Disease detection on exterior surfaces of buildings using deep learning in China.

Urban infrastructure, particularly in ageing cities, faces significant challenges in maintaining building aesthetics and structural integrity. Traditional methods for detecting diseases on building exteriors, such as manual inspections, are often inefficient, costly, and prone to errors, leading to incomplete assessments and delayed maintenance actions. This study explores the application of advanced deep learning techniques to accurately detect diseases on the exterior surfaces of buildings in urban environments, aiming to enhance detection efficiency and accuracy while providing a real-time monitoring solution that can be widely implemented in infrastructure health management.

Large language models are less effective at clinical prediction tasks than locally trained machine learning models.

Objectives: To determine the extent to which current large language models (LLMs) can serve as substitutes for traditional machine learning (ML) as clinical predictors using data from electronic health records (EHRs), we investigated various factors that can impact their adoption, including overall performance, calibration, fairness, and resilience to privacy protections that reduce data fidelity.

Materials And Methods: We evaluated GPT-3.5, GPT-4, and traditional ML (as gradient-boosting trees) on clinical prediction tasks in EHR data from Vanderbilt University Medical Center (VUMC) and MIMIC IV.

Reduced Risk of Cardiovascular Diseases After Bariatric Surgery Based on the New Predicting Risk of Cardiovascular Disease EVENTs Equations.

Background: We applied the novel Predicting Risk of Cardiovascular Disease EVENTs equations to evaluate cardiovascular-kidney-metabolic (CKM) health and estimated cardiovascular disease (CVD) risk after bariatric surgery.

Methods: Among 7804 patients (aged 20-79 years) undergoing bariatric surgery at Vanderbilt University Medical Center during 1999 to 2022, CVD risk factors from before surgery to 2 years after surgery were extracted from electronic health records. The 10- and 30-year risks of total CVD, atherosclerotic CVD, coronary heart disease, stroke, and heart failure (HF) were estimated for patients without CVD history at each time point (n=124-2910), using the social deprivation index-enhanced Predicting Risk of Cardiovascular Disease EVENTs equations.

Seasonal thermal performance of double and triple glazed windows with effects of window opening area.

Despite significant advancements in building technologies, a critical gap exists in understanding how Solar Heat Gain and the Cooling Effect of Ventilation (CEV) interact in high-rise residential buildings. These two factors, which are crucial for achieving thermal comfort, operate in opposing directions: Solar Heat Gain leads to heat retention and an increase in indoor temperature, while CEV promotes cooling and reduces indoor temperature. This contradiction creates a complex thermal dynamic that is not well-understood, particularly in the context of high-rise bedrooms with varying window configurations.

Development and Validation of Natural Language Processing Algorithms in the ENACT National Electronic Health Record Research Network.

Electronic health record (EHR) data are a rich and invaluable source of real-world clinical information, enabling detailed insights into patient populations, treatment outcomes, and healthcare practices. The availability of large volumes of EHR data are critical for advancing translational research and developing innovative technologies such as artificial intelligence. The Evolve to Next-Gen Accrual to Clinical Trials (ENACT) network, established in 2015 with funding from the National Center for Advancing Translational Sciences (NCATS), aims to accelerate translational research by democratizing access to EHR data for all Clinical and Translational Science Awards (CTSA) hub investigators.

Association of migraine treatments with reduced ischemic stroke risk: Evidence from two large-scale real-world data analyses.

Objective: To compare the risk of ischemic stroke in patients with migraine treated with first-line medications, including valproate, topiramate, metoprolol, timolol, or propranolol, versus those not receiving these treatments, using data from two large electronic health records datasets.

Background: The impact of first-line migraine medications on ischemic stroke risk in patients with migraine remains uncertain, highlighting the need for further investigation.

Methods: We conducted a retrospective case-control study using data from Vanderbilt University Medical Center (VUMC) and the All of Us Research Program.

Research on digital empowerment, innovation vitality and manufacturing supply chain resilience mechanism.

As global manufacturing competition increasingly emphasizes supply chain resilience, enhancing the risk resistance of manufacturing supply chains through digital empowerment has become a critical priority. This study leverages the opportunities of the digital economy to deeply investigate the mechanisms that enhance supply chain resilience. Using data from China' s A-share listed manufacturing companies from 2012 to 2020, a research framework is constructed based on information asymmetry and transaction cost theories.

Bioprinted Fibroblast Mediated Heterogeneous Tumor Microenvironment for Studying Tumor-Stroma Interaction and Drug Screening.

