Can we rely on artificial intelligence to guide antimicrobial therapy? A systematic literature review.

Many women with endometriosis turn to digital sources for information. Meanwhile, large language models (LLMs) appear capable of offering health advice. This study aimed to evaluate the potential in answering endometriosis-related queries. This comparative study used 150 anonymized endometriosis Q&As from online forums (2021-2023), answered by human specialists. Another 150 responses were generated using an LLM (ChatGPT-4o). Eight expert reviewers, split into two groups, blindly evaluated either the human or artificial intelligence (AI) response for each question. The primary endpoint was whether responses could be correctly identified as human or AI. Secondary endpoints included incorrect information, harm, and suitability for patient communication. Each reviewer group assessed 600 responses; human and AI responses were differentiated significantly (χ2=246.162, p<0.001, slight interrater agreement). Most responses were accurate (84.8%), harmless (87.2%), and patient-suitable (73.8%). There were no significant differences regarding incorrect information (p=0.308), harm likelihood (p=0.944), harm extent (p=0.892), medical consensus alignment (p=0.235), or suitability for patients (p=0.544). This study found that AI was not inferior to human specialists in answering endometriosis-related queries. While reviewers were able to distinguish AI- from human-generated responses significantly, interrater agreement was only slight. No substantial differences were observed in medical content. As AI continues to evolve, patients increasingly turn to it for medical guidance, highlighting the need for greater specialization in endometriosis care. Future research should further investigate the risks, benefits, and patient acceptance of AI in clinical practice.

The aim of this study was to examine the application of artificial intelligence (AI) and generative AI (GAI) in dental education through a comprehensive bibliometric analysis, with the goal of identifying potential future research areas in this field. Data were obtained from the Web of Science and Scopus databases, with no date restrictions. The inclusion criteria encompassed research articles, reviews and proceedings papers focused on the use of AI in dental education. The Bibliometrix R package was used for data analysis. A total of 54 documents were analysed, revealing a significant increase in publications from 2021 to 2024. The Journal of Dental Education was identified as the most prolific source, with the United States leading in terms of contributions. The findings showed a growing interest in AI's potential to transform dental education, with significant contributions from a diverse set of global authors and institutions. Several key themes were identified, including 'large language models', 'chatbots' and 'clinical decision support systems'. The citation analysis highlighted influential papers, including those by Thurzo etal. (2023) and Yüzbaşıoğlu (2021). There is a growing interest in the use of AI and GAI in dental education. However, further research, particularly experimental studies, is essential to fully understand their impact on educational outcomes in dentistry. Key areas for exploration include the application of AI for personalised learning, the integration of chatbots as educational tools to support students, and the use of AI for training and assessing practical skills.

Artificial intelligence (AI) technologies, including machine learning (ML), deep learning, and large language models, are increasingly applied in medical diagnostics. In rhinology, these tools are being evaluated for tasks such as image interpretation, cytology classification, and clinical decision support. To systematically evaluate the application and diagnostic accuracy of AI technologies in rhinology, with a focus on clinical utility and implementation barriers. This review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. Seventeen full-text studies were screened based on predefined eligibility criteria, focusing on AI applications with diagnostic metrics in rhinology. Data on AI type, diagnostic task, performance outcomes, and study quality were extracted and synthesized narratively. Twelve studies met the inclusion criteria. Image-based diagnostic tools using convolutional neural networks demonstrated high accuracy (81%-99%) in nasal polyp detection, cytology classification, and computed tomography (CT) scan interpretation. ML models using patient-reported data achieved accuracies of 74.5%-85.5% for chronic rhinosinusitis prediction. Large language models like ChatGPT and Gemini were evaluated for clinical question answering, with performance exceeding 80% in some domains. Risk of bias was moderate in most primary studies, and none reported clinical integration beyond prototype stages. AI exhibits promising diagnostic accuracy across several applications in rhinology. However, significant challenges persist, including limited validation, methodological heterogeneity, and lack of clinical implementation. Future research should focus on prospective trials, explainability, and regulatory frameworks to ensure safe integration into clinical workflows.

