AI 安全与对齐 · 全部实体（第 19 / 100 页）

本页收录第 1801–1900 条，共 10000 条 · 返回 AI 安全与对齐 首页

• Explainable deep learning framework incorporating medical knowledge for insulin titration in diabetes.
  Deep learning has shown promise in diabetes management but faces challenges in real-world application due to its "black-box" nature, characterized by opaque internal decision-making processes. Explainable artificial intelligence (XAI) methods have been propose…
  pubmed He H, Ying Z, Li B, Fan Y 等 2026 Feb 26 置信度 0.82
• A genomic approach for accurate identification of closely related species with next-generation sequencing samples.
  Accurate species identification from Whole Genome Sequencing (WGS) data remains challenging, particularly for closely related species such as sheep (Ovis aries) and goats (Capra hircus). Through analysis of mapping quality metrics and Kraken2 taxonomic classif…
  pubmed Dain Marzouka NA, Al-Aamri A, Alshamsi F, Khalili M 等 2026 Feb 27 置信度 0.82
• Nanofiber-assisted construction of flexible sponge sensors with engineered biomimetic structures for wearable devices and gesture recognition.
  Porous flexible piezoresistive sensors are commonly used in wearable devices. To achieve excellent deformation capability, sensitive resistance changes, and stable signal input, such sensors must possess a robust skeletal structure and abundant pores. This not…
  pubmed Liu C, Xin P, Wang L, Jiang S 等 2026 Feb 26 置信度 0.82
• A joint CNN-Bi-LSTM-transformer architecture with SHAP explanations for multi-label arrhythmia detection from 12-lead ECGs.
  Interpretable, automated Artificial Intelligence (AI) solutions are essential for accurate 12-lead electrocardiogram (ECG) arrhythmia classification because they remove the time-consuming and inconsistent aspects of manual interpretation. Current models are li…
  pubmed Al-Bairmani MT, Yazdchi M, Nasimi F 2026 Feb 26 置信度 0.82
• Enhancing generative networks for chest anomaly localization through automatic registration-based unpaired-to-pseudo-paired training data translation.
  Generative adversarial network–based image translation (GAN-IT) has emerged as a promising approach for chest X-ray (CXR) anomaly localization (AL-CXR) without pixel-level annotations, especially when training relies on unpaired data. However, the nonst…
  pubmed Oh SJ, Kim K, Lim CY, Lee JH 等 2026 Feb 26 置信度 0.82
• Patient perceptions of artificial intelligence in ophthalmology: a cross-sectional survey study.
  Patients have largely been excluded from discussions on the use of their health data in developing medical artificial intelligence (AI), despite being directly affected by its integration into care. This study assessed ophthalmology patients' perspectives on A…
  pubmed McCarthy A, Eltemsah L, Cui A, Diamond ME 等 2026 Aug 20 置信度 0.82
• Nurse educators' experiences integrating artificial intelligence in teaching and practice: A descriptive phenomenological study.
  Artificial intelligence (AI) is rapidly reshaping nursing education by transforming teaching strategies, student engagement, and clinical learning. Despite its growing influence, there is limited evidence exploring how nurse educators experience and navigate t…
  pubmed Kulintang MBM, Ngo AD, Salas CJC, Sumaoy KC 等 2026 Jul 置信度 0.82
• Using AI in Forward-Backward Translation of Questionnaires for Men Invited to Prostate Cancer Screening: Methodological Study.
  Translation is important in research to ensure cultural relevance, accuracy, and generalizability, particularly in cross-cultural studies. The forward-backward translation method of the World Health Organization (WHO) is commonly used to improve linguistic and…
  pubmed Andersen SM, Kirkegaard P, Tupikowski K, Hodyra-Stefaniak K 等 2026 Feb 26 置信度 0.82
• PDXNet: An eXplainable Hybrid Attention Convolutional Neural Network for Parkinson's Disease Monitoring and Evaluation.
  Parkinson's disease (PD), the second most common neurodegenerative disorder, affects patients and caregivers worldwide. There is a growing need for technologies that use portable wearable sensors to monitor and assess patients using artificial intelligence (AI…
  pubmed Zhang L, Liu W, Ni Q, Gao Z 等 2026 置信度 0.82
• Rapid and reliable diagnosis of mucormycosis using colorimetric loop-mediated isothermal amplification.
  Current diagnostic approaches for mucormycosis are often limited by low sensitivity and prolonged turnaround times, which result in delayed treatment and poor clinical outcomes. We developed a novel diagnostic method utilizing a colorimetric loop-mediated isot…
  pubmed Gu Y, Ibrahim BA, Gebremariam T, Alkhazraji S 等 2026 Apr 8 置信度 0.82
• Simulation-free spine palliative radiotherapy enabled by AI-adapted diagnostic CT.
  Radiotherapy planning traditionally requires a dedicated simulation CT (sCT), which can introduce delays in initiating treatment. This is particularly impactful in spinal palliative care, where timely treatment is often important for symptom control and preven…
  pubmed Han Y, Hanania AN, Siddiqui ZA, Ugarte V 等 2026 Mar 置信度 0.82
• Future Perspectives on the Application of Systems Biology and Generative Artificial Intelligence in the Design of Immunogenic Peptides for Vaccines.
