搜索结果：Expert

Ultrasonography is increasingly the preferred method for infant hip screening to enable timely diagnosis and treatment of developmental dysplasia of the hip (DDH). However, its reliance on experienced specialists and bulky equipment limits its application in routine screening, particularly in resource-limited and remote settings. We aimed to develop an artificial intelligence wireless handheld ultrasound hip diagnostic system (AI-HUDs) for accurate and robust DDH diagnosis. An AI-HUDs was developed to automatically identify and analyze 6 key anatomical landmarks in static and dynamic hip ultrasound images, employing the Graf method to measure α and β angles. The dataset comprised 1192 ultrasound images and 498 dynamic videos. The YOLOv8 model was trained and tested to construct AI-HUDs. Evaluation focused on the consistency between AI-HUDs' automatic angle measurements and manual measurements by experts using traditional ultrasound equipment. Additionally, 104 hip ultrasound videos from 52 infants were acquired by a resident physician using AI-HUDs, while corresponding static images were manually measured by ultrasound experts to assess agreement between novice-operated AI-HUDs and expert manual assessment. Compared with expert manual measurements, the AI-HUDs demonstrated good performance in static mode: the differences in α and β angles exhibited standard deviations of 1.38° and 2.14°, and mean absolute errors (MAEs) of 1.05° and 1.65°, respectively. The intraclass correlation coefficients (ICCs) were 0.82 (α) and 0.64 (β). In dynamic mode, the MAEs increased slightly to 1.18° (α) and 1.86° (β), while the ICCs decreased to 0.77 for α and 0.51 for β. When operated by the resident physician, AI-HUDs maintained good performance with expert manual measurements: MAEs were 1.16° (α) and 1.91° (β); ICCs were 0.69 (α) and 0.61 (β). Bland-Altman analysis showed 96.15% (α) and 95.19% (β) of data points within the limits of agreement. AI-HUDs demonstrated high reliability and accuracy in automatically measuring α and β angles. Resident physicians using this system achieved diagnostic performance comparable to experts. AI-HUDs show promise as a convenient DDH screening tool in resource-scarce regions, potentially facilitating wider adoption of infant hip ultrasound screening.

This study introduces a unified framework combining artificial intelligence (AI)-directed de novo molecular generation with dual-track lead optimization-comprising expert-guided strategies and AI-driven pathways-to discover tyrosinase (TYR) inhibitors for hyperpigmentation disorders. Using a reinforcement learning (RL)-based generative model, the lead compound AI10 was identified. Subsequent optimization followed two parallel routes. The expert-guided approach yielded AI10-m15 as the most potent TYR inhibitor, with notable antipigmentation activity and excellent cellular safety profiles. In contrast, the AI-driven pathway explored broader chemical spaces, generating unconventional chemotypes, exemplified by the potent TYR inhibitor AI10-a2, highlighting AI's capacity to uncover nonintuitive activity cliffs despite greater output variability. Systematic comparison revealed that the AI model offers exploratory diversity, whereas expert-guided optimization provides predictable improvements in activity and developability. In summary, starting from an AI-generated lead and subsequently integrating both expert-guided and AI-driven structural optimization strategies, these findings further underscore that combining AI technologies with experts' medicinal chemistry insights can substantially accelerate the discovery of viable candidate compounds.

