A5085167653- Advanced Causal Inference Techniques
- Health Systems, Economic Evaluations, Quality of Life
- Machine Learning in Healthcare
- Laser-induced spectroscopy and plasma
- Statistical Methods and Inference
- Statistical Methods in Clinical Trials
- Healthcare Policy and Management
- Cultural Heritage Materials Analysis
- Electronic Health Records Systems
- Analytical chemistry methods development
- Diabetic Foot Ulcer Assessment and Management
- Ethics in Clinical Research
- Urban Heat Island Mitigation
- Advanced Computational Techniques and Applications
- Statistical Methods and Bayesian Inference
- Microstructure and mechanical properties
- Traumatic Brain Injury and Neurovascular Disturbances
- Identification and Quantification in Food
- Critical Theory and Philosophy
- Environmental Quality and Pollution
- Ideological and Political Education
- Liver Disease Diagnosis and Treatment
- Meta-analysis and systematic reviews
- Pressure Ulcer Prevention and Management
- Chronic Kidney Disease and Diabetes
Washington University in St. Louis
2024-2025
Columbia University
2020-2024
Columbia University Irving Medical Center
2020-2024
Xidian University
2023
Institute of Microelectronics
2023
Jiangxi Agricultural University
2019-2021
Kyoto University
2019
Hunan University of Technology
2008-2019
South China Normal University
2006-2018
Harvard University
2017
Importance Semaglutide, a glucagonlike peptide-1 receptor agonist (GLP-1RA), has recently been implicated in cases of nonarteritic anterior ischemic optic neuropathy (NAION), raising safety concerns the treatment type 2 diabetes (T2D). Objective To investigate potential association between semaglutide and NAION Observational Health Data Sciences Informatics (OHDSI) network. Design, Setting, Participants This was retrospective study across 14 databases (6 administrative claims 8 electronic...
AIM:To compare the influence of different transplant sites in bone marrow mesenchymal stem cell (MSC)based therapy for liver fibrosis. METHODS:MSCs isolated from Sprague Dawley (SD) rats were induced into hepatocyte-like cells.Liver fibrosis SD was with carbon tetrachloride.Following hepatocyte induction vitro , 4',6-diamidino-2-phenylindole (DAPI)-labeled MSCs transplanted by intravenous, intrahepatic, and intraperitoneal injection.Histopathological staining, immunohistochemistry,...
A) To characterize the incidence of kidney failure associated with intravitreal anti-vascular endothelial growth factor (VEGF) exposure, and B) compare risk in patients treated ranibizumab, aflibercept, or bevacizumab. Retrospective cohort study across 12 databases Observational Health Data Sciences Informatics (OHDSI) network. Subjects aged ≥18 years ≥3 monthly anti-VEGF medications for a blinding disease (diabetic retinopathy, diabetic macular edema, exudative age-related degeneration,...
Much attention has been devoted recently to the development of machine learning algorithms with goal improving treatment policies in healthcare. Reinforcement (RL) is a sub-field within that concerned how make sequences decisions so as optimize long-term effects. Already, RL have proposed identify decision-making strategies for mechanical ventilation, sepsis management and schizophrenia. However, before implementing learned by black-box high-stakes clinical decision problems, special care...
Pressure injuries are common and serious complications for hospitalized patients. The pressure injury rate is an important patient safety metric indicator of the quality nursing care. Timely accurate prediction risk can significantly facilitate early prevention treatment avoid adverse outcomes. While many assessment tools exist, most were developed before there was access to large clinical datasets advanced statistical methods, limiting their accuracy. In this paper, we describe development...
Confounding remains one of the major challenges to causal inference with observational data. This problem is paramount in medicine, where we would like answer questions from large datasets electronic health records (EHRs) and administrative claims. Modern medical data typically contain tens thousands covariates. Such a set carries hope that many confounders are directly measured, further others indirectly measured through their correlation How can exploit these sets covariates for inference?...