  Peptide-based vaccines offer a modular and readily manufacturable platform for both prophylactic and therapeutic immunization. However, their broader translation has been constrained by the limited capacity to predict protective immunity directly from sequence…
  pubmed Lastra JMP, Sobrino I, Rodríguez Borges VM, de la Fuente J 2026 Feb 13 置信度 0.82
• AI-Assisted Differentiation of Dengue and Chikungunya Using Big, Imbalanced Epidemiological Data.
  Dengue and chikungunya are endemic arboviral diseases in many low- and middle-income countries, often co-circulating and presenting with overlapping symptoms that hinder early diagnosis. Timely differentiation is critical, especially in resource-limited settin…
  pubmed Nguyen TH, Le NQK 2026 Jan 30 置信度 0.82
• Artificial Intelligence in Veterinary Education: Preparing the Workforce for Clinical Applications in Diagnostics and Animal Health.
  Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), is rapidly transforming clinical veterinary practice by enhancing diagnostics, disease surveillance and decision support processes across animal health domains. The safe and …
  pubmed Pérez-García E, Ramírez AS, Quintana-Suárez MÁ, Conde-Felipe MM 等 2026 Feb 12 置信度 0.82
• Transcriptomic Profiling Across Developmental Stages of Camellia petelotii (Merr.) Sealy Flower.
  Background : The Camellia genus is widely recognized for its remarkable diversity in floral morphology and coloration, with Camellia petelotii (Merr.) Sealy being particularly notable for its rare golden-yellow flowers, which possess exceptional ornamental val…
  pubmed Wang Y, Chen X, Zou S, Li X 等 2026 Feb 9 置信度 0.82
• Generation of Schlafen 8-Specific Antibodies.
  Background/Objectives : Schlafen (SLFN) 8 and SLFN9 are mouse members of the Schlafen protein family, believed to have arisen through a gene duplication event. The physiological roles of these proteins remain poorly defined, in part due to the absence of relia…
  pubmed Silva-Espinoza JC, Rodriguez Rodriguez MI, Perucho CE, Terrazas BA 等 2026 Feb 21 置信度 0.82
• In Vitro Mechanical Study of Three-Dimensional Printed Invisible Dental Aligners for Crowded Dentition Problems: A Patient-Specific Study.
  Clear aligners are a popular alternative to fixed orthodontic appliances; however, technical data on the optimal final aligner shell thickness for directly printed aligners remain limited. This in vitro experimental pilot study evaluated the mechanical respons…
  pubmed Reynosa Z, Gan HS, Ramlee MH 2026 Feb 3 置信度 0.82
• Impact of Catheter Configuration on the Mapping of Atrial Fibrillation.
  Mapping of heart rhythms is influenced by the size and configuration of the mapping electrodes. Whether a recorded electrogram represents near (local) or remote activity influences diagnosis and treatment, yet is affected by mapping characteristics that are of…
  pubmed Rodrigo M, Ruipérez-Campillo S, Ganesan P, Feng R 等 2026 Mar 置信度 0.82
• Health technology assessment and medical insurance access for rare disease drugs in China: A policy review with quantitative insights from publicly available data.
  To ascertain the status and propose optimization strategies for rare disease drugs (RDDs) value assessment in the scenario of the National Reimbursement Drug List (NRDL) dynamic adjustment in China, we conducted a narrative policy review that synthesized publi…
  pubmed Ai D, Sui B, Duan C, Liu Z 等 2026 Feb 28 置信度 0.82
• Advancing Decision Support Systems with Data, Informatics, and Learning Health Systems in a Post-Meaningful Use Era.
  The HITECH Act and Meaningful Use (MU) successfully drove widespread EHR adoption but largely missed the strategic goal of healthcare transformation. While EHRs are now ubiquitous, few institutions have transitioned to a true Learning Health System (LHS). To s…
  pubmed Wilcox A 2026 Jan-Feb 置信度 0.82
• Interfacial Synergy in a Band-Aligned Low-Dimensional Heterojunction Toward Broadband Photodetection.
  Monolithic integration of sensing, imaging, and communication from visible to terahertz bands on a single chip remains challenging as efficient detection across such disparate energies demands stringent, often incompatible material properties. However, convent…
  pubmed Wen Y, Xiao K, Yang Y, Jiang M 等 2026 Apr 置信度 0.82
• Chalcones as Multi-target Ligands for Alzheimer's Disease: A Review of Synthetic Strategies and Therapeutic Promise.
  Alzheimer's disease remains a multifactorial neurodegenerative disorder with limited therapeutic options. Chalcones, flavonoid-derived molecules with high structural flexibility and diverse biological activities, have emerged as promising candidates due to the…
  pubmed Antoniolli G 2026 置信度 0.82
• Aligning AI and clinical expertise: A collaborative path for patient education.
  pubmed Rotem R, O'Sullivan OE 2026 Aug 置信度 0.82
• Integrating trust into artificial intelligence for medicine: using diabetes as the exemplar disease.
  Artificial Intelligence (AI) has the potential to impact healthcare across multiple domains. In diabetes, a complex chronic disease affecting 600 million people globally, AI is already being used from primary care to tertiary specialist care to reduce pat…
  pubmed Shao MM, Scheideman AF, Kerr D, Wong TY 等 2026 Feb 25 置信度 0.82
• Digital mental health needs a purpose-driven approach.
  Digital mental health (DMH) encompasses telepsychiatry, mobile apps, games and artificial intelligence (AI)-augmented interventions. In recent years, there has been a steady increase in the development and deployment of DMH solutions, particularly those incorp…
  pubmed Househ M, Shah HA, Tariq ZUA, Alsayed Hassan D 等 2026 Feb 置信度 0.82
• MEETI: A Multimodal ECG Dataset from MIMIC-IV-ECG with Signals, Images, Features and Interpretations.