Cancer-associated fibroblasts (CAFs) are crucial stromal cells in the tumor microenvironment, affecting cancer growth, angiogenesis, and matrix remodeling. Developing an effective in vitro tumor model that accurately recapitulates the dynamic interplay between tumor and stromal cells remains a challenge. In this study, a 3D bioprinted fibroblast - mediated heterogeneous breast tumor model was created, with tumor cells and fibroblasts in a bionic matrix.

Bionic Recognition Technologies Inspired by Biological Mechanosensory Systems.

Mechanical information is a medium for perceptual interaction and health monitoring of organisms or intelligent mechanical equipment, including force, vibration, sound, and flow. Researchers are increasingly deploying mechanical information recognition technologies (MIRT) that integrate information acquisition, pre-processing, and processing functions and are expected to enable advanced applications. However, this also poses significant challenges to information acquisition performance and information processing efficiency.

Biomimetic Diselenide-Sonosensitizer Nanoplatform for Enhanced Sonodynamic Therapy and In Situ Remodeling Immunosuppressive Microenvironment via Activating Innate and Adaptive Immunotherapy.

Sonodynamic therapy (SDT), which is non-invasive and controllable has the potential to treat triple-negative breast cancer (TNBC). However, the hypoxia and immunosuppressive tumor microenvironment (TME) often block the production of reactive oxygen species and the induction of SDT-activated immunogenic cell death, thus limiting the activation of adaptive immune responses. To alleviate these challenges, we proposed the development of a multifunctional biomimetic nanoplatform (mTSeIR), which was designed with diselenide-conjugated sonosensitizers and tirapazamine (TPZ), encapsulated within M1 macrophage membrane.

Bioinspired Active Dynamic Dust Remover for Multiscale Stardust Repelling of Unmanned Probe Surface.

Unmanned probes, mainly powered by solar panels, are effective tools for exploiting space resources to expand the human habitat. However, it remains a great challenge for the unmanned probes to actively repel multiscale dust particles in space. Inspired by the synergistic antifouling mechanism of fly wings and legs, a biomimetic dynamic antifouling surface (BDAS) was prepared based on a combination of self-assembly and template inversion.

Exploring PDE5A upregulation in bipolar disorder: insights from single-nucleus RNA sequencing of human basal ganglia.

Basal ganglia is proposed to mediate symptoms underlying bipolar disorder (BD). To understand the cell type-specific gene expression and network changes of BD basal ganglia, we performed single-nucleus RNA sequencing of 30,752 nuclei from caudate, putamen, globus pallidus, and substantia nigra of control human postmortem brain and 24,672 nuclei from BD brain. Differential expression analysis revealed major difference lying in caudate, with BD medium spiny neurons (MSNs) expressing significantly higher PDE5A, a cGMP-specific phosphodiesterase.

Not the Models You Are Looking For: Traditional ML Outperforms LLMs in Clinical Prediction Tasks.

Objectives: To determine the extent to which current Large Language Models (LLMs) can serve as substitutes for traditional machine learning (ML) as clinical predictors using data from electronic health records (EHRs), we investigated various factors that can impact their adoption, including overall performance, calibration, fairness, and resilience to privacy protections that reduce data fidelity.

Materials And Methods: We evaluated GPT-3.5, GPT-4, and ML (as gradient-boosting trees) on clinical prediction tasks in EHR data from Vanderbilt University Medical Center and MIMIC IV.

Association Between Patient Portal Engagement and Weight Loss Outcomes in Patients After Bariatric Surgery: Longitudinal Observational Study Using Electronic Health Records.

Background: Bariatric surgery is an effective intervention for obesity, but comprehensive postoperative self-management is essential for optimal outcomes. While patient portals are generally seen as beneficial in engaging patients in health management, the link between their use and post-bariatric surgery weight loss remains unclear.

Objective: This study aimed to investigate the association between patient portal engagement and postoperative BMI reduction among patients after bariatric surgery.

Evaluation of wastewater percent positive for assessing epidemic trends - A case study of COVID-19 in Shangrao, China.

Objective: This study aims to assess the feasibility of evaluating the COVID-19 epidemic trend through monitoring the positive percentage of SARS-CoV-19 RNA in wastewater.

Method: The study collected data from January to August 2023, including the number of reported cases, the positive ratio of nucleic acid samples in sentinel hospitals, the incidence rate of influenza-like symptoms in students, and the positive ratio of wastewater samples in different counties and districts in Shangrao City. Wastewater samples were obtained through grabbing and laboratory testing was completed within 24 h.

