AI 安全与对齐 · 全部实体（第 34 / 100 页）

本页收录第 3301–3400 条，共 10000 条 · 返回 AI 安全与对齐 首页

• Bioresorbable Scaffolds for Coronary Revascularization: From Concept to Clinical Maturity.
  Over the past decades, coronary revascularization has evolved dramatically with the introduction of bioresorbable scaffolds (BRSs), designed to provide temporary vessel support, elute antiproliferative drugs, and then fully resorb, ideally restoring natural va…
  pubmed Bourazana A, Briasoulis A, Kourek C, Kuno T 等 2025 Dec 19 置信度 0.82
• Cancer Screening and Prevention in MENA and Mediterranean Populations: A Multi-Level Analysis of Barriers, Knowledge Gaps, and Interventions Across Indigenous and Diaspora Communities.
  Cancer is one of the biggest health burdens for women in the Middle East and North Africa (MENA), with the incidence of breast, cervical and colorectal cancer on the rise. Although preventive measures such as the HPV vaccination and population-based screening …
  pubmed Gozum S, Nimri OF, Merzah MA, Vitorino R 2025 Dec 28 置信度 0.82
• Automated Facial Pain Assessment Using Dual-Attention CNN with Clinically Calibrated High-Reliability and Reproducibility Framework.
  Accurate and quantitative pain assessment remains a major challenge in clinical medicine, especially for patients unable to verbalize discomfort. Conventional methods based on self-reports or clinician observation are subjective and inconsistent. This study in…
  pubmed Sankoh AP, Raza A, Parwez K, Shishah W 等 2026 Jan 8 置信度 0.82
• Decoding Gender in Cough Sounds: A Transformer-Based Analysis.
  Various components of speech, such as pitch, volume, and resonance, influence gender perception, but little is known about gender differences in non-speech upper airway sounds such as cough. This gap has implications for gender-affirming voice care, as coughs …
  pubmed He L, Li H, Wang S, Baik E 等 2026 Jun 置信度 0.82
• Specification Limit Normalization for Nonparametric Process Capability Analysis and Its Application in Cleaning Validation with AI-Enabled Monitoring Models.
  In pharmaceutical manufacturing, equipment is often used for multiple products following a single standard cleaning process regardless of the previously manufactured product. Despite this, residue levels are frequently non-detectable. Regulatory guidelines, su…
  pubmed Yang X, Lou W, Chan M 2026 Jan 26 置信度 0.82
• Intelligent generation of product bionic image forms via multimodal emotion-weighted quantification.
  To address key limitations in traditional bionic image design, including the lack of quantitative analysis of user preferences and the poor controllability of AI-driven picture generation, which often leads to homogeneous outputs with limited emotional resonan…
  pubmed Chen X, Lin L, Yang M, Wu X 等 2026 Jan 26 置信度 0.82
• Fake News Has a New Author, Can You Spot the Lie? Media Cues and the Detection of AI-Generated Health News Through the Lens of the Media Evocation Paradigm.
  As generative artificial intelligence (GAI) increasingly contributes to the creation of news content, its ability to produce authoritative yet fabricated information raises pressing concerns for public trust and misinformation detection. Guided by the media ev…
  pubmed Xie Z, Li BBJ 2026 Jan 26 置信度 0.82
• Mitigating loss of lean muscle in GLP-1 and dual GLP-1/GIP agonists: Pipeline opportunities and limitations.
  Glucagon-like peptide-1 (GLP-1) receptor and dual GLP-1/glucose-dependent insulinotropic polypeptide (GIP) agonists drive significant transformation in the landscape for type 2 diabetes and obesity management, yet 15-40% of weight loss in trials like STEP and …
  pubmed Hierholzer J, Benson H, Ewida HA, Ahmed MS 2026 Apr 置信度 0.82
• Use of Generative AI by Veterinary Students in Two UK Vet Schools: A Moment in Time.
  The higher education community is currently experiencing a significant sense of disruption due to the emergence of Generative AI (GenAI) tools. This study sought to establish baseline data that encompass usage rates, confidence, concerns, and opinions on align…
  pubmed Rhind S, Connelly L, Baillie S, Shaw DJ 等 2026 Jan 22 置信度 0.82
• Developing Collaborative Artificial Intelligence in Artistic Practices: Using AI in Creative Explorations.
  This article describes the design and implementation of a course that evaluated the applicability of an artistic studio model, to educating students on the subject of artificial intelligence (AI). Specifically, four sections of an asynchronous, studio-style un…
  pubmed Campbell BD, Santos BS, Magana AJ, Bidarra R 2026 Jan-Feb 置信度 0.82
• Anti-orthopoxvirus drugs inhibit lumpy skin disease virus replication by targeting viral DNA polymerase.
  Lumpy skin disease (LSD) is an emerging transboundary disease caused by lumpy skin disease virus (LSDV), posing significant threats to global cattle health in the absence of validated drugs. Here, we constructed a recombinant LSDV (rLSDV) expressing both mCher…
  pubmed Gong Z, Dai J, Qu H, Hu Y 等 2026 Jan 置信度 0.82
• Comprehensive Pediatric Health Risk Stratification Using an AI-Driven Framework in Children Aged 2 to 8 Years: Design and Validation Study.
