Evidence-based advanced prompt engineeringin nursing research: quality analysisof ChatGPT-generated Boolean search query

Pielegniarstwo XXI wieku / Nursing in the 21st Century, Год журнала: 2025, Номер 24

Опубликована: Март 14, 2025

Aim. This article explores the use of advanced prompt engineering in nursing research, with a focus on ChatGPT-generated Boolean search queries (BSQs). Material and methods. The study compares effectiveness different models ChatGPT: ChatGPT-3.5, ChatGPT-4.0, ChatGPT-4omni, generating high-quality BSQs for PUBMED. prompting methods analysed involved Zero-Shot, Automated Chain-Of-Thought, Emotional Stimuli, Role-play, Mixed-Methods prompting. Results. found that using prompting, achieved highest quality scores, whereas zero-shot is least effective. Significant variability outcomes was observed across authors recommend ChatGPT-4omni as most effective model BSQs. Conclusions. highlights lack standardized scientific complicating large language such ChatGPT underline potential to automate preparation systematic reviews development strategies. While proved valuable terms synonyms, it often struggles produce fully accurate argues latest models, along techniques, tasks. It also calls further research refine standardise research.

Язык: Английский

---

Harnessing Generative Artificial Intelligence for Exercise and Training Prescription: Applications and Implications in Sports and Physical Activity—A Systematic Literature Review

Applied Sciences, Год журнала: 2025, Номер 15(7), С. 3497 - 3497

Опубликована: Март 22, 2025

Regular physical activity plays a critical role in health promotion and athletic performance, necessitating personalized exercise training prescriptions. While traditional methods rely on expert assessments, artificial intelligence (AI), particularly generative AI models such as ChatGPT Google Gemini, has emerged potential tool for enhancing personalization scalability recommendations. However, the applicability, reliability, adaptability of AI-generated prescriptions remain underexplored. A comprehensive search was performed using UnoPerTutto metadatabase, identifying 2891 records. After duplicate removal (1619 records) screening, 61 full-text reports were assessed eligibility, resulting inclusion 10 studies. The studies varied methodology, including qualitative mixed-methods approaches, quasi-experimental designs, randomized controlled trial (RCT). ChatGPT-4, ChatGPT-3.5, Gemini evaluated across different contexts, strength training, rehabilitation, cardiovascular exercise, general fitness programs. Findings indicate that programs generally adhere to established guidelines but often lack specificity, progression, real-time physiological feedback. recommendations found emphasize safety broad making them useful guidance less effective high-performance training. GPT-4 demonstrated superior performance generating structured resistance compared older models, yet limitations individualization contextual adaptation persisted. appraisal METRICS checklist revealed inconsistencies study quality, regarding prompt model transparency, evaluation frameworks. holds promise democratizing access prescriptions, its remains complementary rather than substitutive guidance. Future research should prioritize adaptability, integration with monitoring, improved AI-human collaboration enhance precision effectiveness AI-driven

Язык: Английский

---

Revolutionizing Breast Cancer Detection With Artificial Intelligence (AI) in Radiology and Radiation Oncology: A Systematic Review

Cureus, Год журнала: 2024, Номер unknown

Опубликована: Апрель 4, 2024

The number one cause of cancer in women worldwide is breast cancer. Over the last three decades, use traditional screen-film mammography has increased, but recent years, digital and 3D tomosynthesis have become standard procedures for screening. With advancement technology, interpretation images using automated algorithms a subject interest. Initially, computer-aided detection (CAD) was introduced; however, it did not show any long-term benefit clinical practice. advances artificial intelligence (AI) methods, these technologies are showing promising potential more accurate efficient treatment. While AI promises widespread integration treatment, challenges such as data quality, regulatory, ethical implications, algorithm validation crucial. Addressing essential fully realizing AI's enhancing early diagnosis improving patient outcomes management. In this review article, we aim to provide an overview latest developments applications screening existing literature primarily consists retrospective studies, ongoing future prospective research poised offer deeper insights. Artificial on verge into holding enhance improve outcomes.