The rapid adoption of robotic surgical systems globally has created a critical gap in training, assessment and certification for visceral and gastrointestinal (GI) surgical trainees. This study, led by the European Association for Endoscopic Surgery (EAES), aimed to achieve an international consensus on a structured, platform-agnostic robotic training curriculum for GI surgical trainees. A 106-item Delphi questionnaire was developed with an international committee of surgical experts, trainees, methodologists and patient representatives. It was disseminated to a multidisciplinary panel of 83 GI robotic surgeons, trainees, human factors experts, robotic theatre team members and industry providers. Two Delphi survey rounds were conducted, with a priori consensus standard set at 70% or higher for agreement. A consensus meeting was subsequently held to discuss and finalise the items needed for a robotic training curriculum for GI surgical trainees. Seventy-one (86%) participants from 15 countries completed round 1. A total of 82 items (77%) reached consensus and 32 new items were generated from free-text comments. Seventy of these participants (99%) completed the 56-item round 2 questionnaire, with 36 items (64%) reaching consensus and 5 new items generated. All 143 statements were discussed in the meeting and consensus was reached in the following areas: (i) key knowledge requirements of the bedside assistant and a console surgeon; (ii) training components; (iii) performance assessment and (iv) certification and supervision. International surgical experts, trainees and other key stakeholders reached consensus on the critical components of a platform-agnostic robotic training curriculum for GI surgical trainees. This will help shape the future of robotic surgical education and certification, promote standardised training practices and ultimately benefit patient safety and outcomes.

Social and behavioral sciences are an integral part of predoctoral dental education, given the important role of social and behavioral factors in oral health, dentist-patient communication, the provision of person-centered care, and patients' experience of dental treatment and their treatment outcomes. The most recent curriculum guidelines in this area were published more than 30 years ago. Given the significant advances made in research, theory, and application since then, as well as the evolution of accreditation standards, the aim of this project was to provide updated curriculum guidelines. Twenty-one experts participated in a modified Delphi technique to reach agreement on the definition of "behavioral science" and recommended topics, teaching/assessment methods, and other curricular considerations for effective and contemporary instruction in social and behavioral sciences as applied to dentistry and oral health. There was expert consensus on seven guidelines, which are presented here along with corresponding explanations and lists of topics that should be included in curricula to facilitate alignment with the guidelines. Expert consensus was also found for related prerequisites, instruction and assessment approaches, teaching facilities, and integration with other parts of the predoctoral dental curriculum. These updated curriculum guidelines have the potential to advance dental education and the practice of dentistry by fostering effective holistic care.

The clinical significance and impact of valve strands, also known as Lambl's excrescences, on management in patients with suspected infective endocarditis (IE) remain unclear. The study aimed to assess the impact of the diagnosis of valve strands on the outcomes of patients investigated for suspected IE. We conducted a retrospective study at Lausanne University Hospital (2014-2024) including adult patients with a valve strand identified on cardiac imaging. Episodes were classified as IE or non-IE by a multidisciplinary Endocarditis Team (2018-2024) or by expert clinicians (2014-2017). One-year outcomes included recurrence of bacteremia/candidemia or IE by the same microorganism. Among 305 episodes with valve strands, 101 (33%) were diagnosed as IE by the Endocarditis Team or expert clinicians. Among the 204 episodes without IE, 165 (81%) had bacteremia/candidemia. Valve strands were identified by transthoracic echocardiography in 141 (50%) out of 282 episodes, and by transesophageal echocardiography in 191 (79%) out of 244 episodes. Among the 257 episodes with bacteremia/candidemia, recurrence of bacteremia/candidemia caused by the same microorganism within one year occurred in 7/92 (8%) among those with IE and 11/165 (7%) among those without (P=0.971). Recurrence of IE due to the same microorganism within one year was significantly more frequent among episodes with IE compared to those without (6/92; 7% versus 2/165; 1%; P=0.029). Most valve strands detected in patients with suspected IE do not represent infectious lesions. Careful evaluation by expert cardiologists and multidisciplinary discussion can safely differentiate valve strands from vegetations, reducing unnecessary treatment.