  Electrocardiograms (ECGs) are essential for diagnosing arrhythmias, myocardial ischemia, and conduction disorders. While machine learning has achieved expert-level performance in ECG interpretation, the development of clinically deployable multimodal artificia…
  pubmed Zhang D, Lan X, Geng S, Zhao Q 等 2026 Feb 26 置信度 0.82
• Emily vs. Lakisha: Quantifying socioeconomic and structural disparities in AI-generated ovarian cancer care plans.
  Rapid integration of Large Language Models (LLMs) into oncology workflows mandates scrutiny of implicit biases that may exacerbate health inequities. This study quantifies structural biases in LLM-generated referral plans for Advanced Ovarian Cancer.
  pubmed İnan M, Akar İnan S, Aypak C, Türkmen O 2026 Apr 置信度 0.82
• Ensuring reliable feature importance in food chemistry AI.
  Food chemistry's rapid AI adoption (2060 AI articles; 415 in 2025) spans machine learning, logistic regression, random forests, and XGBoost. Yet a skills gap in supervised learning fuels misinterpretation: Models optimize prediction, not true associations, and…
  pubmed Takefuji Y 2026 Apr 30 置信度 0.82
• Generative artificial intelligence in dementia care: a scoping review protocol on nursing roles, experiences and ethical perspectives.
  Generative artificial intelligence (GAI), including large language models and multimodal generative systems, is rapidly emerging in healthcare with growing interest in its potential applications for dementia care. These technologies offer new possibilities for…
  pubmed Chen YC, Nieh HC, Chen HC, Chen JC 等 2026 Feb 24 置信度 0.82
• Reflective analysis in radiography research: Methodological foundations and reporting guidance.
  Radiography research has traditionally prioritised quantitative approaches, which are less suited to examining complex practice-based phenomena such as professional judgement, ethical tension, and relational aspects of care and education. Reflective analysis h…
  pubmed Chau S, Ago JL, Kerr H, Ofori-Manteaw B 等 2026 Apr 置信度 0.82
• Anticipating Moral and Economic Considerations, Opportunities, and Potential Frictions for AI in Medical Imaging: Multistakeholder Cocreation Study.
  Artificial intelligence (AI) promises to significantly impact daily radiology practices. Numerous studies have already been conducted that anticipate this potentially disruptive innovation. So far, these studies have mainly focused on single topics, such as "t…
  pubmed Schilder MB, Keyser A, van Hees S, Sbrizzi A 等 2026 Feb 25 置信度 0.82
• Fog/Edge-Aware State Space Models for Multi-Task Chest X-ray Report Generation and Lesion Detection.
  Artificial intelligence (AI) is transforming radiology, particularly in automating medical report generation and abnormality detection. Although recent AI systems have shown clear potential in reducing radiologists' workloads and improving diagnostic accuracy,…
  pubmed Feng W, Lu Y, Li X, Yung KL 等 2026 Feb 25 置信度 0.82
• Ultra-Stable RNA-Based Monomolecular Triplexes.
  The formation of stable nucleic acid triplexes requires an underlying homopurine:homopyrimidine duplex and a third strand that is bound to the homopurine strand through Hoogsteen interactions. Depending on its nucleotide composition, the triplex-forming oligon…
  pubmed Kankia N, Kelley E, Musier-Forsyth K, Kankia B 2026 Mar 12 置信度 0.82
• Chronic intermittent hypoxia reshapes circadian metabolic architecture in a model of sleep apnea.
  Obstructive sleep apnea (OSA), characterized by chronic intermittent hypoxia (IH) during sleep, is increasingly recognized as a driver of metabolic dysfunction. However, its impact on circadian metabolic regulation remains poorly understood. Here, we investiga…
  pubmed Montellier E, Vial G, Bouyon S, Ashtiani KC 等 2026 Feb 27 置信度 0.82
• A Deep Metric Learning and Multimodal Gated Fusion Framework for AI-Driven Risk Assessment of Lingual Plate Perforation and Mandibular Canal Injury in Posterior Mandible Implants.
  To provide an automated risk assessment for lingual plate perforation (LPP) and mandibular canal injury (MCI) in dental implants. Also, to reduce interoperator variability in risk classification and eliminate manual measurements during implant planning.
  pubmed Al-Taezi KA, Liu L, Al-Badwi A, Al-Taezi MA 等 2026 置信度 0.82
• The role and future of the population health observatory: advancing public health intelligence in Saudi Arabia.
  The Population Health Observatory (PHO), established by Saudi Arabia's Ministry of Health, employs cutting-edge technology, machine learning (ML), and proactive forecasting to analyse big data as part of strategic efforts to advance the nation's health at the …
  pubmed Al Eissa MM, Aloufi ME, Eskandarani A, Alshehri AM 等 2026 置信度 0.82
• Standards-Aligned Integration of Artificial Intelligence and Simulation in Nursing Professional Development for Novice Nurse Readiness.
  As artificial intelligence (AI) reshapes health care delivery, nursing professional development (NPD) educators must develop digital readiness in novice nurses. Recent accreditation trends for transition-to-practice programs have formalized curriculum design, …
  pubmed Webb CC, Antisdel J, Pajakowski L 2026 Feb 25 置信度 0.82
• Comparison of large language models for clinical scenario generation in medical education: a mixed-methods study.
