International Journal of Clinical Pharmacy, Journal Year: 2024, Volume and Issue: unknown
Published: Dec. 7, 2024
Language: Английский
BMJ Quality & Safety, Journal Year: 2024, Volume and Issue: unknown, P. bmjqs - 017476
Published: Oct. 1, 2024
Background Search engines often serve as a primary resource for patients to obtain drug information. However, the search engine market is rapidly changing due introduction of artificial intelligence (AI)-powered chatbots. The consequences medication safety when interact with chatbots remain largely unexplored. Objective To explore quality and potential concerns answers provided by an AI-powered chatbot integrated within engine. Methodology Bing copilot was queried on 10 frequently asked patient questions regarding 50 most prescribed drugs in US outpatient market. Patient covered indications, mechanisms action, instructions use, adverse reactions contraindications. Readability assessed using Flesch Reading Ease Score. Completeness accuracy were evaluated based corresponding information pharmaceutical encyclopaedia drugs.com. On preselected subset inaccurate answers, healthcare professionals likelihood extent possible harm if follow chatbot’s given recommendations. Results Of 500 generated overall readability implied that responses difficult read according Overall median completeness 100.0% (IQR 50.0–100.0%) 88.1–100.0%), respectively. 20 experts found 66% (95% CI 50% 85%) be potentially harmful. 42% 25% 60%) these cause moderate mild harm, 22% 10% 40%) severe or even death advice. Conclusions are capable providing complete accurate Yet, deemed considerable number incorrect Furthermore, complexity may limit understanding. Hence, should cautious recommending until more precise reliable alternatives available.
Language: Английский
Citations
4
Current Medical Issues, Journal Year: 2025, Volume and Issue: 23(1), P. 53 - 60
Published: Jan. 1, 2025
Abstract Artificial intelligence (AI) is a milestone technological advancement that enables computers and machines to simulate human problem-solving capabilities. This article serves give broad overview of the application AI in medicine including current applications future. shows promise changing field medical practice although its practical implications are still their infancy need further exploration. However, not without limitations this also tries address them along with suggesting solutions by which can advance healthcare for betterment mass benefit.
Language: Английский
Citations
0
npj Antimicrobials and Resistance, Journal Year: 2025, Volume and Issue: 3(1)
Published: Feb. 21, 2025
Abstract Antimicrobial resistance (AMR) is an emerging threat to global public health. Specifically, Acinetobacter baumannii ( A. ), one of the main pathogens driving rise nosocomial infections, a Gram-negative bacillus that displays intrinsic mechanisms and can also develop by acquiring AMR genes from other bacteria. More importantly, it resistant nearly 90% standard care (SOC) antimicrobial treatments, resulting in unsatisfactory clinical outcomes high infection-associated mortality rate over 30%. Currently, there growing challenge sustainably novel antimicrobials this ever-expanding arms race against AMR. Therefore, sustainable workflow properly manages healthcare resources ultra-rapidly design optimal drug combinations for effective treatment needed. In study, IDentif.AI-AMR platform was harnessed pinpoint regimens four isolates pool nine US FDA-approved drugs. Notably, IDentif.AI-pinpointed ampicillin-sulbactam/cefiderocol cefiderocol/polymyxin B/rifampicin were able achieve 93.89 ± 5.95% 92.23 11.89% inhibition bacteria, respectively, they may diversify reservoir options indication. addition, polymyxin B combination with rifampicin exhibited broadly applicable efficacy strong synergy across all tested isolates, representing potential strategy . potentially serve as alternative strategies
Language: Английский
Citations
0
Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown
Published: March 15, 2025
Language: Английский
Citations
0
Integrated Pharmacy Research and Practice, Journal Year: 2025, Volume and Issue: Volume 14, P. 31 - 43
Published: March 1, 2025
Artificial Intelligence (AI), especially ChatGPT, is rapidly assimilating into healthcare, providing significant advantages in pharmacy practice, such as improved clinical decision-making, patient counselling, and drug information management. The adoption of AI tools heavily contingent upon practitioners' knowledge, attitudes, practices (KAP). This study sought to evaluate the knowledge pharmacists Saudi Arabia concerning utilization ChatGPT their daily activities. A cross-sectional was performed from May 2023 July 2024 including Riyadh, Arabia. An online pre-validated KAP questionnaire disseminated, collecting data on demographics, about ChatGPT. Descriptive statistics regression analyses were conducted using SPSS. Of 1022 respondents, 78.7% familiar with pharmacy, while 90.1% correctly identified an advanced chatbot. Positive attitudes towards reported by 64.1% pharmacists, although only 24.3% used regularly. Significant predictors positive included academic/research roles (β=0.7, p=0.005) 6-10 years experience (β=0.9, p=0.05). Ethical concerns raised 64% 92% a lack formal training. While majority held toward practical implementation remains limited due ethical inadequate Addressing these barriers essential for successful integration supporting Arabia's Vision 2030 initiative.