Язык: Английский

---

Enhancing risk management in hospitals: leveraging artificial intelligence for improved outcomes

Italian Journal of Medicine, Год журнала: 2024, Номер 18(2)

Опубликована: Апрель 15, 2024

In hospital settings, effective risk management is critical to ensuring patient safety, regulatory compliance, and operational effectiveness. Conventional approaches assessment mitigation frequently rely on manual procedures retroactive analysis, which might not be sufficient recognize respond new risks as they arise. This study examines how artificial intelligence (AI) technologies can improve in healthcare facilities, fortifying safety precautions guidelines while improving the standard of care overall. Hospitals proactively identify mitigate risks, optimize resource allocation, clinical outcomes by utilizing AI-driven predictive analytics, natural language processing, machine learning algorithms. The different applications AI are discussed this paper, along with opportunities, problems, suggestions for their use settings.

Язык: Английский

---

Qualitative metrics from the biomedical literature for evaluating large language models in clinical decision-making: a narrative review

BMC Medical Informatics and Decision Making, Год журнала: 2024, Номер 24(1)

Опубликована: Ноя. 26, 2024

The large language models (LLMs), most notably ChatGPT, released since November 30, 2022, have prompted shifting attention to their use in medicine, particularly for supporting clinical decision-making. However, there is little consensus the medical community on how LLM performance contexts should be evaluated. We performed a literature review of PubMed identify publications between December 1, and April 2024, that discussed assessments LLM-generated diagnoses or treatment plans. selected 108 relevant articles from analysis. frequently used LLMs were GPT-3.5, GPT-4, Bard, LLaMa/Alpaca-based models, Bing Chat. five criteria scoring outputs "accuracy", "completeness", "appropriateness", "insight", "consistency". defining high-quality been consistently by researchers over past 1.5 years. identified high degree variation studies reported findings assessed performance. Standardized reporting qualitative evaluation metrics assess quality can developed facilitate research healthcare.

Язык: Английский

---

The Performance of OpenAI ChatGPT-4 and Google Gemini in Virology Multiple-Choice Questions: A Comparative Analysis of English and Arabic Responses

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Апрель 12, 2024

Background: The integration of artificial intelligence (AI) in healthcare education is inevitable. Understanding the proficiency generative AI different languages to answer complex questions crucial for educational purposes. Objective: To compare performance ChatGPT-4 and Gemini answering Virology multiple-choice (MCQs) English Arabic, while assessing quality generated content. Methods: Both models’ responses 40 MCQs were assessed correctness based on CLEAR tool designed evaluation AI-generated classified into lower higher cognitive categories revised Bloom’s taxonomy. study design considered METRICS checklist reporting AI-based studies healthcare. Results: performed better compared with consistently surpassing scores. led 80% vs. 62.5% 65% 55% Arabic. For both models, superior domains was reported. Conclusion: Both exhibited potential applications; nevertheless, their varied across highlighting importance continued development ensure effective globally.

Язык: Английский

---

Evolution of Research Reporting Standards: Adapting to the Influence of Artificial Intelligence, Statistics Software, and Writing Tools

Journal of Korean Medical Science, Год журнала: 2024, Номер 39(32)

Опубликована: Янв. 1, 2024

Reporting standards are essential to health research as they improve accuracy and transparency. Over time, significant changes have occurred the requirements for reporting ensure comprehensive transparent across a range of study domains foster methodological rigor. The establishment Declaration Helsinki, Consolidated Standards Trials (CONSORT), Strengthening Observational Studies in Epidemiology (STROBE), Preferred Items Systematic Reviews Meta-Analysis (PRISMA) just few historic initiatives that increased Through enhanced discoverability, statistical analysis facilitation, article quality enhancement, language barrier reduction, artificial intelligence (AI)-in particular, large models like ChatGPT-has transformed academic writing. However, problems with errors could occur need transparency while utilizing AI tools still exist. Modifying rules include AI-driven writing such ChatGPT is ethically practically challenging. In writing, precautions truth, privacy, responsibility necessary due concerns about biases, openness, data limits, potential legal ramifications. CONSORT-AI Standard Protocol Items: Recommendations Interventional (SPIRIT)-AI Steering Group expands CONSORT guidelines clinical trials-new checklists METRICS CLEAR help promote studies. Responsible usage technology software adoption requires interdisciplinary collaboration ethical assessment. This explores impact technologies, specifically ChatGPT, on past revised open, reproducible, robust scientific publications.

