International Journal of Clinical Pharmacy, Journal Year: 2024, Volume and Issue: unknown
Published: Dec. 7, 2024
Language: Английский
Healthcare, Journal Year: 2024, Volume and Issue: 12(2), P. 125 - 125
Published: Jan. 5, 2024
Artificial intelligence (AI) has emerged as a crucial tool in healthcare with the primary aim of improving patient outcomes and optimizing delivery. By harnessing machine learning algorithms, natural language processing, computer vision, AI enables analysis complex medical data. The integration into systems aims to support clinicians, personalize care, enhance population health, all while addressing challenges posed by rising costs limited resources. As subdivision science, focuses on development advanced algorithms capable performing tasks that were once reliant human intelligence. ultimate goal is achieve human-level performance improved efficiency accuracy problem-solving task execution, thereby reducing need for intervention. Various industries, including engineering, media/entertainment, finance, education, have already reaped significant benefits incorporating their operations. Notably, sector witnessed rapid growth utilization technology. Nevertheless, there remains untapped potential truly revolutionize industry. It important note despite concerns about job displacement, should not be viewed threat workers. Instead, are designed augment professionals, freeing up time focus more critical tasks. automating routine repetitive tasks, can alleviate burden allowing them dedicate attention care meaningful interactions. However, legal ethical must addressed when embracing technology medicine, alongside comprehensive public education ensure widespread acceptance.
Language: Английский
Citations
128
Bulletin of the National Research Centre/Bulletin of the National Research Center, Journal Year: 2024, Volume and Issue: 48(1)
Published: Jan. 22, 2024
Abstract Background Tobacco smoking remains a major preventable cause of disease and death worldwide. Combustible cigarettes release thousands chemicals that can initiate inflammatory pathways leading to smoking-related illness. This review aims synthesize current scientific knowledge on mechanisms smoking-induced disease, epidemiological trends, clinical strategies from recent literature. Main body the abstract At cellular level, cigarette smoke triggers oxidative stress through reactive oxygen species (ROS), causing DNA damage. provokes signaling cascades mediated by damage-associated molecular patterns (DAMPs), receptors like RAGE TLRs, downstream cytokines. Smoking also disrupts apoptosis autophagy. In lungs, inflammation play central roles in COPD pathogenesis. Smoking-induced damage, chronic inflammation, impaired immunity combine promote lung carcinogenesis. For cardiovascular endothelial dysfunction, platelet activation, atherogenesis oxidized LDL effects nitric oxide adhesion molecules. Short conclusion Given unequivocal evidence health risks, cessation is critical reducing disability. Both counseling pharmacotherapy have proven efficacy for quitting, but limited long-term. Emerging nicotine products e-cigarettes unknown impacts population health. Comprehensive efforts encompassing prevention, screening, treatment innovation, harm reduction, policy reform focused curbing smoking-attributable morbidity mortality are warranted.
Language: Английский
Citations
29
npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)
Published: Sept. 28, 2024
Abstract With generative artificial intelligence (GenAI), particularly large language models (LLMs), continuing to make inroads in healthcare, assessing LLMs with human evaluations is essential assuring safety and effectiveness. This study reviews existing literature on evaluation methodologies for healthcare across various medical specialties addresses factors such as dimensions, sample types sizes, selection, recruitment of evaluators, frameworks metrics, process, statistical analysis type. Our review 142 studies shows gaps reliability, generalizability, applicability current practices. To overcome significant obstacles LLM developments deployments, we propose QUEST, a comprehensive practical framework covering three phases workflow: Planning, Implementation Adjudication, Scoring Review. QUEST designed five proposed principles: Quality Information, Understanding Reasoning, Expression Style Persona, Safety Harm, Trust Confidence.
Language: Английский
Citations
17
Informatics, Journal Year: 2025, Volume and Issue: 12(1), P. 9 - 9
Published: Jan. 17, 2025
The rapid advancement of large language models like ChatGPT has significantly impacted natural processing, expanding its applications across various fields, including healthcare. However, there remains a significant gap in understanding the consistency and reliability ChatGPT’s performance different medical domains. We conducted this systematic review according to an LLM-assisted PRISMA setup. high-recall search term “ChatGPT” yielded 1101 articles from 2023 onwards. Through dual-phase screening process, initially automated via subsequently manually by human reviewers, 128 studies were included. covered range specialties, focusing on diagnosis, disease management, patient education. assessment metrics varied, but most compared accuracy against evaluations clinicians or reliable references. In several areas, demonstrated high accuracy, underscoring effectiveness. some contexts revealed lower accuracy. mixed outcomes domains emphasize challenges opportunities integrating AI into certain areas suggests that substantial utility, yet inconsistent all indicates need for ongoing evaluation refinement. This highlights potential improve healthcare delivery alongside necessity continued research ensure reliability.