  Early life health risks can shape long-term morbidity trajectories, yet prevailing pediatric risk assessment paradigms are often fragmented and insufficiently capable of integrating heterogeneous data streams into actionable, individualized profiles.
  pubmed Mao Z, Chen J 2026 Jan 26 置信度 0.82
• Reliability of Gemini 2.5 Pro, ChatGPT 4.1, DeepSeek V3, and Claude Opus 4 in generating standardized CMR protocols.
  Artificial intelligence (AI) and large language models (LLMs) are increasingly integrated into radiology, offering new possibilities for advanced imaging techniques, including cardiovascular magnetic resonance (CMR). This proof-of-concept study assessed four h…
  pubmed Licu RA, Muscogiuri G, Casartelli D, Bacârea A 等 2026 Jan 26 置信度 0.82
• Leveraging artificial intelligence for decision-making in pediatric progressive and refractory solid tumors.
  Pediatric patients with progressive and refractory solid tumors face a challenging prognosis. Despite advancements in treatments like immunotherapy and targeted therapy, survival rates remain low for certain tumor types. Decision-making in these complex cases …
  pubmed Mordechai O, Meir I, Blanche E, Ben-Arush M 2026 Apr-May 置信度 0.82
• Early prediction of diabetic retinopathy using a multimodal deep learning framework integrating fundus and OCT imaging.
  Diabetic Retinopathy (DR) remains a leading cause of preventable vision impairment among individuals with diabetes, particularly when not identified in its early stages. Conventional diagnostic techniques typically employ either fundus photography or Optical C…
  pubmed Emara AM, Alkhateeb JH, Atteia G, Turani A 等 2025 置信度 0.82
• CRUSADE project: Recycling technologies for ELV components to create a sustainable source of market grade materials for EU applications.
  The European Union's ambitions for climate neutrality and digital leadership rely on secure access to CRMs, essential for green and digital technologies but supply risks and geopolitical challenges. The CRUSADE project develops a sustainable, integrated recycl…
  pubmed Yakoumis I, Moschovi AM, Thoda O, Katsiapi A 等 2026 置信度 0.82
• Human and large language model judgments of cognitive impairment from language: An explainable artificial intelligence approach.
  We examine how non-expert humans (young adults unfamiliar with dementia) and large language models (LLMs) perceive dementia in transcribed texts-recognizing signs that may indicate cognitive decline. Human perception is important, as it is often the driver for…
  pubmed Zadok M, Peled-Cohen L, Calderon N, Gonen H 等 2026 Jan-Mar 置信度 0.82
• Beyond black-box AI: Interpretable hybrid systems for dementia care.
  Foundation models (FMs) are entering Alzheimer's disease and related dementias (ADRD), yet bedside impact remains limited. We analyze the interpretability and reliability gaps that impede adoption, including opaque inference, hallucinations in generative model…
  pubmed Kang MJY, Yang W, Roberts MR, Kang BH 等 2026 Jan-Mar 置信度 0.82
• Generative AI for developing foundation models in radiology and imaging: engineering perspectives.
  Recent advances in generative artificial intelligence (AI) have accelerated the development of foundation models-large-scale, pre-trained systems capable of learning across modalities and tasks with minimal supervision. In the radiology domain, where annotated…
  pubmed Lee JG, Kyung S, Kim N 2026 Jan 置信度 0.82
• An improved YOLOv8n with multi-scale feature fusion for real time and high precision railway track defect detection.
  Railway transportation is increasingly critical for modern urban and intercity mobility. However, the expanding scale and intensifying operational intensity of rail networks have elevated track defect detection to a key concern. Traditional inspection methods …
  pubmed Zhang Z, Zhang L, Lu X, Ma T 等 2025 置信度 0.82
• Exploring the impact of ICT interaction on students' creative thinking across performance levels: an explainable AI perspective.
  This study uses the PISA 2022 ICT questionnaire to examine how students' ICT interaction behaviours in digital environments predict creative thinking across low, medium, and high performance levels (Class 0-2). Using multi-class classification models with Shap…
  pubmed Cai X, Bi Y, Feng Y 2025 置信度 0.82
• Effect of Different Bone Graft Materials on Buccal Wall Dimensions During Socket Preservation: A 3D Retrospective Pilot Study.
  Introduction Socket preservation is a fundamental procedure in dental implantology aimed at minimizing post-extraction alveolar ridge resorption. Buccal wall integrity plays a crucial role in implant stability and esthetic outcomes. However, limited research h…
  pubmed Jaber M, El Jalkh R, Khairallah CM, Saleh A 等 2025 Dec 置信度 0.82
• Presenting the Inner Triangle Outer Diamond (ITOD) Framework of Educational Ecosystems and Its Applications to the Integration of Educational Technologies and Innovations.
  Educators are leveraging technologies and innovations, including artificial intelligence (AI), to support learners and deliver quality medical education. Many of these initiatives have reportedly yielded positive impacts. There have also been publications and …
  pubmed Owolabi J 2025 Dec 置信度 0.82
• An artificial intelligence-driven platform for practice question generation.
  High-stakes licensing exams such as the United States Medical Licensing Examination (USMLE) play a critical role in medical education, influencing both trainee progression and patient outcomes. Access to high-quality board preparation resources is uneven and o…
  pubmed Zahn A, Overla S, Lowrie DJ, Zhou CY 等 2026 Mar 1 置信度 0.82
• SynPoC: a high-quality generative diffusion model for transforming ultra-low-field point-of-care MRI using high-field MRI representations.