  In undergraduate medical education, the ability to manage clinical-cases is a core competency expected of future physicians. Traditionally, this skill is developed through repeated exposure to real patient encounters in clinical settings. However, increasing p…
  pubmed Öncü S, Torun F, Ülkü HH 2026 Feb 24 置信度 0.82
• Mapping factors associated with nurses' attitudes toward artificial intelligence: a scoping review.
  BACKGROUND: The integration of artificial intelligence (AI) into nursing practice is advancing, with nurses’ attitudes as a potential critical factor for its successful adoption. A comprehensive understanding of these attitudes is therefore needed. OBJE…
  pubmed Jin S, Feng C, Xin Y, Zhang M 等 2026 Feb 24 置信度 0.82
• Enhancing Psychiatry Education with Generative AI: A Pilot Study on AI-Assisted Object Relations Theory Training.
  To assess whether object relations theory (ORT) formulations generated by large language models (LLMs) enhance resident education in psychodynamic psychiatry.
  pubmed Polet C, Anbarasan D, Carrithers B, Gershengoren L 2026 Aug 置信度 0.82
• Pan-cancer frozen section classification using a soft mixture of experts vision transformer under weak supervision.
  Intraoperative frozen section analysis is critical for evaluating tumor malignancy, assessing surgical margins, and informing real-time clinical decisions. However, limitations such as inconsistent slide quality, diagnostic variability, and time constraints ch…
  pubmed Wu J, Yang M, Li J, Sun P 等 2026 Feb 24 置信度 0.82
• AI-driven audio-to-video generation for dynamic content creation via stable diffusion and CNN-augmented transformers.
  Translating spoken words into emotionally and contextually aligned video content remains an open challenge in generative AI. Subtle vocal patterns-such as pauses and pitch modulations-often obscure emotional cues, resulting in visuals that feel emotionally dis…
  pubmed Dharrao D, Dharrao M, Padgaonkar S, Kumari S 等 2026 Feb 24 置信度 0.82
• AI based prediction of severe exacerbation in Asian bronchiectasis patients using the KMBARC registry.
  Classical scoring tools such as the Bronchiectasis Severity Index (BSI) and FACED have shown good performance for predicting adverse outcomes, yet they were developed using European cohorts and may not fully align with Asian clinical characteristics. This stud…
  pubmed Yang B, Kim SH, Kim GH, Min G 等 2026 Feb 25 置信度 0.82
• Polyhedral alkanes as hydrophobic tags for dual-functional ALK inhibitor-degrader.
  To enhance the pharmacological activity of Brigatinib targeting anaplastic lymphoma kinase (ALK), we developed a 4D-QSAR model based on 49 Brigatinib derivatives. Model visualization suggested that introducing bulky hydrophobic groups at the piperazine moiety …
  pubmed Chu D, Han H, Wei C, Zhang X 等 2026 Jun 5 置信度 0.82
• Banana 0.9: An open-source, reproducible medical imaging system for low-resource gastric cancer screening.
  Gastric cancer remains a major global health burden, particularly in East Asia, yet early-detection programs are often limited by computational constraints, variable imaging quality, and uneven resource availability across clinical settings. Existing AI models…
  pubmed Hu X 2026 置信度 0.82
• Improving Preschoolers' Fire Injury Prevention Using the Health Action Model.
  Young children face elevated risks of unintentional fire injuries, yet few early childhood programs incorporate explicitly theory-informed prevention approaches. Grounded in the Health Action Model (HAM), which emphasizes beliefs, motivation, intentions, and a…
  pubmed Huang WH, Chen HL 2026 Aug 置信度 0.82
• Electrospun polymeric scaffolds enable 3D tissue-like functionality and efficient photoinduced contraction.
  Muscle tissue engineering aims to develop functional muscle constructs with controllable contraction for applications in regenerative medicine and drug screening. In this study, we present the development of a biocompatible, light-responsive bio-hybrid constru…
  pubmed Simoncini G, Marangi F, Venturino I, Vurro V 等 2026 Mar 5 置信度 0.82
• Combining Diverse Expert Opinions in Risk Analysis Using Relative Causal Knowledge.
  Disagreements among domain experts are common in risk analysis, especially when models differ in data sources, causal assumptions, or levels of abstraction. Conventional methods-such as averaging or pooling quantitative probabilities or forcing consensus-risk …
  pubmed Cox LA 2026 Mar 置信度 0.82
• Multimodal perishable fruits and vegetables dataset.
  There is a growing need in the agricultural industry for non-invasive methods to classify the freshness and quality of produce. To address this, we developed a multimodal dataset comprising six commonly exported fruits and vegetables from India: guava, carrot,…
  pubmed Unnikrishnan D, Deepak K, P T S YA, T B 2026 Apr 置信度 0.82
• Seagrass monitoring methods: Aligning expert opinion with practice.
  Seagrass meadows are vital ecosystems, yet methods to monitor their health lack standardization, which makes data comparison challenging. To identify key approaches and evaluate alignment with expert opinion, we compared the most used health monitoring methods…
  pubmed Rising K, Bulling M, Sweet M 2026 Mar 20 置信度 0.82
• Stakeholder views about the responsibilities of principal investigators in multicenter randomized controlled trials.
