursing medical NLP share their started first round with open questions our framework. In second third round, participants scored these items. Results first, second, rounds had 28, 23, 21 participants, respectively. Almost all (26/28, 93% 1 20/21, 95% 3) were affiliated academic institutions. Agreement reached 103 items related cases, benefits, risks, reliability, adoption aspects, future Participants offered several supporting clinical tasks, documentation research education, agreed LLM-based systems will act as assistants patient education. agreed-upon benefits included increased efficiency handling extraction, improved automation processes, quality services overall outcomes, provision personalized care, accelerated diagnosis treatment interaction between patients professionals. total, 5 risks general identified: cybersecurity breaches, potential misinformation, ethical concerns, likelihood biased decision-making, risk associated inaccurate communication. Overconfidence recognized profession. 6 privacy unregulated cloud compromise security, exposure sensitive data, breaches confidentiality, fraudulent information, vulnerabilities storage communication, inappropriate access or data. Conclusions Future should not only focus testing possibilities NLP-related but also consider workflows models could contribute requirements regarding quality, integration, regulations needed successful implementation practice.

Language: Английский

Citations

22

Assessing Generative Pretrained Transformers (GPT) in Clinical Decision-Making: Comparative Analysis of GPT-3.5 and GPT-4 DOI Creative Commons
Adi Lahat, Κassem Sharif, Narmin Zoabi

et al.

Journal of Medical Internet Research, Journal Year: 2024, Volume and Issue: 26, P. e54571 - e54571

Published: June 27, 2024

Background Artificial intelligence, particularly chatbot systems, is becoming an instrumental tool in health care, aiding clinical decision-making and patient engagement. Objective This study aims to analyze the performance of ChatGPT-3.5 ChatGPT-4 addressing complex ethical dilemmas, illustrate their potential role care while comparing seniors’ residents’ ratings, specific question types. Methods A total 4 specialized physicians formulated 176 real-world questions. 8 senior residents assessed responses from GPT-3.5 GPT-4 on a 1-5 scale across 5 categories: accuracy, relevance, clarity, utility, comprehensiveness. Evaluations were conducted within internal medicine, emergency ethics. Comparisons made globally, between seniors residents, classifications. Results Both GPT models received high mean scores (4.4, SD 0.8 for 4.1, 1.0 GPT-3.5). outperformed all rating dimensions, with consistently higher than both models. Specifically, rated as more beneficial complete (mean 4.6 vs 4.0 respectively; P<.001), similarly 4.1 3.7 3.9 3.5, P<.001). Ethical queries highest ratings models, reflecting consistency accuracy completeness criteria. Distinctions among types significant, emergency, internal, questions (4.2, 1.0; 4.3, 0.8; 4.5, 0.7, GPT-3.5’s beneficial, dimensions. Conclusions ChatGPT’s assist medical issues promising, prospects enhance diagnostics, treatments, While integration into workflows may be valuable, it must complement, not replace, human expertise. Continued research essential ensure safe effective implementation environments.

Language: Английский

Citations

22