The protein design field is rapidly advancing, with frequent emergence of new models and pipelines for designing de novo proteins with tailored properties and functions not found in nature. However, the current tool landscape is fragmented, tools are hard to install and deploy, and require significant computational expertise to integrate into end-to-end, scalable pipelines. A particular challenge is managing many sequences, structures, and metrics for downstream testing and retrospective analysis of input parameters. To address this need, we introduce Ovo, an open-source de novo protein design ecosystem that consolidates models, workflows, data management, and interactive visualization into a scalable, infrastructure-agnostic platform. Ovo features Nextflow-based workflow orchestration, a storage layer, and both command-line and graphical interfaces that democratize scaffold design, binder design and diversification, and validation workflows. Ovo's novel ProteinQC module computes comprehensive sequence and structure descriptors, contextualizing designs against reference sets. Ovo plugins let the community add new workflows and user interfaces to accelerate adoption of emerging methods and facilitate community-driven benchmarking. Ovo lowers engineering barriers and demystifies the design process, allowing experts and non-technical users to design proteins at scale. With community-driven development, Ovo can accelerate de novo protein design and advance discovery in therapeutics and biotechnology.

Community nurses play a pivotal role in palliative care but face barriers in managing complex symptoms, such as fragmented knowledge and a lack of community-tailored evidence-based guidance, impairing clinical efficiency. The aim of this study was to develop and evaluate a knowledge graph-based question-answering system for symptom management in community palliative care. A three-phase codesign study guided by the Knowledge-to-Action framework was conducted. Phase 1 (Knowledge Creation): A Symptom Management Knowledge Base (Knowledge Product I) was developed through a codesign process involving a multidisciplinary expert panel. This panel adapted a knowledge base created by researchers through systematic evidence synthesis, employing FAME criteria for contextual adaptation. Phase 2 (Action Cycle: Implementation): A semantically structured knowledge graph (Knowledge Product II) was constructed via automated extraction by software developers, followed by manual verification by researchers. Based on this graph, a question-answering system was created and implemented as a WeChat mini-program, resulting in a practical KG-QA system (Knowledge Product III). Phase 3 (Action Cycle: Evaluation): The system's acceptability, usability, and perceived usefulness and ease of use were assessed among experts and community nurses during a two-week evaluation period using the Clinical Nursing Information System Effectiveness Evaluation Scale and the Post-Study System Usability Questionnaire, which is grounded in the Technology Acceptance Model. The knowledge base comprises 225 evidence items for nine symptoms; the knowledge graph integrates ten entity types, 11 relationship categories, 442 entities and 668 relationships, with the system supporting four query interfaces and three search methods. The evaluations demonstrated high perceived usefulness and ease of use, with strong scores for acceptability (102.25 ± 16.21; 110.56 ± 9.90) and usability (2.47 ± 1.98; 2.23 ± 1.93). The question-answering system bridges the evidence-practice gap via a nursing-process paradigm, offering a potentially scalable model that aligns with national policies pending further validation. However, these findings are based on a small‑scale, single‑region, short‑term evaluation relying largely on subjective measures. Future research should explore its long-term clinical outcomes and cross-setting scalability.

To systematically evaluate the accuracy, reliability, and clinical applicability of artificial intelligence and large language models (LLMs) in pediatric orthopedics, comparing their performance against established clinical guidelines and assessing their utility for patient education and clinical decision support. A search of PubMed and ScienceDirect (2020-2025) identified 2624 articles using the keywords 'ChatGPT', 'Gemini', 'Claude' and 'orthopedic pediatrics'. After screening and refinement using Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 guidelines, 15 studies met inclusion criteria. Studies evaluated ChatGPT, Google Gemini, Meta AI, Microsoft Copilot, and Claude across multiple pediatric orthopedic conditions across conditions like developmental dysplasia of the hip, slipped capital femoral epiphysis, and scoliosis. Heterogeneity was assessed using Cochran's Q and I2 statistics, and publication bias was evaluated using funnel plots and Egger's test. LLM accuracy ranged from 44.3 to 93% (pooled: 74.1%), with pooled accuracy of 74.1%. Reproducibility was moderate, with ChatGPT demonstrating a Spearman coefficient of 0.55 for complex queries. Regional expert consensus scores varied significantly (Europe: 80, North America: 65; P = 0.034; Fleiss\kappa = 0.113). Up to 33% of responses to guideline-based questions were rated neutral or inaccurate. Reading complexity was elevated (Flesch-Kincaid grade: 12.7), exceeding the recommended sixth-grade level. Parent surveys indicated 82% trust in artificial intelligence as supplementary tools with professional oversight. Minimal statistical heterogeneity was observed (I2 = 0.00%), though publication bias was detected (Egger's test P = 0.0001). LLMs show potential for education and triage but lack consistency in complex scenarios, elevated reading complexity, and significant regional variability in expert assessments. These tools should be used as educational supplements under professional medical supervision rather than for independent clinical decision-making. Broader clinical application requires domain-specific tuning, standardized evaluation, and readability optimization. Level V- systematic review.

