A5100714052- Electronic Health Records Systems
- Network Security and Intrusion Detection
- Machine Learning in Healthcare
- Complex Network Analysis Techniques
- Healthcare Systems and Technology
- Biomedical Text Mining and Ontologies
- Advanced Graph Theory Research
- Intensive Care Unit Cognitive Disorders
- Internet Traffic Analysis and Secure E-voting
- Graph theory and applications
- Anomaly Detection Techniques and Applications
- Chronic Disease Management Strategies
- Computational Drug Discovery Methods
- Artificial Intelligence in Healthcare and Education
- Bariatric Surgery and Outcomes
- Wireless Signal Modulation Classification
- Data Quality and Management
- Opinion Dynamics and Social Influence
- Telemedicine and Telehealth Implementation
- Graph Labeling and Dimension Problems
- Neonatal Respiratory Health Research
- Artificial Intelligence in Healthcare
- Neonatal and fetal brain pathology
- Mental Health Research Topics
- Advanced Decision-Making Techniques
Vanderbilt University
2016-2025
Vanderbilt University Medical Center
2018-2025
Air Force Engineering University
2016-2025
Universiti Sains Malaysia
2024
Shanghai Jiao Tong University
2023-2024
Yale University
2023
China-Japan Friendship Hospital
2020-2022
Nankai University
2018-2022
East China Jiaotong University
2022
Jinan University
2021-2022
The potential of artificial intelligence (AI) to reduce health care disparities and inequities is recognized, but it can also exacerbate these issues if not implemented in an equitable manner. This perspective identifies biases each stage the AI life cycle, including data collection, annotation, machine learning model development, evaluation, deployment, operationalization, monitoring, feedback integration. To mitigate biases, we suggest involving a diverse group stakeholders, using...
Large pre-trained language models (PLMs) such as GPT-3 have shown strong in-context learning capabilities, which are highly appealing for domains biomedicine that feature high and diverse demands of technologies but also data annotation costs. In this paper, we present the first systematic comprehensive study to compare few-shot performance with fine-tuning smaller (i.e., BERT-sized) PLMs on two representative biomedical information extraction (IE) tasks: named entity recognition relation...
Computational phenotyping is the process of converting heterogeneous electronic health records (EHRs) into meaningful clinical concepts. Unsupervised methods have potential to leverage a vast amount labeled EHR data for phenotype discovery. However, existing unsupervised do not incorporate current medical knowledge and cannot directly handle missing, or noisy data. We propose Rubik, constrained non-negative tensor factorization completion method phenotyping. Rubik incorporates 1) guidance...
Electronic health record (EHR) log data have shown promise in measuring physician time spent on clinical activities, contributing to deeper understanding and further optimization of the environment. In this article, we propose 7 core measures EHR use that reflect multiple dimensions practice efficiency: total time, work outside work, documentation, prescriptions, inbox teamwork for orders, an aspirational measure amount undivided attention patients receive from their physicians during...
Telehealth is an alternative care delivery model to in-person care. It uses electronic information and telecommunication technologies provide remote clinical patients, especially those living in rural areas that lack sufficient access health services. Like other of affected by the COVID-19 pandemic, prevalence telehealth has increased prenatal This study reports on use at a large academic medical center Middle Tennessee, USA. We examine records over 2500 women characterize 1) volume visits...
Abstract Non-pharmaceutical interventions (NPI) have great potential to improve cognitive function but limited investigation discover NPI repurposing for Alzheimer's Disease (AD). This is the first study develop an innovative framework extract and represent information from biomedical literature in a knowledge graph (KG), train link prediction models repurpose novel NPIs AD prevention. We constructed comprehensive KG, called ADInt, by extracting literature. used previously-created SuppKG...
Collaborative information systems (CISs) are deployed within a diverse array of environments that manage sensitive information. Current security mechanisms detect insider threats, but they ill-suited to monitor in which users function dynamic teams. In this paper, we introduce the community anomaly detection system (CADS), an unsupervised learning framework threats based on access logs collaborative environments. The is observation typical CIS tend form structures subjects accessed (e.g.,...
Collaborative information systems (CIS) are deployed within a diverse array of environments, ranging from the Internet to intelligence agencies healthcare. It is increasingly case that such applied manage sensitive information, making them targets for malicious insiders. While sophisticated security mechanisms have been developed detect insider threats in various file systems, they neither designed model nor monitor collaborative environments which users function dynamic teams with complex...
Abstract Context Metabolic surgery remains the most effective and durable treatment for severe obesity related metabolic diseases. Objective We examined cardiometabolic improvements after associated presurgery demographic clinical factors in a large multiracial cohort. Methods Included were 7804 patients (20-79 years) undergoing first-time at Vanderbilt University Medical Center from 1999 to 2022. Pre- 1-year postsurgery profiles extracted medical records, including body mass index (BMI),...
Weight loss response after bariatric surgery is highly variable, and several demographic factors are associated with differential responses to surgery. Preclinical studies demonstrate numerous sex-specific surgery, but whether these also operation dependent unknown.
Specific emitter identification is a technique that distinguishes different emitters using radio fingerprints. Feature extraction and classifier selection are critical factors affecting SEI performance. In this paper, we propose an method the Bispectrum-Radon transform (BRT) hybrid deep model. We BRT to characterize unintentional modulation of pulses due superiority bispectrum distributions in characterizing nonlinear features signals. then apply model based on denoising autoencoders belief...
Influential nodes identification in complex networks is vital for understanding and controlling the propagation process networks. Some existing centrality measures ignore impacts of neighbor node. It well-known that degree a famous measure influential identification, contributions neighbors also should be taken into consideration. Furthermore, topological connections among will affect nodes' spreading ability, is, denser neighbors, greater chance infection. In this paper, we propose novel...
Abstract Aim The purpose of this study is to assess the associations between periodontal disease, tooth loss and liver diseases. Materials methods PubMed Embase databases were utilized search eligible studies. Odds ratio (OR) with 95% confidence interval (CI) was used as effect size diseases risk. Results Our results indicated positive disease non‐alcoholic fatty (NAFLD) (OR = 1.19, CI 1.06–1.33), cirrhosis 2.28, 1.50–3.48) elevated transaminase level risk 1.08, 1.02–1.15). Moreover, could...
Importance US health professionals devote a large amount of effort to engaging with patients’ electronic records (EHRs) deliver care. It is unknown whether patients different racial and ethnic backgrounds receive equal EHR engagement. Objective To investigate there are differences in the level professionals’ engagement for hospitalized according race or ethnicity during inpatient Design, Setting, Participants This cross-sectional study analyzed access log data from 2 major medical...
Identifying influential nodes in real networks is significant studying and analyzing the structural as well functional aspects of networks. VoteRank a simple effective algorithm to identify high-spreading nodes. The accuracy monotonicity are poor network topology fails be taken into account.Given nodes' attributes neighborhood structure, this paper put forward an based on Edge Weighted (EWV) for identifying network. proposed draws inspiration from human voting behavior expresses...