  Ultra-low-field (ULF) point-of-care (PoC) Magnetic Resonance Imaging (MRI) offers a promising pathway to improve accessibility in medical imaging due to its portability and lower cost. However, the diagnostic utility of ULF MRI is currently limited by lower im…
  pubmed Islam KT, Dayarathna S, Zhong S, Zakavi P 等 2026 Jan 24 置信度 0.82
• Electric Vehicle Batteries Recycling: A Review.
  The rapid growth of electric vehicles has created an urgent need for practical end-of-life lithium-ion battery recycling systems that are technically competent, economically viable, and environmentally sustainable. To clarify these growing technical and system…
  pubmed Esmaeilian B, Xiao Y, Goyal GK, Zuo L 等 2026 Feb 1 置信度 0.82
• Integrative machine learning approach for identifying genes associated with quantitative traits: A soybean (Glycine max) yield case study.
  To improve the identification of minor-effect molecular markers and genes associated with quantitative traits, addressing inefficiencies in traditional molecular marker mining and the limited impact of these markers in practical breeding, we analyzed over 15,0…
  pubmed Zhou W, Ouyang H, Yan Z, Song J 等 2026 Mar 置信度 0.82
• From predefined indicators to a management dashboard for heart failure telemonitoring: a modified nominal group technique approach in Portuguese hospitals.
  BACKGROUND: Clinical, operational, and financial data drive healthcare decisions, but deriving insights from complex datasets is challenging and error-prone. Dashboards simplify analytics, yet adoption is constrained by skepticism about generic solutions desig…
  pubmed Miranda R, Rodrigues DF, Matos Baptista F, Oliveira MD 2026 Jan 23 置信度 0.82
• Spatial heterogeneity and subtypes of functional connectivity development in youth.
  Brain age prediction has been widely utilized to assess functional connectivity (FC) development, but conventional global brain age indices are limited in capturing spatial heterogeneity across the cortex. This study introduces a regional brain development ind…
  pubmed Li H, Cui Z, Cieslak M, Salo T 等 2026 Jan 23 置信度 0.82
• Two axes of white matter development.
  Despite decades of neuroimaging research, how white matter develops along the length of major tracts in humans remains unknown. Here, we identify fundamental patterns of white matter maturation by examining developmental variation along major, long-range corti…
  pubmed Luo AC, Meisler SL, Sydnor VJ, Alexander-Bloch A 等 2026 Jan 23 置信度 0.82
• IPATH: A Large-Scale Pathology Image-Text Dataset from Instagram for Vision-Language Model Training.
  Recent advancements in artificial intelligence (AI) have revealed important patterns in pathology images imperceptible to human observers that can improve diagnostic accuracy and decision support systems. However, progress has been limited due to the lack of p…
  pubmed Mirhosseini S, Rai T, Diaz-Santana P, La Ragione R 等 2026 Jan 23 置信度 0.82
• From Evidence-based Endodontics to Generative AI: A Comparative Study of 11 Large Language Models.
  Generative large language models (LLMs) are increasingly used in dentistry, yet their guideline-based diagnostic accuracy and reproducibility remain uncertain. Position statements from the American Association of Endodontists and the European Society of Endodo…
  pubmed de Araújo LP, Moreno LB, de Araújo BCC, Chaves ET 等 2026 Jun 置信度 0.82
• Evolving Trends and Emerging Frontiers in Clear Aligner Therapy: A Bibliometric and Social Impact Analysis (2015-2024).
  Clear aligner therapy (CAT) serves as an innovative alternative to traditional fixed appliances, gaining rapid clinical adoption in recent years due to its superior aesthetics, treatment efficiency, patient comfort, and ease of use, which has driven explosive …
  pubmed Wu J, Zhang J, Yu X, Jia Y 等 2026 Apr 置信度 0.82
• Data Poisoning Vulnerabilities Across Health Care Artificial Intelligence Architectures: Analytical Security Framework and Defense Strategies.
  Health care artificial intelligence (AI) systems are increasingly integrated into clinical workflows, yet remain vulnerable to data-poisoning attacks. A small number of manipulated training samples can compromise AI models used for diagnosis, documentation, an…
  pubmed Abtahi F, Seoane F, Pau I, Vega-Barbas M 2026 Jan 23 置信度 0.82
• FluoroSAM: A Language-promptable Foundation Model for Flexible X-ray Image Segmentation.
  Language promptable X-ray image segmentation would enable greater flexibility for human-in-the-loop workflows in diagnostic and interventional precision medicine. Prior efforts have contributed task-specific models capable of solving problems within a narrow s…
  pubmed Killeen BD, Wang LJ, Iñígo B, Zhang H 等 2026 置信度 0.82
• Exploring the Neurotherapeutic Potential of Bacillus-derived Macrolactins as NMDAR Antagonists for Alzheimer's Disease: Network Pharmacology and Molecular Modeling Insights.
  The N-methyl-D-aspartate receptor (NMDAR) plays a critical role in regulating excitatory glutamatergic neurotransmission and synaptic plasticity. However, excessive NMDAR activation can lead to increased calcium ion influx, resulting in excitotoxicity- a key c…
  pubmed Rajendran R, Elangovan E 2026 置信度 0.82
• Explainable artificial intelligence for sedimentary facies segmentation.
  Recent advances in artificial intelligence are transforming geosciences, with growing attention on explainable models to support both scientific research and practical adoption. Here, we present a general yet tailored pipeline for semantic segmentation of sedi…
  pubmed Di Martino A, Carlini G, Amorosi A 2026 Jan 22 置信度 0.82
• Evaluating single-cell ATAC-seq atlasing technologies using sequence-to-function modeling.
