搜索结果：Artificial

To describe penetrating keratoplasty with sutureless membrane artificial endothelial replacement technique (PK-SMART), a surgical procedure that allows for combined penetrating keratoplasty (PK) and EndoArt (EndoArt, EyeYon Medical, Israel) implantation in high-risk eyes for graft failure. Three consecutive patients with failed PK and a history of multiple ocular surgeries underwent repeat PK combined with implantation of a synthetic endothelial replacement membrane. The implant was positioned within a stromal lamellar pocket of the donor cornea before graft transplantation, without the need for transcorneal sutures or postoperative gas tamponade. Outcome measures included corrected distance visual acuity (CDVA), graft clarity, central corneal thickness, and device adherence. At 6 months, all corneal grafts were clear with complete EndoArt adhesion. Preoperative CDVA ranged from light perception to hand motion in 2 eyes. Postoperative CDVA improved to hand motion, 20/400, and 20/100, respectively. Central corneal thickness decreased in all patients, from 803 to 578 μm, from 975 to 587 μm, and from 761 to 548 μm. No postoperative complications were observed, including implant detachment requiring rebubbling. PK-SMART simultaneously addresses stromal opacities through PK and endothelial dysfunction through artificial endothelial replacement. The technique is suited for complex, high-risk eyes in which standalone EndoArt implantation cannot resolve stromal opacities and is associated with a high risk of device detachment. Central corneal clarity was restored in all our patients, with quantifiable improvements in visual function. Larger studies with extended follow-up will be required to confirm the long-term safety and efficacy of this procedure.

Designing compact, high-gain antennas at 400 MHz is challenging due to large size, narrow bandwidth, and low efficiency. This work proposes an interaction-driven Artificial Magnetic Conductor-Defected Ground Structure (AMC-DGS) microstrip antenna for subsurface communication. The design exploits electromagnetic interaction between the slot-type DGS, radiating patch, and AMC surface with spacer layer for performance enhancement. The DGS functions not only for impedance tuning or to attain polarization purity but also as an active radiator, enabling current redistribution and higher order mode perturbation. This interaction, combined with composite superposed mode (CSM) excitation and orthogonal slot radiation, achieves a 400 MHz band (379-419 MHz) with 10.2% bandwidth and 6.5 dBi peak gain. Additionally, a higher-order mode generates a second band at 700 MHz (700-714 MHz) with 2% bandwidth and 6.1 dBi gain. The antenna maintains stable broadside radiation with efficiencies of 98% and 70% at 400 MHz and 700 MHz, respectively. The proposed AMC-DGS antenna provides a compact, dual-band solution for subsurface sensing, Wireless Underground Sensor Networks (WUSN), Internet of Underground Things (IoUT), Ground Penetrating Radar (GPR), and other low-frequency communication systems.

Family history, body mass index (BMI), and ethnicity are three key, well-established determinants of susceptibility to type 2 diabetes mellitus (T2DM), reflecting genetic predisposition, modifiable metabolic risk, and biological as well as social influences, respectively. These factors interact in complex, non-linear patterns that are not fully captured by conventional risk prediction models. This review examines how artificial intelligence (AI) and machine learning approaches can integrate these variables to improve risk stratification and early identification of individuals at high risk of T2DM. By leveraging large-scale, longitudinal datasets, data-driven models facilitate the capture of population-level heterogeneity and identify risk patterns that extend beyond static thresholds. Incorporating AI-enhanced prediction tools into clinical and public health settings could enable more timely, targeted, and equitable interventions. Ultimately, integrating advances in AI with a deeper understanding of the interplay between BMI, ethnicity, and genetic predisposition may support more personalised prevention strategies and risk-stratified care pathways for T2DM.