Aerosol therapy is an essential procedure in the treatment of acute and chronic respiratory diseases. Currently, there are no up-to-date guidelines from German-speaking countries on the selection and use of nebulizer systems in patients undergoing high-flow therapy via nasal cannula (HFT) and non-invasive ventilation (NIV). An interdisciplinary panel of experts consisting of pulmonologists and intensive care physicians developed practice-oriented recommendations for aerosol therapy under HFT and NIV. The evidence base was derived from a systematic search of the PubMed database of the US National Library of Medicine up to and including November 2025.Publications on clinical studies, reviews, guideline documents, and technical reports were included. The respective level of evidence of the information was evaluated. The recommendations were agreed upon in a multi-stage process. Aerosol administration under HFT and NIV with a vibrating mesh nebulizer (VMN) achieved better lung deposition compared to the use of a jet nebulizer (JN). A JN is suitable if VMNs are not available, if highly viscous drug solutions are to be nebulized, or if there are budgetary limitations. The choice and application of the nebulizer system should be patient-specific, consistent with the indication, taking into account technical, clinical, and economic requirements. Die Aerosoltherapie ist ein essenzielles Verfahren in der Behandlung akuter und chronischer Atemwegserkrankungen. Derzeit existiert keine aktuelle Leitlinie aus den deutschsprachigen Ländern zur Auswahl und Anwendung von Verneblersystemen bei Patienten unter High-Flow-Therapie via Nasenkanüle (HFT) und nichtinvasiver Beatmung (NIV).Ein interdisziplinäres Expertengremium aus Pneumologen und Intensivmedizinern entwickelte praxisorientierte Empfehlungen zur Aerosoltherapie unter HFT und NIV. Die Evidenzgrundlage bildete eine systematische Recherche in der Datenbank PubMed der US National Library of Medicine bis einschließlich November 2025.Einbezogen wurden Publikationen zu klinischen Studien, Übersichtsarbeiten, Leitliniendokumente und technische Berichte. Der jeweilige Evidenzgrad der Informationen wurde bewertet. Die Empfehlungen wurden in einem Mehrstufenverfahren konsentiert.Die Aerosolapplikation unter HFT und NIV mit einem Vibrating-Mesh-Vernebler (VMN) führt zu einer besseren Lungendeposition im Vergleich zur Verwendung eines Jet Nebulizers (JN). Ein JN ist geeignet, wenn VMN nicht verfügbar sind, hochvisköse Medikamentenlösungen vernebelt werden sollen oder wenn budgetäre Limitationen bestehen.Die Wahl und Anwendung des Verneblersystems sollte patientenindividuell, indikationsbezogen und unter Berücksichtigung technischer, klinischer und ökonomischer Rahmenbedingungen erfolgen.