Language: Английский
Citations
0
npj Digital Medicine, Journal Year: 2025, Volume and Issue: 8(1)
Published: March 28, 2025
Abstract Medication-related harm has a significant impact on global healthcare costs and patient outcomes. Generative artificial intelligence (GenAI) large language models (LLM) have emerged as promising tool in mitigating risks of medication-related harm. This review evaluates the scope effectiveness GenAI LLM reducing We screened 4 databases for literature published from 1st January 2012 to 15th October 2024. A total 3988 articles were identified, 30 met criteria inclusion into final review. AI LLMs applied three key applications: drug-drug interaction identification prediction, clinical decision support, pharmacovigilance. While performance utility these varied, they generally showed promise early identification, classification adverse drug events, supporting decision-making medication management. However, no studies tested prospectively, suggesting need further investigation integration real-world application.
Language: Английский
Citations
0
IGI Global eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 415 - 434
Published: March 28, 2025
Indian Sign Language (ISL) is the dominant language used by deaf and dumb community in India. According to a report WHO, there are around 63 million people across India who suffering from hearing impairments. With having large population percentage occurrence of impairments being high, need for spoken ISL translation systems improve communication between communities. The current work done this domain promising but quite restricted due lack dictionary words resources. Our proposal takes on different approach than existing translation. purpose research create system that translates Hindi into through Neural Machine Translation (NMT). Using rule-based approach, corpus created which follows all grammar conventions ISL. This dataset then train an NMT model can be deployed further
Language: Английский
Citations
0
JACCP JOURNAL OF THE AMERICAN COLLEGE OF CLINICAL PHARMACY, Journal Year: 2025, Volume and Issue: unknown
Published: April 22, 2025
Abstract Introduction The expanding use of Chat Generative Pre‐Trained Transformer (ChatGPT, OpenAI, San Francisco, CA) for drug information may enhance access to information. However, it is crucial assess the accuracy and reproducibility ChatGPT responses questions, examining its utility limitations in clinical decision‐making. Objective To evaluate ChatGPT‐3.5 ChatGPT‐4 responding clinician questions compared with a commonly accepted resource, Lexicomp®(Wolters Kluwer Health, Philadelphia, PA). Methods A serial cross‐sectional study was conducted on from March 5 12, 2024 United States. free, artificial intelligence (AI) chatbot trained up January 2022; paid‐subscription AI internet more data. For trial 1 (day 0) we input 30 real‐world (10 categories) into both ChatGPT‐4. 2 1) 3 7), 10 randomly selected were re‐input ChatGPT. primary outcome evaluated versus (vs.) Lexicomp® using 4‐point Likert scale. Secondary outcomes included assessing vs. Lexicomp, comparing versions' responses, over time. Cohen's Kappa Cochran's Q assessed reproducibility. Results demonstrated 30% (9/30), while had 40% (12/30) ( p = 0.51). Neither versions accurately answered all any category. ChatGPT‐3.5's agreement between trials 2, 3, fair k 0.21), moderate (k 0.41), substantial 0.62), respectively. 0.23), 0.80), (0.40). across three 30%, 20%, 10% 0.78), 60%, 40%, 50% 0.82). Conclusions Both limited answering suggesting that health care professionals should exercise caution when
Language: Английский
Citations
0
Frontiers in Education, Journal Year: 2025, Volume and Issue: 10
Published: May 1, 2025
Background In the recent generative artificial intelligence (genAI) era, health sciences students (HSSs) are expected to face challenges regarding their future roles in healthcare. This multinational cross-sectional study aimed confirm validity of novel FAME scale examining themes Fear, Anxiety, Mistrust, and Ethical issues about genAI. The also explored extent apprehension among HSSs genAI integration into careers. Methods was based on a self-administered online questionnaire distributed using convenience sampling. survey instrument scale, while toward assessed through modified State-Trait Anxiety Inventory (STAI). Exploratory confirmatory factor analyses were used construct scale. Results final sample comprised 587 mostly from Jordan (31.3%), Egypt (17.9%), Iraq (17.2%), Kuwait (14.7%), Saudi Arabia (13.5%). Participants included studying medicine (35.8%), pharmacy (34.2%), nursing (10.7%), dentistry (9.5%), medical laboratory (6.3%), rehabilitation (3.4%). Factor analysis confirmed reliability Of constructs, Mistrust scored highest, followed by Ethics. participants showed generally neutral genAI, with mean score 9.23 ± 3.60. multivariate analysis, significant variations observed previous ChatGPT use, faculty, nationality, expressing highest level apprehension, Kuwaiti lowest. Previous use correlated lower levels. higher agreement Ethics constructs statistically associations apprehension. Conclusion revealed notable Arab HSSs, which highlights need for educational curricula that blend technological proficiency ethical awareness. Educational strategies tailored discipline culture needed ensure job security competitiveness an AI-driven future.
Language: Английский
Citations
0
Published: Jan. 26, 2025
Language: Английский
Citations
0