Machine learning and deep learning in clinical practice: Advancing neurodegenerative disease diagnosis with multimodal markers.

The implementation of electronic health records (EHRs) has revolutionized modern clinical practice, increasing efficiency, accessibility, and quality of care. Nevertheless, EHR-related workload has been considered as a significant contributor to healthcare professionals' burnout, a syndrome associated with emotional exhaustion, depersonalization, and reduced personal accomplishment. As modern health system explores technological solutions, artificial intelligence (AI) has gained attention for its potential to facilitate documentation processes and alleviate cognitive burden. This systematic review aims to explore and understand the impact of artificial intelligence on burnout associated with electronic health records among healthcare professionals. A systematic literature review was conducted following the PRISMA 2020 guidelines. Relevant studies published between 2019 and 2025 were retrieved from three electronic databases: PubMed, Scopus, and Web of Science. The search strategy included three main domains: artificial intelligence, electronic health records, and healthcare professional burnout. Eligible included studies are peer-reviewed original research articles that evaluated the impact of AI-based technologies on burnout among healthcare professionals. The screening and selection processes were carried out by following the PRISMA framework. Methodological quality assessment of the included studies was performed using the Joanna Briggs Institute Critical Appraisal Tools. Of the 287 records initially identified, eight studies met the inclusion criteria. The majority of identified studies were conducted in the United States and Canada. The identified interventions were categorized into four domains: ambient artificial intelligence scribes, clinical decision support systems, large language models, and natural language processing tools. Most studies focused on mitigating documentation or inbox-related burdens and reported positive outcomes, including decreased documentation time, enhanced workflow efficiency, and reduced symptoms of burnout among healthcare professionals. Nonetheless, several methodological limitations were observed, including the absence of control groups, small sample sizes, and short follow-up periods, which constrain the generalizability of the findings. The integration of artificial intelligence into electronic health record systems may have potential to alleviate documentation burden and inbox management burden. Although preliminary findings are promising, further methodologically robust research is necessary to evaluate long-term outcomes, assess usability across diverse clinical contexts, and ensure the safe and effective implementation of AI technologies in routine healthcare practice. https://osf.io/pevfj.

This bibliographic study covers Artificial Intelligence (AI)theory and its applications from the healthcare field and in particular from the discipline of pathology. This review includes basics of AI, supervised and unsupervised machine learning (ML), various supervised ML algorithms, and their applications in healthcare and pathology. Digital Pathology with Deep Machine Learning is more advantageous over traditional pathology that is based on ‘physical slide on a physical microscope’. However, various implementation challenges of cost, data quality, multi-center validation, bias, and regulatory approval issues for AI in clinical practice still remain, which are also described in this study.