  Clinical trials are commonly believed to benefit from the involvement of an academic principal investigator who accepts responsibility for design, conduct, and reporting. Little evidence exists, however, about the importance that diverse stakeholders assign to…
  pubmed Joffe S, Bair EF, Gleason KA, Sellers DE 等 2026 Jun 置信度 0.82
• Fertilization and Aridity Legacies Determine Soil Microbial Necromass Persistence Across Climates.
  Microbial necromass-mineral interactions are vital for soil organic carbon (C) persistence, but their response to concurrent climate and fertilization legacies in croplands remains unclear. Using six long-term field sites (27-38 years) across a pronounc…
  pubmed Xu LX, Yu GH, Liu CQ, Guggenberger G 2026 Feb 置信度 0.82
• Ten simple rules for coordinating a large digital health project: Perspectives from EU and implications for global contexts.
  Coordinating a large-scale digital health project requires a unique mix of scientific leadership, administrative skill, and human sensitivity. Drawing from our experience leading CAPABLE, a European Horizon 2020 project aimed at improving the quality of life o…
  pubmed Sacchi L, Zupan B, Quaglini S 2026 Feb 置信度 0.82
• EEG, clinical, and MRI features of status epilepticus associated with mitochondrial diseases.
  This study aimed to identify specific EEG features of status epilepticus (SE) in patients with mitochondrial diseases and correlate them with clinical and neuroimaging findings.
  pubmed Damiano M, Lambrecq V, Nguyen-Michel VH, Marois C 等 2026 Feb 23 置信度 0.82
• Dentistry 5.0: An Emerging Framework Integrating Bioengineering, AI, and Global Innovation Pathways for Equitable Oral Health.
  Dentistry is undergoing a profound transformation driven by advances in bioengineering that integrate artificial intelligence (AI), regenerative biology, digital manufacturing, salivary diagnostics, and extended reality (XR). Despite the rapid pace of innovati…
  pubmed Mascolo A, Bugelli G, Dinculescu O, Kipper MJ 等 2026 Jan 置信度 0.82
• Retrieval augmented generation in dentistry: potentials, applications, and future directions.
  Retrieval Augmented Generation offers a robust framework for developing reliable and evidence- aligned artificial intelligence in dentistry. By integrating external knowledge sources with the generative capabilities of large language models, RAG addresses key …
  pubmed Firoozi T, Adabdokht R, Lai H 2025 置信度 0.82
• Multimodal AI for Real-Time Food Safety and Quality: From Sensors to Foundation Models, Edge Deployment, and Regulation.
  Real-time assurance of food safety and quality requires decisions at line speed, from farm to retail, using signals that span vision, spectroscopy, volatiles, biosensing, and process telemetry. This review investigates and summarizes evidence on multimodal art…
  pubmed Chen Z, Zhang G, Zhang F 2026 Feb 置信度 0.82
• Hot-yet-suppressed under PD-1 blockade: an RMP-NRF2-PD-L1 axis associated with a reduced proportional response in hepatocellular carcinoma.
  Immune checkpoint blockade (ICB) provides therapeutic benefits to a subset of patients with hepatocellular carcinoma (HCC); however, reliable predictors of treatment efficacy remain scarce. This study investigates whether RPB5-mediating protein (RMP) facilitat…
  pubmed Zuo M, Li H, Chen N, Guo Z 等 2026 置信度 0.82
• Emotionally based strategic communications as a new tool in defensive cognitive warfare.
  In modern cognitive warfare, adversaries deliberately target human cognition, emotion, belief, trust, and decision-making processes, seeking to destabilize democratic societies through disinformation and divergent media campaigns. This article argues that the …
  pubmed Ćosić K, Popović S, Wiederhold B 2026 置信度 0.82
• Application of the RE-AIM framework to evaluate a stepped care intervention for adolescents and youth living with HIV in Kenya: a mixed methods approach.
  Recently expanded WHO guidelines on differentiated service delivery (DSD) include expanded eligibility for adolescents and youth living with HIV (AYLHIV). We evaluated implementation of a stepped care program that included DSD for stable AYLHIV and intensified…
  pubmed Chhun N, Mangale DI, Agot K, Masyuko S 等 2026 Feb 23 置信度 0.82
• Landscape of diabetic kidney disease drug clinical trials in China (2013-2023): global implications for innovation and policy.
  With the increasing prevalence of diabetes, the incidence rate of diabetic kidney disease (DKD) has risen yearly in China. While traditional therapies like renin-angiotensin system blockers remain foundational, the treatment paradigm is rapidly evolving with t…
  pubmed Yang Y, Tan H, Xiao Z, Zhu J 等 2026 Dec 置信度 0.82
• WOMBAT (ANZUP 2201): A Phase 2, Single-arm Study of Bipolar Androgen Therapy in Patients with Nonmetastatic Castration-resistant Prostate Cancer with Prostate-specific Antigen Progression on Darolutamide.
  Resistance to androgen receptor pathway inhibitors (ARPIs) such as darolutamide signals impending metastatic progression of prostate cancer (PC) with limited subsequent therapeutic options. It has been shown that bipolar androgen therapy (BAT) resensitizes cas…
  pubmed Talmor B, Harris CA, Gianacas C, Pook D 等 2026 Apr 置信度 0.82
• External validation of a pre-trained hybrid convolutional neural network in radiographers agreement of positioning in lateral knee radiographs.
  Accurate positioning in lateral knee radiographs is essential for diagnostic quality but prone to inter-observer variability. Artificial intelligence (AI) may standardize quality assessment, yet its influence on radiographers' critical reasoning and decisions …
  pubmed Lysdahlgaard S, Jensen J, Pedersen MRV, Kusk KW 等 2026 Apr 置信度 0.82
• Waning moon: Revising a culturally informed intervention with perimenopausal American Indian and Alaska native women.