Abstract Background While many falls are preventable, they remain a leading cause of injury and death in older adults. Primary care clinics largely rely on screening questionnaires to identify people at risk falls. Limitations standard fall include suboptimal accuracy, missing data, non‐standard formats, which hinder early identification prevention injury. We used machine learning methods develop evaluate electronic health record (EHR)‐based tools adults fall‐related injuries primary...
Abstract Objective Observational studies can impact patient care but must be robust and reproducible. Nonreproducibility is primarily caused by unclear reporting of design choices analytic procedures. This study aimed to: (1) assess how the logic described in an observational could interpreted independent researchers (2) quantify interpretations’ variability on characteristics. Materials Methods Nine teams highly qualified reproduced a cohort from Albogami et al. The were provided clinical...
The coronavirus disease 2019 (COVID-19) is a resource-intensive global pandemic. It important for healthcare systems to identify high-risk COVID-19-positive patients who need timely health care. This study was conducted predict the hospitalization of older adults have tested positive COVID-19.We screened all with COVID test records from 11 Mass General Brigham hospitals population. A total 1495 age 65 and above outpatient setting were included in final cohort, among which 459 hospitalized....
The PSO-SVM method shown here, for the analysis of LIBS spectral data, provides much better fitting results and prediction accuracy than siPLS MLP-ANN models quantitative heavy metal content in pork.
Laser-induced breakdown spectroscopy (LIBS) combined with pattern recognition was proposed to discriminate rice species. LIBS spectra in the range of 210-480 nm wavelength from 11 different species were collected and preprocessed. Principal component analysis applied extract characteristic variables spectral data. Three methods, discriminant analysis, radial basis function neural network, multi-layer perceptron network (MLP) performed compare precision identifying The results showed that...
Synthetic Electronic Health Records (EHR) have emerged as a pivotal tool in advancing healthcare applications and machine learning models, particularly for researchers without direct access to data. Although existing methods, like rule-based approaches generative adversarial networks (GANs), generate synthetic data that resembles real-world EHR data, these methods often use tabular format, disregarding temporal dependencies patient histories limiting replication. Recently, there has been...
Propensity score adjustment addresses confounding by balancing covariates in subject treatment groups through matching, stratification, inverse probability weighting, etc. Diagnostics ensure that the has been effective. A common technique is to check whether standardized mean difference for each relevant covariate less than a threshold like 0.1. For small sample sizes, of falsely rejecting validity study because chance imbalance when no underlying balance exists approaches 1. We propose an...
Healthcare continues to grapple with the persistent issue of treatment disparities, sparking concerns regarding equitable allocation treatments in clinical practice. While various fairness metrics have emerged assess decision-making processes, a growing focus has been on causality-based concepts due their capacity mitigate confounding effects and reason about bias. However, application causal notions evaluating electronic health record (EHR) data remains an understudied domain. This study...
Laser-induced breakdown spectroscopy (LIBS) is a promising alternative to conventional methods in classifying citrus huanglongbing (HLB). Mature fruits with similar features were picked and divided into healthy HLB-asymptomatic groups. LIBS spectra images collected by focusing laser on fresh fruit surfaces without sample preparation. The pH value soluble solids content of juice as the indicators acidity sugar detected, Ca, Zn, K peel pulp was analyzed. characteristic lines from extracted...
Abstract Objective The study sought to explore information needs arising from a gap in clinicians’ knowledge that is not met by current evidence and identify possible areas of use target groups for future clinical decision support system (CDSS), which will guide clinicians cases where no exists. Materials Methods We interviewed 30 physicians large academic medical center, analyzed transcripts using deductive thematic analysis, developed set themes related unmet evidence. conducted additional...
Transistor aging significantly affects digital circuit performance, the development of aging-aware standard cell libraries for reliability analysis is essential. Machine learning-based methods have shown promise in efficient library characterization. However, existing neither investigate unlabeled samples nor consider similarity between timing arcs within cell. In this brief, a semi-supervised transfer learning framework proposed, which leverages and correlated to enhance efficiency...
Knowledge management, especially, tacit knowledge is a significant guarantee for the sustainable development of universities. The transfer college teachers' key and difficult point in management This paper starts from existence application condition China puts forward countermeasures suggestions management.