Digital Information Ecosystems in Modern Care Coordination and Patient Care Pathways and the Challenges and Opportunities for AI Solutions.

The integration of digital technologies into health care has significantly enhanced the efficiency and effectiveness of care coordination. Our perspective paper explores the digital information ecosystems in modern care coordination, focusing on the processes of information generation, updating, transmission, and exchange along a patient's care pathway. We identify several challenges within this ecosystem, including interoperability issues, information silos, hard-to-map patient care journeys, increased workload on health care professionals, coordination and communication gaps, and compliance with privacy regulations.

Discovering Severe Adverse Reactions From Pharmacokinetic Drug-Drug Interactions Through Literature Analysis and Electronic Health Record Verification.

While drug-drug interactions (DDIs) and their pharmacokinetic (PK) mechanisms are well-studied prior to drug approval, severe adverse drug reactions (SADRs) caused by DDIs often remain underrecognized due to limitations in pre-marketing clinical trials. To address this gap, our study utilized a literature database, applied natural language processing (NLP) techniques, and conducted multi-source electronic health record (EHR) validation to uncover underrecognized DDI-SADR signals that warrant further investigation. PubMed abstracts related to DDIs from January 1962 to December 2023 were retrieved.

N-doped carbon nanotubes and CoS@NC composites as a multifunctional separator modifier for advanced lithium-sulfur batteries.

Lithium-sulfur batteries (LSBs), with their high theoretical energy density and specific capacity, are considered optimal candidates for next-generation energy storage systems. However, significant challenges remain in their cycle life and efficiency for practical applications, primarily due to the shuttle effect of lithium polysulfides (LiPSs) and the poor electrical conductivity of sulfur materials. The key to addressing these challenges lies in designing materials with excellent dispersion, good electrical conductivity, and high catalytic activity.

Bioinspired Antireflective and Antifogging Surface for Highly Efficient and Stable Inverted Solar Cells.

Photovoltaic devices are essentially solar energy collectors that convert incident photons into charge carriers. However, light reflection losses and external factors (e.g.

Professional identity and its associated psychosocial factors among physicians from standardized residency training programs in China: a national cross-sectional study.

Introduction: Shortage and high turnover intention rate of physicians are concerning problems in China. Professional identity has been shown as an influential factor for physicians' turnover intention. Enhancing physicians' professional identity in their early phase of career, standardized residency training program (SRTP), may help reduce the turnover rate.

Tofacitinib Citrate Coordination-Based Dual-Responsive/Scavenge Nanoplatform Toward Regulate Colonic Inflammatory Microenvironment for Relieving Colitis.

Ulcerative colitis is an inflammation of the colon characterized by immune dysregulation and intestinal inflammation. Developing safe oral nanomedicines that suppress intestinal inflammation, while modulating colonic inflammatory microenvironment by scavenging reactive oxygen species (ROS) and hydrogen sulfide (HS) is crucial for the effective treatment of colitis. Here, the tofacitinib citrate and copper coordination-based nanoparticle (TF-Cu nanoparticle, T-C) to dual-scavenge ROS and HS by coordination competition is synthesized.

Reduced Risk of Cardiovascular Diseases after Bariatric Surgery Based on the New PREVENT Equations.

Background: We applied the novel Predicting Risk of Cardiovascular Disease EVENTs (PREVENT) equations to evaluate cardiovascular-kidney-metabolic (CKM) health and estimated CVD risk, including heart failure (HF), after bariatric surgery.

Methods: Among 7804 patients (20-79 years) undergoing bariatric surgery at Vanderbilt University Medical Center during 1999-2022, CVD risk factors at pre-surgery, 1-year, and 2-year post-surgery were extracted from electronic health records. The 10- and 30-year risks of total CVD, atherosclerotic CVD (ASCVD), coronary heart disease (CHD), stroke, and HF were estimated for patients without a history of CVD or its subtypes at each time point, using the social deprivation index-enhanced PREVENT equations.

The Oncogenic Role of TNFRSF12A in Colorectal Cancer and Pan-Cancer Bioinformatics Analysis.

Purpose: Cancer has become a significant major public health concern, making the discovery of new cancer markers or therapeutic targets exceptionally important. Elevated expression of tumor necrosis factor receptor superfamily member 12A (TNFRSF12A) expression has been observed in certain types of cancer. This project aims to investigate the function of TNFRSF12A in tumors and the underlying mechanisms.