Ovarian cancer is a gynecological malignancy associated with high mortality and poses significant clinical challenges in early diagnosis and precision treatment. Although the rapid advancement of artificial intelligence (AI) has introduced novel approaches to this field, a comprehensive bibliometric overview remains lacking. This study aims to fill this gap by providing a systematic bibliometric analysis of this rapidly evolving domain. In this study, the Web of Science Core Collection (WoSCC) was used to retrieve literature on AI applications in ovarian cancer research published from 2006 to the search date (November 19, 2025). Using CiteSpace and VOSviewer, we conducted visual and quantitative analyses of publication trends, countries/regions, institutions, authors, journals, highly cited papers, and keywords. A total of 786 publications were included in the analysis. The annual publication output showed pronounced exponential growth, with a marked acceleration after 2019. China, the United States, and the United Kingdom were the leading contributing countries. Research hotspots centered on AI-assisted diagnosis, prognostic prediction models, radiomics, and biomarker discovery. The evolution of keywords indicated that frontier research has shifted from basic classification toward more advanced areas, including high-grade serous ovarian carcinoma, multimodal learning, and explainable AI. Research on AI in ovarian cancer has progressed rapidly, with international collaboration concentrated among leading contributors such as China, the USA, and the UK. Future efforts should prioritize the development of explainable and robust clinical AI systems, deeper integration of multimodal data, closer collaboration between clinicians and AI researchers, and high-quality data sharing to facilitate the translation of research findings into precise clinical practice.

We compared performance across 3 breast cancer risk domains-clinical, polygenic, and mammography artificial intelligence-alone and in combination over a 10-year time horizon among women with a negative screening mammogram within a Kaiser Permanente Research Bank (KPRB) prospective cohort. The study included 82 957 women (61 962 non-Hispanic White, 7256 Asian, 3414 Black, and 5466 Latina) who enrolled in KPRB between 2003 to 2020. Women with a prior history of breast cancer or high/moderate-penetrant gene mutation were excluded. The negative screening mammogram (no clinically visible cancer) closest to enrollment was used to generate the Mirai mammography AI risk score. KPRB survey and electronic health record data were used to generate the Breast Cancer Surveillance Consortium version 3 (BCSCv3) clinical risk score. Genome-wide genotypes were used to compute the 313-SNP polygenic risk score, adjusted for genetic ancestry (PRS313adj). Risks of breast cancer (invasive or ductal carcinoma in situ) at 0 to 10 years after the mammogram were estimated using Cox models, with 5-fold cross-validation used to estimate the C-index. During 10 years of follow-up, 2471 women developed breast cancer. The C-index (95% CI) for the combined model with all 3 risk scores (0.70; 95% CI = 0.69 to 0.71) was significantly higher than for univariate models with only the BCSCv3 (0.62; 95% CI = 0.61 to 0.63), PRS313adj (0.61; 95% CI = 0.60 to 0.62), or Mirai (0.66; 95% CI = 0.65 to 0.67) risk score. Integrating mammographic AI and polygenic risk scores with clinical risk models significantly improved breast cancer risk discrimination, supporting use of combined models for personalized screening and prevention.

Electric field tumor therapy has emerged as a promising non-invasive treatment for glioblastoma (GBM), but its clinical efficacy is severely limited by skull-induced attenuation of electric field intensity. To overcome this limitation, we developed a multilayer thin-film sonoelectric meningeal device (MF-SMD) consisting of an electrospun PLGA artificial meningeal scaffold integrated with a microneedle-based triboelectric film. This device converts externally applied low-intensity ultrasound into intracranial electric fields, enabling transcranial, localized, and controllable electric ablation of brain tumors. Upon low-intensity ultrasound excitation, the film generates localized intracranial electric fields that disrupt tumor mitosis while preserving neuronal integrity, and significantly reduce skull-induced field attenuation. In vitro and in vivo experiments validated the antitumor efficacy of the device, achieving approximately 68% proliferation inhibition in clinical GBM cell lines and a 72% reduction in tumor burden in orthotopic mouse models. Notably, compared with conventional tumor treating fields (TTF) systems that employ extracranial electrodes, the MF-SMD maintained electric field attenuation below 20% at therapeutic frequencies. These results establish a novel therapeutic paradigm that overcomes skull-induced electric field attenuation, addressing a key challenge in transcranial brain tumor therapy.