  American Indian and Alaska Native (AI/AN) women experience more vasomotor symptoms during menopausal transition compared to women of other racial and ethnic groups. Yet, there have been no evidence-based interventions aimed at peri‑ and post-menopause t…
  pubmed Aderibigbe T, Kent-Marvick J, Austin S, Macias SN 等 2026 May-Jun 置信度 0.82
• Targeting Where the Burden is: Evaluating California's Emergency Department Screening Program Against Human Immunodeficiency Virus Epidemic Priorities.
  The federal Ending the Human Immunodeficiency Virus (HIV) Epidemic (EHE) initiative emphasizes targeted efforts in "priority" jurisdictions to reduce new infections through earlier diagnosis and treatment. In California, the Emergency Department Screening Prog…
  pubmed Das IG, Yin E, Bennett CL 2026 Apr 置信度 0.82
• Practical prediction model for day 4 embryonic development potential: integration of morphology and AI scoring.
  This study aims to develop a practical predictive model for day 4 embryonic developmental potential, focusing on analyzing key influencing factors and visually presenting their relative importance, and evaluating the model's clinical applicability.
  pubmed Geng Y, Dai F, Dai H, Tao L 等 2026 Feb 21 置信度 0.82
• AI-augmented mixed reality for 3D visualization of perforator vessels: A feasibility study in fibular flap surgery.
  Using the fibular flap as a model, this study aims to develop a three-dimensional visualization method for perforator vessels. This method integrates artificial intelligence algorithms, mixed reality technology, and polyetheretherketone (PEEK) fiducial markers…
  pubmed Liu Y, Wu J, Zhao Y, Wang C 等 2026 Sep 置信度 0.82
• Rapid Detection of Erythrosine (FD&C Red 3) in Candy Using a Paper-Based SERS Substrate and a Handheld Raman Spectrometer.
  Erythrosine (FD&C Red 3) is a synthetic colorant that was banned in food products by the Food and Drug Administration in January 2025. Monitoring Red 3 in food products is significant for the FDA to ensure that the food industry complies with its regulatio…
  pubmed Forbes A, He L 2026 Apr 置信度 0.82
• TADynFed: Dynamic modality-adaptive federated learning with tissue-aware disentanglement for cross-disease analysis.
  Federated learning (FL) enables collaborative medical image analysis across decentralized institutions while preserving data privacy. However, real-world deployment faces critical challenges: modality heterogeneity, where clients possess incomplete or varying …
  pubmed Iqbal S, Zhong X, Khan MA, Wu Z 等 2026 May 置信度 0.82
• Artificial intelligence-generated marathon training programs: reliable tools in exercise prescription for athletic performance?
  Marathon running has evolved into a global phenomenon, with rising participation across age and experience groups. Training for a marathon requires adherence to well-established principles involving pacing, training volume, and periodization. With the increasi…
  pubmed Montaruli G, Nikolaidis PT, Racil G, Maffulli N 等 2026 Jan 2 置信度 0.82
• Prospective pilot evaluation of a deep learning model for kidney stone detection on CT using a web-based workflow platform.
  Rapid and reliable detection of kidney stones on non-contrast abdominal CT is essential for timely decision-making in emergency radiology. However, rising imaging volumes and workflow pressures continue to limit reporting capacity, creating a need for AI syste…
  pubmed Öksüz C 2026 Aug 置信度 0.82
• Strain-Induced Magnetic Ordering Unlocks Spin-Conserved Catalysis in Lithium-Oxygen Batteries.
  Designing advanced ferromagnetic catalysts with robust intrinsic magnetism and efficient spin polarization is critical for enabling spin-selective electron transfer between triplet O 2 and singlet Li 2 O 2 in lithium-oxygen batteries (LOBs), yet controlling ma…
  pubmed Zhou Z, Li B, Li J, Wang K 等 2026 Mar 置信度 0.82
• Characterizing, protocolizing, and scaling up local adjunctive interventions and implementation strategies to enhance the reach of HIV-prevention and mental health/substance use treatments: a study protocol.
  Latino men who have sex with men (MSM) in the United States experience significant HIV disparities, exacerbated by mental health and substance use (MH/SU) concerns. Although evidence-based clinical interventions, such as pre-exposure prophylaxis (PrEP) and MH/…
  pubmed Harkness A, Tidd M, Doblecki-Lewis S, Jaramillo J 等 2026 Feb 21 置信度 0.82
• Multimodal contrastive learning for non-invasive chondroid bone tumor classification and grading using radiographs.
  OBJECTIVE: Diagnosing and grading chondroid bone tumors with radiography is difficult due to overlapping features with benign conditions such as avascular necrosis and fibrous dysplasia. Histology remains the gold standard, but it is invasive, costly, and not …
  pubmed Hua P, Sin JM, Henderson ER, Ha J 等 2026 Feb 20 置信度 0.82
• A novel average treatment effect estimation approach for integrated incomplete datasets, with application in childhood anemia.
  BACKGROUND: Integrating multiple observational datasets from disparate sources remains fundamentally challenging when validation data are absent. These pooled datasets typically contain incomplete records with substantial missingness, necessitating careful han…
  pubmed Woldemariam AA, Zhou Y, Qiu Y 2026 Feb 20 置信度 0.82
• Intelligent tool wear monitoring using XGBoost, SVR, and DNN models in NMQL environment.