In today’s rapidly evolving business landscape, Artificial Intelligence (AI), and specifically Large Language Models (LLMs), are redefining how organizations operate, make decisions, and engage with customers. AI-driven technologies have become indispensable, providing businesses with powerful tools to streamline operations, derive actionable insights from vast data, and foster more meaningful customer interactions. For business leaders, scholars, and practitioners alike, understanding the transformative potential of AI isn’t just advantageous—it’s essential to staying competitive in an increasingly data-driven world.This editorial delves into recent scholarly advancements in LLM applications within business contexts, analyzing studies that explore AI’s potential across various domains, from decision support to creative industries. By introducing a structured framework, this editorial highlights key insights and contributions from recent studies, assessing their value to academia and industry. The following comparative analysis sheds light on how these innovations shape our understanding of AI’s role in business while pointing to future research directions.Puyt and Madsen's (2024) study stands out as a foundational exploration of LLM accuracy, assessing ChatGPT-4's ability to recount the history of the SWOT analysis-a vital business strategy tool. Their findings reveal that, while ChatGPT-4 effectively conveys general concepts, it struggles with detailed historical information, often producing inaccuracies or "hallucinations." This gap underscores the need for LLMs to be trained with verified academic data, particularly for strategic business applications that demand precision. This study not only contributes to the literature by proposing methods to evaluate AI accuracy in historical contexts but also highlights the importance of rigorous information vetting in industry settings where reliability is crucial.In contrast, Raikov et al. (2024) explore a hybrid intelligence model that combines LLM capabilities with explainable AI (XAI) principles to enhance human-machine collaboration. Their approach emphasizes cognitive semantics, improving transparency and decision-making efficiency. The hybrid model's real-time adaptability addresses the needs of complex, regulated industries such as finance and healthcare, where trust in AI decisions is paramount. Academically, this study provides a valuable addition to XAI literature by demonstrating how LLMs can bridge the gap between AI autonomy and human oversight, making it a model for future human-AI interactions in complex business environments.Another significant study by Mariotti and colleagues (2024) examines the integration of LLMs with enterprise knowledge graphs to enhance data-driven decision-making. By enabling organizations to leverage knowledge graphs for more accurate and scalable data retrieval, this research provides a robust framework for businesses seeking efficient knowledge management systems. The academic contribution here lies in advancing the dialogue between LLMs and knowledge graphs, emphasizing ethical data handling and quality standards essential for industry applications. For enterprises, the study offers practical solutions to achieve streamlined data management, balancing automation with privacy and security. 2024) take a different approach, investigating LLMs' role in creative industries, specifically within fashion design. They introduce a hybrid intelligence model that supports creative processes, allowing AI to complement rather than replace human ingenuity. While LLMs in this field demonstrate potential in automating repetitive design tasks and enhancing customer personalization, the study reveals limitations in AI's ability to handle spatial and stylistic nuances. This study's academic contribution lies in promoting human-AI co-creation, inspiring further research into AI applications across diverse creative sectors, including media and marketing.Collectively, these studies not only illuminate LLMs' transformative potential in business but also highlight critical ethical and operational considerations. Ensuring accuracy, transparency, and data privacy are vital to responsibly integrating AI into business workflows. Future research should focus on enhancing LLM accuracy, refining hybrid intelligence models, and exploring creative AI applications, all while maintaining ethical standards. As LLMs evolve, interdisciplinary collaborations will be essential to harness their full potential, making AI an ethical, effective, and innovative force in the business world.

Continual learning in medical devices: FDA's action plan and beyond

Introduction: This study details the phased development and implementation of an Artificial Intelligence (AI)-driven nursing summary system designed to reduce nurses’ documentation workload. Methods: Over a 1-year development period beginning in December 2023, we constructed a system that automatically generates nursing care summaries from patient records to support care continuity. The system utilized large language models with prompt tuning techniques and a subjective, objective, assessment, plan (SOAP) format integration. Results: Through three iterations informed by clinical feedback, the system reduced the median summary creation time from 16 to 10 minutes (p < 0.001), representing an approximate 40% reduction. When validating the AI-generated nursing summaries, total scores for the five evaluation items in Versions 0.2 and 0.3 showed no significant difference. Discussion: This system produces comprehensive summaries that consider both nursing care plans and changes in patient condition, simultaneously improving efficiency and enhancing documentation quality. This study demonstrates the importance of iterative development and expert knowledge integration in implementing AI in clinical practice, offering valuable insights for advancing digital healthcare transformation. Conclusion: This study achieved an approximate 40% reduction in nursing record creation time and produced clinically acceptable summary documents through the phased development and implementation of an AI-driven nursing summary system. Keywords: patient discharge summaries, artificial intelligence, nursing, large language models, electronic health records