  Deciphering the cis-regulatory logic underlying cell type identity remains a key challenge in biology. Single-cell chromatin accessibility (scATAC-seq) atlases enable training of sequence-to-function (S2F) deep learning models to decode enhancer logic. Yet, op…
  pubmed Dickmänken H, Wojno M, Mahieu L, Theunis K 等 2026 Jan 22 置信度 0.82
• CoDrug: A Text-Driven Molecular Virtual Screening and Multiproperty Optimization Framework via Multimodal Language Model.
  Traditional molecular screening methods are often limited by high computational cost, long design cycles, and a strong reliance on high-quality 3D protein structures, which are not always available or reliable. To address these limitations, we propose CoDrug, …
  pubmed Gu R, Liu Y, Zhu B, Liang L 等 2026 Feb 9 置信度 0.82
• EEG-to-gait decoding via phase-aware representation learning.
  Accurate decoding of lower-limb motion from EEG signals is essential for advancing brain-computer interface (BCI) applications in movement intent recognition and control. This study presents NeuroDyGait, a two-stage, phase-aware EEG-to-gait decoding framework …
  pubmed Fu X, Jiang W, Liu R, Müller-Putz GR 等 2026 Jun 置信度 0.82
• Clinician preferences for explainable AI in critical care: a comparative study of interpretable models and visualizations for intubation decision support.
  The complexity of many AI models hinders their clinical adoption because the clinicians using them do not regard them as transparent. This study addresses the lack of clinician-centered explainable AI (XAI) interfaces by designing and evaluating intuitive visu…
  pubmed Xian T, Mehandjiev N, Constantinides P, Chen YW 等 2026 Apr 15 置信度 0.82
• Functional impact assessment of tissue-specific missense variants in the PTPRH gene using a multi-tool computational framework.
  Cancer is driven by genetic alterations that disrupt cellular processes, and one key gene involved in this progression is Protein Tyrosine Phosphatase Receptor Type H (PTPRH). Acting as both a tumor suppressor and oncogene, the role of PTPRH varies across canc…
  pubmed Naseem AA, Khan R, Hameed U 2026 Apr 置信度 0.82
• Explainable depth-wise and channel-wise fusion models for multi-class skin lesion classification.
  The clinical adoption of deep learning in dermatology requires models that are not only highly accurate but also transparent and trustworthy. To address this dual challenge, this study presents a systematic investigation into deep feature fusion, exploring how…
  pubmed AbuAlkebash H, Saleh RAA, Ertunç HM 2026 置信度 0.82
• Awareness, trust, and expectations of AI for glaucoma care among Bulgarian ophthalmologists: Role of demographic factors.
  Artificial intelligence (AI) holds promise for enhancing glaucoma screening and management, yet its adoption depends on clinician perceptions, particularly in resource-limited regions like Eastern Europe. This study explores awareness, trust, and expectations …
  pubmed Radeva MN, Hristova E, Georgiev RT, Zlatarova ZI 2026 Jan 置信度 0.82
• Drug stewardship for RAS inhibitors and SGLT2 inhibitors in chronic kidney disease: stay on, restart.
  Renin-angiotensin system inhibitors (RASis) and sodium-glucose co-transporter 2 inhibitors (SGLT2is) are the cornerstones of management for patients with chronic kidney disease (CKD). The use of these treatments is limited by frequent discontinuations, increas…
  pubmed Bouwmans P, Clase CM, Carrero JJ 2026 Jun 30 置信度 0.82
• Exploring T. cruzi IMPDH as a promising target through Chagas Box screening and AVN-944 inhibition.
  Chagas disease, caused by Trypanosoma cruzi , remains a leading cause of heart failure in Latin America, with current treatments limited to acute-phase efficacy, significant toxicity, and emerging resistance. Inosine monophosphate dehydrogenase (IMPDH) is an e…
  pubmed Lobo-Rojas A, Marchese L, Eufrasio AG, Souza GTD 等 2026 Mar 4 置信度 0.82
• Tracing strategic divergence: archetypal and counterfactual analysis of StarCraft II gameplay trajectories.
  To address the challenges of data heterogeneity, strategic diversity, and process opacity in interpreting multi-agent decision-making within complex competitive environments, we have developed TRACE, an end-to-end analytical framework for StarCraft II gameplay…
  pubmed Zhang J, Yang W 2025 置信度 0.82
• Machine learning for predicting clinical outcomes of hospitalised children: a systematic review of applications in low- and middle-income countries.
  Machine Learning (ML) can contribute to reducing child mortality and morbidity in low- and middle-income countries (LMICs), yet its development and clinical adoption remain unclear. This systematic review provides an overview of ML for hospitalised children in…
  pubmed Nkhono W, van Lieshout E, Calis J, Naanyu V 等 2026 Jan 置信度 0.82
• Training a Bilingual Artificial Intelligence Model on Pediatric Orthopaedic Resources to Enhance the Readability of Patient Education Materials.
  Low health literacy affects nearly one-third of adults in the United States, and almost 68 million Americans speak a language other than English at home. These barriers to understanding medical information are associated with worse clinical outcomes, higher re…
  pubmed Mauffrey O, Lashani S, Mitchell SL 2026 Feb 置信度 0.82
• Combining thermography and artificial intelligence in comparison with a diabetic foot nurse for diabetic foot ulcer detection: A diagnostic accuracy study.