Language: Английский
Citations
1
Frontiers in Medicine, Journal Year: 2025, Volume and Issue: 12
Published: Jan. 23, 2025
Large Language Models (LLMs) are transforming patient education in medication management by providing accessible information to support healthcare decision-making. Building on our recent scoping review of LLMs education, this perspective examines their specific role guidance. These artificial intelligence (AI)-driven tools can generate comprehensive responses about drug interactions, side effects, and emergency care protocols, potentially enhancing autonomy decisions. However, significant challenges exist, including the risk misinformation complexity accurate without access individual data. Safety concerns particularly acute when patients rely solely AI-generated advice for self-medication This analyzes current capabilities, critical limitations, raises questions regarding possible integration We emphasize need regulatory oversight ensure these serve as supplements to, rather than replacements for, professional
Language: Английский
Citations
1
The Journal of Clinical Pharmacology, Journal Year: 2024, Volume and Issue: 64(9), P. 1095 - 1100
Published: April 16, 2024
ChatGPT is a language model that was trained on large dataset including medical literature. Several studies have described the performance of exams. In this study, we examine its in answering factual knowledge questions regarding clinical pharmacy. Questions were obtained from Dutch application features multiple-choice to maintain basic level for pharmacists. total, 264 pharmacy-related presented and responses evaluated accuracy, concordance, quality substantiation, reproducibility. Accuracy defined as correctness answer, results compared overall score by pharmacists over 2022. Responses marked concordant if no contradictions present. The substantiation graded two independent using 4-point scale. Reproducibility established presenting multiple times various days. yielded accurate 79% questions, surpassing pharmacists' accuracy 66%. Concordance 95%, deemed good or excellent 73% questions. consistently high, both within day between days (>92%), well across different users. demonstrated higher reproducibility related pharmacy practice than Consequently, posit could serve valuable resource We hope technology will further improve, which may lead enhanced future performance.
Language: Английский
Citations
8
European Journal of Clinical Pharmacology, Journal Year: 2024, Volume and Issue: 80(8), P. 1133 - 1140
Published: April 9, 2024
Language: Английский
Citations
7
Cureus, Journal Year: 2024, Volume and Issue: unknown
Published: June 4, 2024
Background ChatGPT is a language model that has gained widespread popularity for its fine-tuned conversational abilities. However, known drawback to the artificial intelligence (AI) chatbot tendency confidently present users with inaccurate information. We evaluated quality of responses questions pertaining atrial fibrillation patient education. Our analysis included accuracy and estimated grade level answers whether references were provided answers. Methodology was prompted four times 16 frequently asked on from American Heart Association asked. Prompts Form 1 (no prompt), 2 (patient-friendly 3 (physician-level 4 (prompting statistics/references). Responses scored as incorrect, partially correct, or correct (perfect). Flesch-Kincaid grade-level unique words response lengths recorded Proportions at differing scores compared using chi-square analysis. The relationship between form assessed variance. Results Across all forms, scoring frequencies one (1.6%) five (7.8%) 55 (85.9%) three (4.7%) perfect. least did not differ by (p = 0.350), but perfect 0.001). had lower mean (12.80 ± 3.38) than Forms (14.23 2.34), (16.73 2.65), (14.85 2.76) < 0.05). in only Notably, when additionally sources references, still out (18.8%). Conclusions holds significant potential enhancing education through accurate, adaptive responses. Its ability alter complexity based user input, combined high rates, supports use an informational resource healthcare settings. Future advancements continuous monitoring AI capabilities will be crucial maximizing benefits while mitigating risks associated AI-driven
Language: Английский
Citations
7
Journal of Medicine Surgery and Public Health, Journal Year: 2024, Volume and Issue: 2, P. 100078 - 100078
Published: Feb. 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.
Language: Английский
Citations
5
Exploratory Research in Clinical and Social Pharmacy, Journal Year: 2024, Volume and Issue: 15, P. 100478 - 100478
Published: July 23, 2024
Language: Английский
Citations
4