BACKGROUND Artificial intelligence (AI) and machine learning (ML) models are frequently developed in medical research to optimize patient care, yet they remain rarely utilized in clinical practice. OBJECTIVE The present study aims to understand the disconnect between model development and implementation by surveying physicians of all specialties across the United States. METHODS A HIPAA-compliant survey was emailed to residency coordinators at ACGME-accredited residency programs to distribute among attending physicians and resident physicians affiliated with their institution. Respondents were asked to identify and quantify the extent of their training, specialization, and the type and location of their practice. Physicians were then asked follow-up questions regarding AI in their practice: whether its use is permitted, whether they would use it if made available, primary reasons for using or not using AI, elements that would encourage its use, and ethical concerns. RESULTS Of the 941 physicians who responded to the survey, 384 (40.8%) were attending physicians, and 557 (59.2%) were resident physicians. The majority (81.9%) of physicians indicated they would adopt AI in clinical practice if given the opportunity. The most cited intended uses for AI were risk stratification, image segmentation/image analysis, and disease prognosis. The most common reservation, cited by the 18.1% of physicians who indicated that they would not use AI even if it were clinically accessible, was the potential to replicate human bias. CONCLUSIONS The present study emphasizes that most academic physicians within the United States are open to adopting AI in their clinical practice. For AI to become clinically relevant, however, developers and physicians must work synergistically to design models that are accurate, accessible, and intuitive while thoroughly addressing ethical concerns associated with the implementation of AI into medicine.

Large language models illuminate a progressive pathway to artificial intelligent healthcare assistant

Background Large Language Models (LLMs) are transforming clinical decision-making by offering rapid, context-aware access to evidence-based knowledge. However, their efficacy in pediatric dentistry remains underexplored, especially across multiple LLM platforms.Objective: To comparatively evaluate the clinical quality, readability, and originality of responses generated by nine contemporary LLMs for pediatric dental queries.Material and Methods A cross-sectional study assessed the performance of ChatGPT-3.5, ChatGPT-4o, Gemini 2.0, Gemini 2.5, Claude 3.5 Haiku, Claude 3.7 Sonnet, Grok-3, Grok-3 Mini, and DeepSeek-V3. Twenty pediatric dental questions were posed in one-shot queries to each LLM. Responses were evaluated by ten pediatric dental experts using the Modified Global Quality Scale (MGQS), Flesch Reading Ease Score (FRES), Flesch-Kincaid Grade Level (FKGL), and Turnitin Similarity Index. ANOVA and Cohen’s Kappa were used for statistical analysis.Results ChatGPT-4o demonstrated the highest overall MGQS (4.28 ± 0.24), followed by ChatGPT-3.5 (3.45 ± 0.27). DeepSeek-V3 scored lowest (2.18 ± 0.19). Topic-wise, ChatGPT-4o consistently outperformed others across all subdomains. FRES and FKGL scores indicated moderate readability, with Claude models exhibiting the highest linguistic complexity. Turnitin analysis revealed low-to-moderate similarity across models. Inter-rater agreement was substantial (κ = 0.78).Conclusions Among evaluated LLMs, ChatGPT-4o exhibited superior performance in clinical relevance, coherence, and originality, suggesting its potential utility as an adjunct in pediatric dental decision-making. Nonetheless, variability across models underscores the need for critical appraisal and cautious integration into clinical workflows. Key words:Artificial Intelligence, Clinical decision support, Health Communication, Large language models, Natural Language Processing.