  Early detection of diabetic foot complications is essential to prevent ulcers and amputations. Thermographic imaging offers a non-invasive method for identifying risk, but clinical interpretation has traditionally relied on human thermographers. Artificial int…
  pubmed Shara K, Alghali M, Abu-Ashour W, Almnaizel AT 等 2026 Jan-Dec 置信度 0.82
• Large language models for neurology: a mini review.
  Large language models have the potential to transform neurology by augmenting diagnostic reasoning, streamlining documentation, and improving workflow efficiency. This Mini Review surveys emerging applications of large language models in Alzheimer's disease, P…
  pubmed Wunsch Iii DC, Hier DB 2025 置信度 0.82
• Artificial intelligence in emergency department triage: perspective of human professionals.
  The triage process in emergency departments (EDs) is complex, and AI-based solutions have begun to target it. At this pivotal stage, the challenge lies less in designing smarter algorithms than in fostering trust and alignment among medical and technical stake…
  pubmed Petrica A, Marza AM, Barsac C, Cebzan A 等 2025 置信度 0.82
• Prevention and early intervention screening for inherited ocular diseases in Saudi Arabia: a national perspective.
  Consanguineous marriages are common, particularly in Saudi Arabia, where approximately half of all marriages are consanguineous. The likelihood of autosomal recessive (AR) genetic abnormalities, especially rare diseases (RDs) that present long-term health issu…
  pubmed AlEissa MM, Abedalthagafi M, Edward DP 2025 置信度 0.82
• Multidisciplinary artificial intelligence systems versus single-model approaches for the diagnosis and management of ileus and volvulus.
  The accurate and timely diagnosis of ileus versus volvulus is essential in emergency care, as treatment choices directly influence patient outcomes. In this study, the diagnostic accuracy and adherence to guidelines of multidisciplinary AI systems were compare…
  pubmed Ucdal M, Yurtsever K, Ekingen E 2026 Jan 21 置信度 0.82
• [China National Lung Cancer Screening Guideline with Low-dose Computed Tomography (2025 Version)].
  Lung cancer remains the leading cause of cancer-related deaths in China. Optimizing lung cancer screening strategies to improve screening efficiency and mitigate associated harms has become a key research focus and priority in current clinical practice. The pu…
  pubmed Chinese Expert Group on Early Diagnosis and Treatment of Lung Cancer, China Lung Oncology Group 2025 Dec 20 置信度 0.82
• Antidepressant use among American adults in a 50-state survey.
  Antidepressants are among the most prescribed medications in the USA, yet challenges in access to mental health treatment persist.
  pubmed Perlis RH, Ramachandiran AK, Verhaak PF, Santillana M 等 2026 Jan 21 置信度 0.82
• Understanding acute vertigo in emergency care in a large London teaching hospital: patient and physician perspectives on diagnostic challenges and digital support.
  Acute vertigo is a common but diagnostically challenging presentation in emergency departments (EDs), where rapid distinction of life-threatening conditions-like stroke-is critical. Patient and clinician perspectives are often overlooked, and real ED needs and…
  pubmed Cortese E, Ramsay AIG, Koohi N, Kaski D 2026 Jan 21 置信度 0.82
• Retinal biomarkers for early Alzheimer's detection: a systematic review of optical coherence tomography (OCT) findings.
  Retinal biomarkers accessible via non-invasive optical coherence tomography (OCT) could facilitate early detection of Alzheimer's disease (AD), complementing current invasive or costly diagnostic methods. This review evaluates the evidence for spectral-domain …
  pubmed Lepoittevin M, Greig J, Erol O, Benani A 等 2026 Jan 21 置信度 0.82
• Federated Learning in Healthcare: From Research to Real-World Deployment.
  Artificial intelligence (AI), including deep and traditional machine learning, holds great promise for advancing biomedical research and healthcare. However, most AI studies remain academic in nature and rarely transition into clinical practice, largely due to…
  pubmed Bakas S, Li X, Shah P, Roth HR 2026 May 置信度 0.82
• High-resolution EEG dataset during resting and localized visual stimulation in the lower-left visual field.
  This dataset provides high-temporal-resolution electroencephalography (EEG) recordings collected from eight healthy adults during two conditions: (1) eyes-open resting state and (2) localized visual stimulation using a static, sector-shaped checkerboard presen…
  pubmed Onojima T, Kitajo K 2026 Feb 置信度 0.82
• Workflow-embedded AI as a cognitive scaffold: A randomized trial on knowledge retention and diagnostic competency in undergraduate radiology education.
  Traditional didactic methods in medical imaging education, predominantly reliant on static images (non-augmented, traditional PACS workflow that requires manual, unguided search and interpretation), consistently fail to bridge the theory-practice divide, contr…
  pubmed Li J, Zhao H 2026 Jun 置信度 0.82
• Circulating tumor DNA and Response Evaluation Criteria In Solid Tumors: ctDNA-RECIST proof-of-concept in HER2-positive metastatic breast cancer.
  BACKGROUND: Response Evaluation Criteria In Solid Tumors (RECIST 1.1) and circulating tumor DNA (ctDNA) recapitulate and anticipate response to treatment, respectively. However, ctDNA-RECIST (cRECIST) and ctDNA-guided End of Treatment (cEoT) are not applied ro…
  pubmed Fabi A, Giordani E, Ricciardi E, Arpino G 等 2026 Jan 20 置信度 0.82
• Domain adaptation, self-supervision, and generative augmentation enhance GNNs for breast cancer prediction.