This study involves an integrated approach to predict the mechanical properties of luffa fiber and marble dust- based concrete. It employs Artificial Neural Network (ANN) for mechanical properties prediction aiming for a higher accuracy than currently available models. The composite material used marble dust in the proportion 0-40% as fine aggregate replacement and luffa fiber in the proportion 0-2% as the natural reinforcement. Experimental results implied that the composite containing 20% marble dust and 1% luffa fiber exhibited greatest mechanical characteristics- Compressive strength of 34.5 MPa, flexural strength of 6.2 MPa and split tensile strength of 4.25 MPa. This improvement was attributed to enhanced particle packing by marble dust and effective crack bridging by treated luffa fiber. A single multi-output feedforward multilayer perceptron (MLP) ANN consisting of two hidden layers of 64 and 32 neurons with ReLU activation functions and a three-neuron linear output layer was developed for simultaneously modelling the nonlinear interactions between the input variables and strength outputs. The model was trained on 70% of the dataset, with 15% for validation and 15% for testing. The ANN model was able to predict all three mechanical strength properties simultaneously with a high degree of accuracy as demonstrated by R² values of 0.89 (compressive strength), 0.94 (flexural strength), and 0.96 (split tensile strength) for the training data sets and small root mean square error (RMSE) values and negligible bias. The 100% a20 score indicated that all the samples from the predictions fell within ± 20% of the actual experimental values, demonstrating good robustness or generality. This research basically aims to address a major gap in the existing works by exploring the limited application of ANN in predicting the performance of hybrid sustainable concrete mixes incorporating both marble dust and plant-based fibers by developing a predictive model which is capable of capturing the complex interactions between multiple factors and enhancing the prediction efficiency, minimizing the dependency on extensive experimental investigations thereby promoting data driven evaluation of strength characteristics in sustainable concrete composites.

Maternal and neonatal health (MNH) urgently requires precision medicine interventions, as morbidity, mortality, and health disparities hinder the achievement of Sustainable Development Goal 3. Clinical implementation of artificial intelligence (AI)-powered Pharmacogenomics (PGx) requires validated, transparent algorithms and frameworks. The "pregnancy black box"-which refers to a data void due to historical exclusion of pregnant and postpartum women from clinical trials-continues to create bias in AI models. The review establishes a path for upcoming research, including methods to reduce algorithmic bias via AI-driven data augmentation, resolution of ethical challenges, and creation of international registries. Ultimately, leveraging AI for remote monitoring is crucial for enhancing equitable access in lower-resource environments. The proposed roadmap provides organizations with a robust framework to develop AI-driven PGx systems, which will enable safer and more tailored pharmacotherapy for mothers and their newborns.

Artificial light at night (ALAN) disrupts the physiology and behavior of coastal marine animals globally, but the cellular mechanisms underlying these effects remain unclear. We defined sleep in the damselfish Chromis viridis, tracked school dynamics within their coral habitats, and determined the acute and chronic effects of ALAN on behavioral interactions, sleep, and neuronal health under both controlled laboratory and natural reef conditions. We found that ALAN increased territorial occupancy, aggression, and nocturnal feeding while reducing sleep duration and consolidation. These sleep disruptions correlated with increased DNA damage in neurons of the dorsal pallium, a brain region involved in sleep-dependent brain functions. Our findings introduce a model that links ALAN-dependent alterations in sleep with neuronal insults in reef-dwelling tropical fish.