Язык: Английский

---

Mapping the Landscape of Electronic Health Records and Health Information Exchange Through Bibliometric Analysis and Visualization

Cureus, Год журнала: 2024, Номер unknown

Опубликована: Апрель 27, 2024

The adoption of Electronic Health Records (EHRs) and the establishment Information Exchange (HIE) systems have significantly transformed healthcare delivery management. This study presents a comprehensive bibliometric analysis visualization landscape surrounding EHRs HIE to provide insights into current state emerging trends in this field. Leveraging advanced methodologies, including co-citation analysis, keyword co-occurrence network techniques, we systematically map scholarly literature spanning several decades. Our reveals key thematic clusters, influential publications, prolific authors, collaborative networks within domain HIE. Furthermore, identify significant research gaps areas for future exploration, interoperability challenges, privacy concerns, integration technologies such as artificial intelligence blockchain. findings offer valuable researchers, policymakers, practitioners seeking navigate contribute ongoing evolution systems, ultimately enhancing quality, efficiency, accessibility services.

Язык: Английский

---

Enhancing Musculoskeletal Injection Safety: Evaluating Checklists Generated by Artificial Intelligence and Revising the Preformed Checklist

Cureus, Год журнала: 2024, Номер unknown

Опубликована: Май 5, 2024

Background Musculoskeletal disorders are a significant global health issue, necessitating advanced management strategies such as intra-articular and extra-articular injections to alleviate pain, inflammation, mobility challenges. As the adoption of these interventions by physicians grows, importance robust safety protocols becomes paramount. This study evaluates effectiveness conversational artificial intelligence (AI), particularly versions 3.5 4 Chat Generative Pre-trained Transformer (ChatGPT), in creating patient checklists for managing musculoskeletal enhance preparation documentation. Methodology A quantitative analysis was conducted evaluate AI-generated against preformed checklist adapted from reputable medical sources. Adherence generated calculated classified. The Wilcoxon signed-rank test used assess performance differences between ChatGPT 4. Results ChatGPT-4 showed superior adherence compared ChatGPT-3.5, with both classified very good protocol creation. Although no were present sign-in sign-out parts versions, had significantly higher scores procedure planning part (p = 0.007), its overall also < 0.001). Subsequently, revised incorporate new contributions ChatGPT. Conclusions ChatGPT, especially version 4, proved effective generating injections, highlighting potential AI streamline clinical practices. Further enhancements necessary fully meet standards.

Язык: Английский

---

A New Approach: Generative Artificial Intelligence in Physiatry Resident Education

Medical Records, Год журнала: 2024, Номер 7(1), С. 120 - 128

Опубликована: Дек. 4, 2024

Aim: This study assessed the effectiveness of ChatGPT-4o, an artificial intelligence (AI) platform, in creating a therapeutic exercises presentation for physiatry residents’ education. The aim was to compare quality content created by ChatGPT-4o with that expert, exploring potential AI healthcare Material and Method: Both expert 24 PowerPoint slides across six topics, using same reputable sources. Two other experts these according CLEAR criteria: completeness, lack false information, appropriateness, relevance scored as excellent, 5; very good=4, good=3, satisfactory/fair=2, or poor, 1. Results: Interrater reliability confirmed. Average scores (calculated from two raters’ scores) each topic were significantly lower than although whole did not differ between two. Overall average all items) good excellent AI, expert. overall score Highest ranks individual criteria information Some AI-generated elements later integrated into work, enhancing content. Conclusion: can generate effective educational content, though outperforms it, highlighting need professional oversight. Collaboration humans may further enhance outcomes.

Язык: Английский

---