  Breast cancer presents substantial molecular heterogeneity, requiring accurate subtype classification, receptor-status prediction, and survival estimation for precision care. Existing machine-learning models often fail to generalize across cohorts or adapt to …
  pubmed Qiu S, Zhao Y, Li X 2026 Jan 20 置信度 0.82
• Innovative impact of artificial intelligence and management in rural revitalization under fuzzy based decision-making approach.
  The integration of Artificial Intelligence (AI) and modern management strategies plays a transformative role in rural revitalization, helping rural regions shift from traditional, resource-based economies to innovation-driven and sustainable development models…
  pubmed Wang M, Zhang H, Zhao H 2026 Jan 20 置信度 0.82
• Evaluation of three artificial intelligence chatbots for generating clinical hematology multiple choice questions for medical students.
  The integration of artificial intelligence (AI) into medical education has shown promise in streamlining content creation, yet the reliability and validity of AI-generated assessments remain critical concerns. This study evaluates three AI models-ChatGPT, Perp…
  pubmed Boufrikha W, Sallem A, Laabidi B, Mallek R 等 2026 Jan 20 置信度 0.82
• AI-enabled energy baselines for verified building decarbonization.
  Accurately quantifying energy savings in retrofitted and operational buildings remains challenging due to dynamic occupancy, weather variability, and changing operational conditions. This study proposes an AI-enabled Energy Conservation Calculation (ECC) frame…
  pubmed Li J, Hao Y, Li Y 2026 Jan 20 置信度 0.82
• Patient Perceptions of the Use of Artificial Intelligence in Radiology: A Scoping Review.
  Artificial intelligence (AI) is increasingly being used to support diagnostic accuracy and efficiency in radiology. While its technical potential is well recognized, little is known about how patients perceive these tools or whether their expectations align wi…
  pubmed Udupa S, Sharma O, Sharma S, Yong-Hing CJ 2026 Mar 置信度 0.82
• Retinal Coronary Artery Calcium Scoring - A Scalable Tool for Life Insurers.
  Cardiovascular risk estimation for life insurance underwriting relies on risk estimation from conventional metrics: age, sex, smoking status, body mass index, systolic and diastolic blood pressure, total and high-density lipoprotein cholesterol and stress elec…
  pubmed Khan MA 2026 Feb 23 置信度 0.82
• Adjunctive Therapies in Periodontitis: Current Concepts and the Future.
  Periodontitis is a chronic, host-mediated inflammatory disease in which microbial dysbiosis and dysregulated immune responses drive the destruction of tooth-supporting tissues. Although conventional therapy remains centered on mechanical biofilm control, persi…
  pubmed de Molon RS, Steffens JP, de Avila ED, Teughels W 等 2026 Feb 置信度 0.82
• Token-Level Attribution for Transparent Biomedical AI.
  Explainability (xAI) is critical for fostering trust, ensuring safety, and supporting regulatory compliance in healthcare AI systems. Large Language Models (LLMs), with impressive capabilities, operate as "black boxes" with prohibitive computational demands an…
  pubmed Geukes Foppen RJ, Zoccoli A, Gioia V 2026 置信度 0.82
• Artificial Intelligence-Powered Answers to Questions in Genomic Medicine.
  We asked first-year medical students to critique ChatGPT-generated responses to questions in genomic medicine. Students compared AI outputs to biomedical literature, highlighting AI's strengths and limitations. The exercise fosters critical thinking about AI i…
  pubmed Worden MK, Cruise A, Craig JMB, Williams ES 2025 Oct 置信度 0.82
• Mapping the integration of artificial intelligence in knee replacement surgery: a data-driven bibliometric analysis with emphasis on robotic innovation.
  Artificial intelligence (AI) is increasingly reshaping the landscape of orthopedic surgery, with notable applications in knee replacement surgery (KRS), particularly in robotic-assisted interventions. AI-driven tools are enhancing preoperative planning, intrao…
  pubmed Khired ZA, Taha MME 2026 Jan 20 置信度 0.82
• Adapting quality function deployment to translate patient feedback into prioritized technical requirements for healthcare artificial intelligence.
  Human-centered artificial intelligence (AI) is increasingly recognized as important to advancing quality, safety, and trust in healthcare analytics, yet most validation frameworks continue to prioritize technical metrics over interpretability and stakeholder e…
  pubmed Muda N, Sulaiman MH 2026 Jan 19 置信度 0.82
• Genomic language model mitigates chimera artifacts in nanopore direct RNA sequencing.
  Chimera artifacts in nanopore direct RNA sequencing (dRNA-seq) introduce substantial inaccuracies, complicating downstream applications such as transcript annotation and gene fusion detection. Current basecalling models are unable to detect or mitigate these a…
  pubmed Li Y, Wang TY, Guo Q, Ren Y 等 2026 Jan 19 置信度 0.82
• The feasibility of diol-assisted fractionation for lignin-first biorefinery: An integrated process design and sustainability study.
  Lignin-first biorefinery strategies have emerged as powerful method to prevent undesired recondensation during biomass fractionation, thereby enabling the sustainable valorization of lignin and cellulose. Among these, the diol-assisted fractionation (DAF) oper…
  pubmed Ai J, Zhang Z, Zhan G, Chen Y 等 2026 Mar 置信度 0.82
• Bridging Organic Chemistry Teaching Laboratories and Real-World Research with Modern Computing and Spectroscopic Techniques.