  This study explores the implementation of artificial intelligence (AI)-based predictive frameworks for the precise evaluation of tool wear in the sustainable machining of Hastelloy X using PVD TiAlN-coated carbide inserts. To improve lubrication effectiveness …
  pubmed Almomani O, Venkatesh B, Chaudhary SP, Mishra A 等 2026 Feb 20 置信度 0.82
• A multi-scale hybrid ResNet-transformer with distance-aware learning for interpretable BI-RADS mammographic classification.
  Timely and accurate classification of breast lesions is needed on mammograms, as it will enhance clinical decisions and reduce unnecessary biopsies. The study proposes a Multi-Scale Hybrid ResNet–Transformer with Distance-Aware Learning for interpretabl…
  pubmed Singh M, Mohan A, Tripathi U, Pathak S 等 2026 Feb 20 置信度 0.82
• QVT score, a radiomic biomarker of vascular complexity, enables prognostication and monitoring of NSCLC immunotherapy.
  Immune checkpoint inhibitors (ICIs) improve survival in advanced non-small cell lung cancer (NSCLC), yet current biomarkers such as programmed death-ligand 1 (PD-L1) expression and response criteria (Response Evaluation Criteria in Solid Tumors, RECIST, V.1.1)…
  pubmed Chae YK, Velcheti V, Zhang K, Hiremath A 等 2026 Feb 20 置信度 0.82
• The value of artificial intelligence combined with multimodal data analysis in tumor immunotherapy and targeted therapy.
  The advent of immunotherapy and targeted therapy has revolutionized oncology treatment in recent years, marking a transformative shift toward precision medicine. Artificial intelligence (AI) technology has played a pivotal role in tumor immunotherapy, targeted…
  pubmed Lv D, Wang S, Xiao W, Xu J 等 2026 Apr 置信度 0.82
• State-wise linear modulation (SLim): A novel approach for steering large language models.
  The new decade breakthrough Large Language Models (LLMs), trained on extensive text corpora, have achieved remarkable advancements in NLP, demonstrating sophisticated language comprehension and text generation capabilities. However, for effective human-AI inte…
  pubmed Sangayya Hiremath B, Polignano M, Levantesi M, Semeraro G 等 2026 Jul 置信度 0.82
• Enhancing survival analysis through federated learning in non-IID and scarce data scenarios.
  Integrating Artificial Intelligence (AI) into Survival Analysis (SA) has advanced predictive modeling in healthcare, enabling precise and personalized predictions of time-to-event outcomes, such as patient survival. However, real-world SA datasets often suffer…
  pubmed Apellániz PA, Parras J, Zazo S 2026 Mar 置信度 0.82
• Bridging Neural Topology and Affective Computing: Graph Attention for EEG Emotion Recognition.
  Electroencephalography (EEG) offers high temporal resolution and strong physiological validity for emotion recognition. However, complex spatial organization and inter-subject variability present major modeling challenges. Graph-based spatial attention mechani…
  pubmed Yang W, Yuan J, Duan B, Chow SKK 2026 Feb 20 置信度 0.82
• Demographic Disparities in AI-Generated Versus Search-Engine-Sourced Images of Ophthalmologists: A Cross-Sectional Analysis.
  Purpose : To evaluate demographic representation in AI-generated and search-engine-sourced images of North American ophthalmologists, overall and stratified by subspecialty, and compare these with actual demographic data. Methods : This cross-sectional analysi…
  pubmed Gandhi S, Jung K, Balas M, Arjmand P 2026 Feb 10 置信度 0.82
• vEMRec: High-Resolution Volume Electron Microscopy Reconstruction Based on Structure-Preserving and High-Fidelity 3D Alignment.
  Three-dimensional (3D) alignment is a key step in volume electron microscopy (vEM), aimed at addressing misalignment during data acquisition, thereby recovering the correct biological structures. However, automated 3D alignment has long been challenged by the …
  pubmed Zhang Z, Li H, Yang Z, Xu Z 等 2026 Apr 置信度 0.82
• Weightbearing Radiographic Predictors of Middle Facet Subluxation in Progressive Collapsing Foot Deformity.
  Middle facet subluxation (MFS) of the subtalar joint is a key indicator of peritalar subluxation in progressive collapsing foot deformity (PCFD). Although its assessment relies on weightbearing computed tomography (WBCT), it remains unclear which weightbearing…
  pubmed Huánuco Casas EJ, Acker A, Wang CS, Luo E 等 2026 May 置信度 0.82
• AI literacy and creative self-beliefs among Chinese college students: examining the underlying mechanisms and boundary conditions.
  With the rapid advancement of artificial intelligence (AI), enhancing AI literacy has become a critical objective in higher education. How to leverage AI to foster students' creativity thus emerged as a research focus. Creative self-beliefs (creative self-effi…
  pubmed Peng C, Zhang Z, Zhang J, Liu Y 等 2026 置信度 0.82
• Evaluating the Clinical Decision-Making Accuracy of Artificial Intelligence in Common Geriatric Syndromes Using Evidence-Based Guidelines.
  Background Artificial intelligence (AI) tools such as ChatGPT are increasingly being explored for clinical decision support, yet their role in geriatric medicine remains uncertain due to the complexity of multimorbidity and care planning. This study aimed to e…
  pubmed Cassar P, Galea F, Ferry P 2026 Jan 置信度 0.82
• An auditable and source-verified framework for clinical AI decision support: integrating retrieval-augmented generation with data provenance.