This study examines organizational racial power dynamics through a case study of the interactions between a Diversity, Equity, and Inclusion (DEI) Committee and the Board of Directors at an organization specializing in health care practitioner training. We explore how power-defined as control over resources by certain individuals while others lack such control-can be utilized constructively or destructively. Understanding the hoarding of power to maintain hierarchies, rather than fostering equitable systems, is crucial for driving proactive organizational change. Employing a case study methodology, we analyze the division of power within an organization and elucidate behaviors that led to the concentration of power, highlighting its detrimental use. We also examine how organizational leadership systematically undermined the DEI Committee's efforts to establish an accountable, transparently governed organization committed to justice, equity, diversity, and inclusion. Our analysis reveals that when existing power structures are threatened, they adapt to defend their dominance, often at the expense of the organization's mission. A failure to integrate DEI principles resulted in the loss of relationships with field experts and inflicted harm on its members, ultimately leading to the organization's collapse. Harm included symptoms of racial stress and trauma in racialized board members. In addition to exposing governance failures, this study illuminates the psychological and racial trauma experienced by affected members, linking structural exclusion to cumulative harm. This analysis is contextualized within current events, where similar patterns of dismantling equity-focused initiatives are observed at national levels. This paper offers a unique and timely perspective on advancing organizational equity, particularly relevant for diversity consultants tasked with analyzing and resolving problematic organizational dynamics. We provide guidelines for distinguishing between appropriate Board governance and detrimental power hoarding, contributing to the broader discourse on fostering equitable organizational practice. Below is a list of our various positionalities and our professional/lived experiences. These inform how we approached the present case study; through an examination of race-based power hoarding. Our various identities and life circumstances strengthened and challenged our understanding of how diversity, equity, and inclusion can be integrated within an organization. Early career co-authors consulted more senior career co-authors and all feedback was welcomed. Each author’s positionality and lived experience was valued and improved our work. The first author, Sonya Faber, PhD, MBA, is an African American scholar residing in Germany, as well as a neuroscientist and pharmaceutical professional, with a specialization in clinical development and a passionate commitment to social justice issues. NiCole T. Buchanan, Ph.D. is a Professor in the Department of Psychology at Michigan State University; her research examines how race, gender, and victimization relate to well-being and how organizations can utilize workplace best practices to reduce bias and create healthy work environments where all employees thrive. Dr. Diana Quinn, a queer mestizo Chicana with a background in Cultural Anthropology and a doctorate in Naturopathic Medicine, positions herself at the intersection of holistic health and social justice. Her extensive experience in integrative mental health care, particularly for marginalized communities, reflects a commitment to Healing Justice and transformative practices that address generational trauma and oppression. Robyn Wong-Lee is a Chinese-Canadian ciswoman and a graduate student at the University of Massachusetts Boston researching anti-Asian racism, Asian-American mental health, and resistance/activism. Daniel Zalewa is a graduate student at The University of New Haven studying Industrial Organizational Psychology with a special interest in work stress and health, particularly revolving around experiences of workplace discrimination and their impact on employee wellbeing. The senior author, Monnica Williams, PhD, is an African American woman living in Canada with expertise in racism, mental health, and anxiety-related conditions; she is a board-certified licensed clinical psychologist, tenured professor at the University of Ottawa, a major urban university, and Canada Research Chair for Mental Health Innovation and Equity. We recognize that our positionalities shape our interpretive lens, and we address this through methodological transparency and documentation of data sources.

In the quest to enhance medical consultation, our study introduces AI4Doctor, a sophisticated large-language model (LLM) tailored for the clinical domain. At the heart of AI4Doctor is an innovative integration strategy that synergizes distilled data extracted from electronic medical records (EMR) with empirical insights gathered from practicing physicians during the supervised fine-tuning. Although existing platforms offer informative responses, they fall short of replicating the nuanced decision-making processes of medical professionals, particularly in complex, integrative diagnostic scenarios. Motivated by the need to create a realistic medical practice environment, we propose that a combination of direct knowledge transfer from seasoned doctors and the strategic use of EMR can augment the abilities of LLM, enabling it to more closely mimic the clinical acumen of healthcare practitioners. To navigate the complexities of merging diverse instructional sources, we employ a curriculum learning approach during the fine-tuning process. Moreover, we advance our model's performance by developing a reward system that incentivizes the alignment of the LLM's outputs with the valuable attributes inherent in both doctors' expertise, including diagnostic priors, risk thresholds, and heuristic saliencies accumulated from practice and EMR data. This is achieved through a novel reinforcement-learning approach. Besides, we introduce a new benchmark involving a comparative evaluation. We utilize a subjective evaluation system wherein experts critically assess the responses from a professional perspective as well. Our research underscores the potential of this hybrid model to serve as a robust tool in medical consultations, bridging the gap between artificial intelligence and real-world clinical practice.