  The Reimagining Organic Chemistry Laboratories in Education Systems (ROLES) initiative at Spelman College was established to provide undergraduate students with synthetic, analytical, computing, and critical-thinking skills necessary for training innovators an…
  pubmed Camp DM 2026 Jan 13 置信度 0.82
• Exploring the Role of DeepSeek in Addressing Common Patient Concerns About Colorectal Cancer: A Commentary.
  Since its inception, Artificial Intelligence (AI) has demonstrated its utility across diverse scientific and clinical domains. One such AI chatbot, developed by a Chinese AI company and widely used across the Asia-Pacific region, is DeepSeek AI. As it is well …
  pubmed Kocharlakota SVNS 2025 Dec 置信度 0.82
• Ribbon-shaped microgels as bioinks for 3D bioprinting of anisotropic tissue structures.
  Granular microgels are attractive bioinks for bioprinting due to their injectability, printability, modularity, and enhanced macroporosity compared to conventional nanoporous hydrogels. Despite the potential of microgels for bioprinting, most previous work has…
  pubmed Lee HP, Tai M, Jones SJ, Tong X 等 2026 May 置信度 0.82
• MuCoSA: Multi-contextual similarity assessment for histopathology image search.
  Histological diagnosis in pathology often begins with visual identification of morphological patterns that resemble known disease entities. Whereas digital pathology and augmented intelligence have enabled reverse image search in histopathology, most existing …
  pubmed Kim GY, Jeon Y, Jeong H, Lee S 等 2026 Jan 置信度 0.82
• Carboxymethyl chitosan hydrogel particles for Pretilachlor delivery: ensuring sustained release and environmental safety in rice weed control.
  Pretilachlor (PR), a pre-emergence herbicide crucial for rice weed management, is prone to rapid degradation and poses significant environmental risks, necessitating frequent applications. This study aims to develop an environmentally friendly carboxymethyl ch…
  pubmed Jiang T, Li Z, Tan Y, Liang Q 等 2026 May 置信度 0.82
• AI-driven patient-centered care: A digital transformation framework for gynecologic cancer genetic counseling.
  ObjectivesThis study evaluates artificial intelligence (AI) reasoning capabilities in gynecologic cancer genetic counseling, comparing the performance of ChatGPT and DeepSeek models to guide patient-centered AI implementation in clinical genetics.MethodsUsing …
  pubmed Yang R, Zheng X, Deng Y, Deng M 等 2026 Jan-Mar 置信度 0.82
• Risk of total hip arthroplasty following lumbar fusion surgery in a nationwide cohort study.
  Alterations in spinopelvic alignment following lumbar fusion surgery (LFS) have been suggested to influence hip biomechanics, yet long-term population-based evidence regarding the risk of total hip arthroplasty (THA) remains limited. Using a nationwide cohort …
  pubmed Bae Y, Lee SW, Seo S, Han J 等 2026 Jan 18 置信度 0.82
• The effectiveness of AI-based conversational agents in nursing education: A systematic review.
  Comprehensive evaluation of randomized and non-randomized controlled trials (RCTs and NRCTs, respectively) on the effectiveness of AI-driven conversational agents in nursing education.
  pubmed Go J, Lee Y 2026 Feb 置信度 0.82
• Unlocking 2D/3D+T myocardial mechanics from cine MRI: a mechanically regularized space-time finite element correlation framework.
  Accurate and biomechanically consistent quantification of cardiac motion remains a major challenge in cine MRI analysis. While classical feature-tracking and recent deep learning methods have improved frame-wise strain estimation, they often lack biomechanical…
  pubmed Liu H, Qin X, Liu Z, Jin Y 等 2026 Mar 置信度 0.82
• Prioritizing Feasible and Impactful Actions to Enable Secure AI Development and Use in Biology.
  As artificial intelligence continues to enhance biological innovation, the potential for misuse must be addressed to fully unlock the potential societal benefits. While significant work has been done to evaluate general-purpose AI and specialized biological de…
  pubmed Dettman J, Lathrop E, Attal-Juncqua A, Nicotra M 等 2026 May 置信度 0.82
• AI-assisted preoperative planning combined with robotic-assisted total knee arthroplasty vs. conventional surgery: a retrospective controlled study.
  To compare perioperative outcomes and early functional recovery between AI-robotic and conventional total knee arthroplasty (TKA).
  pubmed Hu Y, Fan Y, Sun Z, Song H 2026 Jan 16 置信度 0.82
• Arachidonic acid analog AACOCF3 suppresses cPLA2-negative NSCLC cell proliferation by targeting SSRP1 to activate the IFNα/β pathway.
  AACOCF3, a cell-permeable arachidonic acid analogue, is widely established as a selective inhibitor of cytosolic phospholipase A2 (cPLA2, PLA2G4A) in studies of metabolic disorders. Although its primary mechanism involves cPLA2 inhibition, emerging evidence in…
  pubmed Wang H, Wen Z, Jia Y, Tong X 等 2026 Apr 置信度 0.82
• A Multimodal Framework for Understanding Collaborative Design Processes.