ingInfrastructure-as-Code (IaC) is a systems management practice that involves managing and provisioning computing infrastructure through machine-readable definition files, rather than physical hardware configuration or interactive configuration tools. IaC is an essential contribution to the complete automation of the entire software lifecycle in a Development and Operations (DevOps) context. The deployment and management of software through coded configuration, monitoring, and analysis is the IaC solution. In recent times, artificial intelligence (AI)—including generative AI, machine learning, and related techniques—offers opportunities to improve techniques across the IaC life cycle from IaC code generation to its deployment and runtime analysis. We conducted a comprehensive and systematic literature review for all IaC code development and operations phases, considering IaC as a specific software type that we map to the DevOps model. We present the bibliographic review results and investigate in which phases and how AI can enhance IaC techniques by extracting a framework of phase-specific AI contributions and research challenges, contrasting, in particular, generative AI and machine-learning applications across the phases. Key findings include Large Language Models (LLMs) dominating generation and Machine Learning (ML) dominating analysis activities, also showing that operations phases are less studied than IaC development. This review extends previous literature reviews by covering the full DevOps lifecycle, developing a phase-specific taxonomy of AI techniques for IaC, and aligning a comprehensive analysis of research challenges and directions with those that benefit developers by highlighting current innovations and pointing researchers to future directions.

Artificial intelligence (AI) is increasingly integrated into modern healthcare, with rapidly expanding applications in medical diagnostics, laboratory medicine, rehabilitation, and patient-centered digital health solutions. The aim of this narrative review is to provide a critically curated overview of current clinical applications of AI across the healthcare continuum, from diagnosis to rehabilitation, while highlighting their clinical benefits, limitations, and implementation challenges. A targeted narrative literature search was conducted using major biomedical databases, including PubMed/MEDLINE, Scopus, Web of Science, and Embase, with emphasis on recent and influential studies published primarily over the past decade. Evidence was qualitatively synthesized across key clinical domains, including diagnostic imaging, laboratory diagnostics, rehabilitation technologies, and conversational agents. The reviewed literature indicates that AI systems can achieve diagnostic performance comparable to healthcare professionals in selected, well-defined tasks, particularly within imaging-based specialties such as radiology, mammography, ophthalmology, dermatology, and digital pathology, predominantly under retrospective or controlled study conditions. In laboratory medicine, AI-based tools support workflow optimization, result interpretation, and clinical decision support, while in rehabilitation, AI-enabled systems - including robotics, motion analysis platforms, and large language models - facilitate personalized therapy and functional recovery, albeit with heterogeneous evidence and limited prospective validation. AI-based chatbots demonstrate potential to support patient education, mental health interventions, and communication workflows, particularly as adjuncts to clinician-led care. Despite these advances, challenges related to generalizability, algorithmic bias, ethical implementation, and regulatory oversight persist. Overall, this review underscores that AI should be regarded as a supportive clinical decision-support technology rather than a replacement for healthcare professionals, with future research prioritizing prospective validation, real-world effectiveness, and responsible integration into routine clinical practice.

Cardiovascular disease (CVD) remains the leading cause of morbidity and mortality worldwide. Large language models (LLMs) offer potential solutions for enhancing patient education and supporting clinical decision-making. This study aimed to evaluate LLMs' applications in CVD and explore their current implementation, from prevention to treatment. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, this systematic review assessed LLM applications in CVD. A comprehensive PubMed search identified relevant studies. The review prioritized pragmatic and practical applications of LLMs. Key applications, benefits, and limitations of LLMs in CVD prevention were summarized. Thirty-five observational studies met the eligibility criteria. Of these, 54% addressed primary prevention and risk factor management, while 46% focused on established CVD. Commercial LLMs were evaluated in all but one study, with 91% (32 studies) assessing ChatGPT. The LLM applications were categorized as follows: 72% addressed patient education, 17% clinical decision support, and 11% both. In 68% of studies, the primary objective was to evaluate LLMs' performance in answering frequently asked patient questions, with results indicating accurate, comprehensive, and generally safe responses. However, occasional misinformation and hallucinated references were noted. Additional applications included patient guidance on CVD, first aid, and lifestyle recommendations. Large language models were assessed for medical questions, diagnostic support, and treatment recommendations in clinical decision support. Large language models hold significant potential in CVD prevention and treatment. Evidence supports their potential as an alternative source of information for addressing patients' questions about common CVD. However, further validation is needed for their application in individualized care, from diagnosis to treatment.