  Artificial intelligence (AI) has shown promise in supporting clinical decision making, yet adoption in healthcare remains limited by concerns regarding transparency, verifiability, and accountability of AI-generated recommendations. In particular, generative a…
  pubmed Alu FF, Oluwadare S 2026 置信度 0.82
• Multimodal Machine Learning Approach for Diagnosing Atopic Dermatitis.
  Atopic dermatitis (AD) is a prevalent, chronic inflammatory skin disease with diverse clinical presentations, often overlapping with other dermatoses. Its diagnosis remains largely dependent on clinical expertise, leading to variability and limited diagnostic …
  pubmed Widiawaty A, Indriatmi W, Jatmiko W, Novianto E 等 2025 置信度 0.82
• A configurational exploration of how personality traits influence GAI academic misconduct behaviors using fuzzy-set qualitative comparative analysis.
  The rapid adoption of Generative Artificial Intelligence (GAI) in higher education has introduced new ethical challenges, particularly concerning students' academic misconduct. While prior research has linked personality traits to unethical behavior, little is…
  pubmed Liang H, Reiss MJ 2026 Feb 19 置信度 0.82
• Robust and interpretable unit level causal inference in neural networks for pediatric myopia.
  Understanding causal mechanisms in deep learning is essential for clinical adoption, where interpretability and reliability are critical. Most existing AI systems act as black boxes, limiting transparency in medicine. We propose a causal inference framework in…
  pubmed Jin Z, Kang M, Zhao W, Gui W 等 2026 Feb 19 置信度 0.82
• Predicting porosity in composite high-pressure hydrogen vessels using augmented fuzzy cognitive AI and manufacturing process parameters.
  High-pressure hydrogen storage vessels type IV (HPV), made from carbon fiber-reinforced composites, are essential for hydrogen-powered applications due to their strength and light weight. However, they remain vulnerable to internal defects such as porosities, …
  pubmed Achour L, Zalila Z, Aboura Z, Lorentz B 等 2026 Feb 19 置信度 0.82
• Cloning and functional characterization of Pcficolin1 and Pcficolin2 in red swamp crayfish (Procambarus clarkii).
  To explore the molecular characteristics, tissue expression patterns and biological functions of Ficolin1 and Ficolin2 in red swamp crayfish (Procambarus clarkii), this study cloned the coding sequences (CDS) of the two genes via PCR amplification technology, …
  pubmed Wang L, Zhu X, He H, Ai X 等 2026 May 置信度 0.82
• Research priorities for data science and artificial intelligence in global health: an international consensus exercise.
  Applications of data science and artificial intelligence (AI) in global health are expanding, yet research remains fragmented and often misaligned with the needs of low-income and middle-income countries (LMICs). To address this misalignment, we conducted a gl…
  pubmed Song P, Jiang D, Zhou J, Zhu Y 等 2026 Mar 置信度 0.82
• From modality-specific to compositional foundation models for cell biology.
  Deriving principles governing cell biology from single-cell measurements across modalities, called multimodal modeling, can advance our understanding of cellular states in health and disease. Realizing the full potential of multimodal models requires learning …
  pubmed Bahrami M, Richter T, Schmacke NA, Egea Lavandera A 等 2026 Feb 18 置信度 0.82
• Decoder Design for Concurrent Estimation of Arousal and Performance from One Continuous and Two Binary Observations.
  Human cognitive functions are linked to hidden cognitive states, i.e., arousal and performance. The Yerkes-Dodson law suggests an inverted-U link between these two states, and they may need to be decoded concurrently. However, conventional decoders decode thes…
  pubmed Khazaei S, Gong J, Faghih RT 2026 Feb 19 置信度 0.82
• Nursing Professional Organisations as Human Rights Intermediaries: Towards an Integrated Framework of Stakeholdership for Healthcare AI Governance.
  To propose a normative framework that guides nursing professional organisations to act as human rights intermediaries in the governance of artificial intelligence in healthcare.
  pubmed Cleofas JV 2026 Feb 19 置信度 0.82
• NanoScript-Enabled Nonviral Transient Repression of Phosphatase and Tensin Homolog for Axonal Regeneration and Central Nervous System Injury Repair.
  Spinal cord injury (SCI) remains a debilitating neurological disorder with limited therapeutic options, as existing treatments primarily address symptoms rather than address the complex interplay of cellular and molecular barriers to regeneration. These barrie…
  pubmed Conklin B, Liu Y, Nevins S, Song BG 等 2026 Mar 3 置信度 0.82
• Artificial intelligence for cardiology: from diagnosis to management.
  Artificial intelligence (AI) and machine learning are rapidly transforming cardiac electrophysiology, offering new avenues for diagnosing, managing, and treating cardiac arrhythmias. These technologies leverage diverse data sources, including clinical records,…
  pubmed Naidoo V, Madamshetty L, Krishna SBN 2026 Jan-Dec 置信度 0.82
• The Syndemic Attrition Crisis of European Truck Drivers: A Systems-AI Framework to Transform Research and Policy.
  Truck drivers sustain the movement of goods across Europe, yet the sector faces a concurrent health and workforce retention crisis-mirroring trends observed in North America. Approximately 426,000 driver positions remain unfilled across Europe, while rates of …
  pubmed Apostolopoulos Y 2026 May 置信度 0.82