Early risk stratification in patients after acute myocardial infarction (AMI) is critical for guiding therapy and resource allocation. While left ventricular ejection fraction (LVEF) is routinely assessed by echocardiography, novel markers offer additional prognostic utility but are not widely assessed due to time constraints or limited expertise. Artificial intelligence (AI) enables rapid, fully automated analysis of echocardiograms, producing standardized, comprehensive measurements. We evaluated the utility of AI-derived echocardiographic parameters on top of clinical variables in predicting outcomes post-AMI. Consecutive AMI patients undergoing invasive coronary angiogram were included. Echocardiograms were analyzed using Us2.ai software. Independent predictors of one-year all-cause mortality and major adverse cardiac events (MACE) were assessed using Cox regression. Clinical, echocardiographic, and combined models were compared. Among 1001 patients, aged 64&#x202f;years (54, 72) and predominantly male (78.1%), 161 (16.1%) died during follow-up. AI-echocardiographic markers independently associated with one-year all-cause mortality or MACE included lower LVEF, greater LV wall thickness, lower LV mass, greater LA area, lower LA reservoir strain and lower aortic valve area. For one-year mortality, the combined model demonstrated superior discrimination compared with the clinical model alone (AUC 0.85 vs. 0.81; p&#x202f;=&#x202f;0.018). Similarly, for one-year MACE, the combined model showed improved discrimination compared with the clinical model (AUC 0.80 vs. 0.74; p&#x202f;<&#x202f;0.001) and yielded the lowest Akaike's and Bayesian Informations. Combining AI-derived echocardiographic parameters, together with traditional clinical risk factors, provides incremental prognostic value post-AMI. AI tools that automate complex assessments accurately and reproducibly may enhance risk stratification.

Mental health disorders are highly prevalent worldwide, yet access to timely and effective mental health assessment (and care) remains limited. Artificial intelligence (AI) offers potential solutions, but the literature on its use in psychological assessment contexts has not been comprehensively mapped. This review aimed to systematise existing research, identify gaps, evaluate methodological limitations, and outline future directions. Using a librarian-approved search strategy, 7595 records were retrieved from major databases and screened independently by two coders. Following the eligibility assessment, 320 peer-reviewed articles were included. Studies showed wide variability in sample sizes (1-19,400,000) with no clear temporal trend. Most recruited clinical (21%) or general population (16%) samples from China (24%) or the United States (21%), and focused on depression (54%), anxiety (14%), suicidality (12%) or stress (8%). Supervised (75%) and deep learning (47%) approaches predominated, often with multiple algorithms compared (77% of the studies). Validation commonly relied on cross-validation and convergence with screening instruments, with relatively little use of DSM or ICD diagnostic criteria (71% used neither). Area-Under-the-Receiver-Operating-Characteristics-Curve (AUC) was the most frequently used performance metric, and unsupervised models achieved the highest average AUC. A marginal improvement in performance was evident from 2014 to 2025. Overall, AI shows promise as a psychological assessment tool, but progress is constrained by limited transparency, heavy reliance on self-report data, inconsistent use of validated diagnostic standards, a narrow focus on outcomes, and insufficient demographic and cultural analyses. Future research should prioritise interpretability, ethical and cultural responsiveness, multi-modal data, diverse samples, and clinically meaningful validation.

To present the diagnosis and management of a patient with an iatrogenic urethrovaginal fistula and the subsequent management of stress urinary incontinence (SUI) secondary to intrinsic sphincter deficiency (ISD) through laparoscopic artificial urinary sphincter (AUS) implantation. Secondary care center specialized in minimally invasive reconstructive urogynecology. A 69-year-old woman with an iatrogenic urethrovaginal fistula following transobturator suburethral sling failed surgery for SUI, who subsequently developed ISD after fistula repair. Diagnostic confirmation of the urethrovaginal fistula and surgical repair via excision, urethrorrhaphy, and interposition of a right bulbocavernosus Martius flap through a submucosal tunnel for suburethral positioning prior to colporrhaphy.

暂无摘要（点击查看详情）

暂无摘要（点击查看详情）

暂无摘要（点击查看详情）