Lens epithelial cells (LECs) have a critical role in nutrient transport, ion balance, and the synthesis of essential molecules required to preserve the lens's transparency. We hypothesize that lens epithelial cell density (LECD) may be correlated with the formation and severity of cataracts. Studying this relationship is limited by current quantification methods. This study aimed to develop an AI-driven model capable of automatically performing epithelial cell (LEC) counts in excised capsules, including density, distribution, and determining factors that affect LECD. We developed an AI-based software that leverages deep learning algorithms to automate the enumeration of LECs from light micrographs of harvested anterior lens capsules. To evaluate the performance and reliability of our AI model, we compared its results against traditional manual cell counting methods. Validation analyses included repeated-measures ANOVA, Bland-Altman analysis, mean absolute percentage error (MAPE), the intraclass correlation coefficient (ICC), and a comparison against inter-observer agreement between two independent expert observers to quantitatively assess agreement between AI-generated cell counts and manual enumeration. Participants were patients with age-related cataracts scheduled for phacoemulsification. Over 43,000 individual cellular targets were analyzed across 20 validation images. The AI-driven software showed excellent agreement with consensus manual counts (98.1% accuracy; MAPE 1.87%, 95% CI 1.27-2.47%; Pearson r = 0.99; ICC 0.994, 95% CI 0.982-0.997), tighter than the agreement between the two expert observers themselves (MAPE 3.74%; ICC 0.972). The AI tool provides a rapid, objective, and repeatable method for LECD analysis.

Background: Deaf individuals who use sign language (SL) as their primary language often encounter communication barriers in everyday service interactions dominated by spoken or written language. These challenges are particularly evident in street-food settings, where ordering requires rapid and precise communication. This study developed and evaluated a visual-first, multimodal web application to support street-food ordering for Deaf users. Methods: The application integrated food images, structured menu selection, SL videos, text, and audio output to facilitate communication with hearing vendors. Development followed an iterative User-Centered Design (UCD) process involving expert review, pilot testing, and final usability evaluation with 60 Deaf participants. Quantitative and qualitative data were collected to assess usability and user experience. Results: Participants reported high levels of agreement regarding accessibility, visual clarity, and comprehension of SL content. Structured menus, realistic food images, concise SL videos, and audio output were perceived as helpful for constructing and communicating orders. However, lower ratings were observed for learnability and button operation. Qualitative findings further identified challenges related to interaction flow, visibility of interactive elements, and interface complexity. Discussion: The findings suggest that visual-first, multimodal interfaces can improve perceived communication efficiency and support more accessible food-ordering interactions for Deaf users. The study highlights the importance of Deaf-informed, culturally grounded design and demonstrates how iterative UCD processes can identify both usability benefits and design trade-offs. These findings provide practical guidance for the development of accessible communication technologies in everyday service contexts. The application is available at: https://supachan.github.io/street_food_ordering/index.html. Visual-first, multimodal ordering tools can enhance functional communication independence for Deaf sign language users in everyday community settings where spoken-language systems dominate.Structured menu selection combined with realistic food imagery, concise SL videos, and audio output may reduce communication barriers and support more efficient order construction compared with unstructured pointing or brief text entry.Integrating accessible audio playback with clear visual system feedback can facilitate interaction between Deaf customers and hearing service providers, supporting participation in routine social and cultural activities.Rehabilitation professionals, assistive technology developers, and service designers should adopt culturally grounded, Deaf-informed design approaches that prioritise visual cognition, sign language communication, and interaction flow, rather than relying solely on text-based accessibility compliance.Community-based evaluation in real-world service contexts remains essential prior to large-scale deployment, particularly to assess learnability, scalability, and the dynamics of bidirectional communication.