  An essential task in analyzing collaborative design processes, such as those that are part of workshops in design studies, is identifying design outcomes and understanding how the collaboration between participants formed the results and led to decision-making…
  pubmed Koch M, Pathmanathan N, Weiskopf D, Kurzhals K 2026 Jan 置信度 0.82
• Acceptability of Using Large Language Models to Support Smoking Cessation Attempts: a Qualitative Study Among African Americans Who Smoke.
  African Americans face significant disparities in tobacco-related diseases and access to smoking cessation resources. Digital health interventions using large language models (LLMs) show promise in increasing engagement and successful quit attempts. However, i…
  pubmed McKinney W, Fernholz D, Pakhomov S, Kotlyar M 等 2026 May 22 置信度 0.82
• KIF18A inhibition and its rising role in cancer therapy trials: from bench to bedside.
  Chromosomal instability (CIN), a hallmark of over 90% of solid tumors, presents both a vulnerability and an opportunity in cancer therapy. KIF18A, a kinesin motor protein essential for mitotic fidelity, becomes critical for CIN cancer cells, where it suppresse…
  pubmed Truong JQ, Galper T, Holien JK 2026 Jan 置信度 0.82
• Artificial Intelligence in Nutrigenomics: A Critical Review on Functional Food Insights and Personalized Nutrition Pathways.
  This review critically evaluates the applications of artificial intelligence in nutrigenomics, focusing on its role in interpreting functional food-gene interactions, supporting personalized nutrition strategies, and enabling evidence-based dietary interventio…
  pubmed Balamurugan J, Adeyeye SAO 2026 Feb 置信度 0.82
• NetMHCIIphosPan: a machine learning tool for predicting HLA class II antigen presentation of phosphorylated peptides.
  Phosphorylated peptides presented by human leukocyte antigen (HLA) class II molecules play pivotal roles in immune regulation, yet their characterization and prediction remain challenging due to data noise and limited HLA coverage. Here, we introduce NetMHCIIp…
  pubmed Alvarez HMG, Kaabinejadian S, Yari H, Shepherd CM 等 2026 Jan 5 置信度 0.82
• A visually grounded language model for fetal ultrasound understanding.
  Freehand fetal ultrasound examinations require substantial clinical skill. Here we propose Sonomate (mate of a sonographer), an AI assistant to a user during fetal ultrasound examinations. Sonomate is based on aligning video features and text features derived …
  pubmed Guo X, Alsharid M, Zhao H, Wang Y 等 2026 Aug 置信度 0.82
• Illuminating the functional dark matter of the gut microbiome.
  In this issue of Cell Host & Microbe, Liu et al. provide a roadmap for decoding the gut microbiome's functional dark matter through a structural atlas of gut phage and bacterial proteins, validating structure-guided functions from endolysins to microbial-h…
  pubmed Zhang H, Liao C 2026 Jan 14 置信度 0.82
• Egyptian National Consensus on Dermocosmetic Ingredient Selection Across Common Dermatology Scenarios: A RAND/UCLA Appropriateness Study.
  Dermocosmetics are widely used to complement dermatologic care, yet context-specific guidance remains limited for populations with Fitzpatrick skin types III-V. We convened a national expert panel to generate transparent, reproducible recommendations across te…
  pubmed Rageh MA, Seoudy WM, Abozeid MF, Elkholy AM 等 2026 Feb 置信度 0.82
• From observation to understanding: A multi-agent framework for smart microscopy.
  Smart microscopy represents a paradigm shift in biological imaging, moving from passive observation tools to active collaborators in scientific inquiry. Enabled by advances in automation, computational power, and artificial intelligence, these systems are now …
  pubmed Kesavan PS, Nordenfelt P 2026 Jan 15 置信度 0.82
• Surgically Oriented Ultrasound-Based AI of Median Nerve Morphology as a Decision Support for Carpal Tunnel Release: A Calibrated ConvNeXt-CBAM Framework With Supervised Contrastive Warm-Up.
  Carpal tunnel syndrome (CTS) is a compressive neuropathy commonly encountered in hand surgery, and decisions regarding whether operative decompression should be conducted rely on accuracy and clinical interpretability of imaging findings. Ultrasound is commonl…
  pubmed Yang K, He X, Ye P, Qian Y 等 2026 Jan 10 置信度 0.82
• Deep eutectic solvents for green extraction and separation of bioactive compounds from traditional Chinese medicines.
  Traditional Chinese Medicines (TCM) has long relied on bioactive compounds derived from natural sources, but conventional extraction and separation methods often involve violate/hazardous organic solvents, posing environmental and health risks. Deep Eutectic S…
  pubmed Ali A, Li R, Zhu R, Mahmood S 等 2026 Jan 15 置信度 0.82
• Training large language models on narrow tasks can lead to broad misalignment.
  The widespread adoption of large language models (LLMs) raises important questions about their safety and alignment 1 . Previous safety research has largely focused on isolated undesirable behaviours, such as reinforcing harmful stereotypes or providing danger…
  pubmed Betley J, Warncke N, Sztyber-Betley A, Tan D 等 2026 Jan 置信度 0.82
• Progress in wastewater treatment, separation and purification technologies: mechanisms, benefits, challenges, efficiencies, and sustainability perspectives.
  Escalating global demand for clean water, compounded by increasing contamination from untreated wastewater effluents, has intensified the need for advanced wastewater treatment, separation, and purification technologies. Wastewater treatment is indispensable f…
  pubmed Ossai IC, Hamid FS, Redzwan G, Aboudi-Mana SC 等 2026 Feb 1 置信度 0.82