A5084207601- ECG Monitoring and Analysis
- Cardiovascular Function and Risk Factors
- Cardiac Imaging and Diagnostics
- Cardiac electrophysiology and arrhythmias
- Olfactory and Sensory Function Studies
- Medical Coding and Health Information
- Heart Failure Treatment and Management
- Acute Myocardial Infarction Research
- Machine Learning in Healthcare
- Glioma Diagnosis and Treatment
- Biomedical Text Mining and Ontologies
- Bone health and osteoporosis research
- Osteoarthritis Treatment and Mechanisms
- Potassium and Related Disorders
- Advanced Chemical Sensor Technologies
- Meningioma and schwannoma management
- Heart Rate Variability and Autonomic Control
- Hormonal Regulation and Hypertension
- Palliative Care and End-of-Life Issues
- Renin-Angiotensin System Studies
- Chronic Lymphocytic Leukemia Research
- Atrial Fibrillation Management and Outcomes
- Advanced MRI Techniques and Applications
- Biochemical Analysis and Sensing Techniques
- Lymphoma Diagnosis and Treatment
National Defense Medical Center
2016-2025
Tri-Service General Hospital
2018-2025
National Defense Medical College
2020-2024
Fu Jen Catholic University
2024
Institute of Life Sciences
2023
Weatherford College
2020
Cathay General Hospital
2018
Neurological Surgery
2017
London Rebuilding Society
2015
SwissLitho (Switzerland)
2015
Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining anonymity, thus removing many barriers to sharing. Here we 20 institutes across the globe train FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts future oxygen requirements of symptomatic patients COVID-19 using inputs vital signs, laboratory and X-rays. achieved an average area under curve (AUC) >0.92 predicting...
Abstract Editor’s Perspective What We Already Know about This Topic Article Tells Us That Is New Background Previous research has shown different effects of anesthetics on cancer cell growth. Here, the authors investigated association between type anesthetic and patient survival after elective colon surgery. Methods A retrospective cohort study included patients who received surgery January 2005 December 2014. Patients were grouped according to anesthesia received: propofol or desflurane....
Purpose: Our goal was to demonstrate the appearance of phantom tastes and smells (phantageusia phantosmia, respectively) by use functional MRI (fMRI) brain efficacy drug treatment that inhibited both subjective presence these phantoms fMRI activation initiated phantoms. Method: Multislice FLASH MR or echo planar scans were obtained in two patients with phantageusia phantosmia response memory tastants (salt sweet); odors (banana peppermint); actual smell amyl acetate, menthone, pyridine;...
This study investigated the specific preoperative MRI features of patients with intracranial meningiomas that correlate pathological grade and provide appropriate planning.From 2006 to 2012, 120 (36 men 84 women, age range 20-89 years) newly diagnosed symptomatic undergoing resection were retrospectively analyzed in terms radiological MRI. There 90 WHO Grade I 30 II or III meningiomas. The relationships between histopathological scored quantitatively.According results multivariate logistic...
The detection of dyskalemias-hypokalemia and hyperkalemia-currently depends on laboratory tests. Since cardiac tissue is very sensitive to dyskalemia, electrocardiography (ECG) may be able uncover clinically important dyskalemias before results.Our study aimed develop a deep-learning model, ECG12Net, detect based ECG presentations evaluate the logic performance this model.Spanning from May 2011 December 2016, 66,321 records with corresponding serum potassium (K+) concentrations were obtained...
Delayed diagnosis or misdiagnosis of acute myocardial infarction (AMI) is not unusual in daily practice. Since a 12-lead electrocardiogram (ECG) crucial for the detection AMI, systematic algorithm to strengthen ECG interpretation may have important implications improving diagnosis.We aimed develop deep learning model (DLM) as diagnostic support tool based on electrocardiogram.This retrospective cohort study included 1,051/697 ECGs from 737/287 coronary angiogram (CAG)-validated STEMI/NSTEMI...
Dyskalemias are common electrolyte disorders associated with high cardiovascular risk. Artificial intelligence (AI)-assisted electrocardiography (ECG) has been evaluated as an early-detection approach for dyskalemia. The aims of this study were to determine the clinical accuracy AI-assisted ECG dyskalemia and prognostic ability on outcomes such all-cause mortality, hospitalizations, ED revisits. This retrospective cohort was done at two hospitals within a health system from May 2019 December...
BackgroundTimely diagnosis of ST-elevation myocardial infarction (STEMI) is crucial for the treatment patients with acute coronary syndrome. Artificial intelligence–enabled electrocardiogram (AI-ECG) has shown potential accurate and timely detection STEMI on 12-lead electrocardiograms (ECGs). However, its impact clinical times unknown.MethodsTo evaluate AI-ECG–assisted to reduce delays STEMI, we conducted an open-label, cluster randomized controlled trial involving 43,234 eligible (mean age,...
Purpose: Our goal was to use functional MRI (fMRI) measure brain activation in response olfactory stimuli. Method: fMRI scans were obtained 17 normal subjects (9 men, 8 women) using multislice FLASH three stimuli (pyridine, menthone, amyl acetate) coronal sections selected from anterior posterior temporal regions. Activation images derived correlation analysis, and ratios of areas activated total calculated. Results: present each section all subjects. Subjective estimation vapor intensity...
Bone weakening can be affected by agents other than bone mineral density (BMD). Increased marrow fat may have a direct link to loss. This pilot study analyzes the relationship between and BMD in subjects with normal structurally weakened vertebrae.Twenty-six underwent both dual-energy X-ray absorptiometry proton MR spectroscopy of 71 lumbar vertebrae. Fifteen had normal-appearing vertebrae on MRI, 11 signs weakening.We found that high did not consistently equate low BMD. indicate nearly as...
Military personnel have greater psychological stress and are at higher suicide attempt risk compared with the general population. High mental may cause ideations which crucially driving attempts. However, traditional statistical methods could only find a moderate degree of correlation between ideation in non-psychiatric individuals. This article utilizes machine learning techniques including logistic regression, decision tree, random forest, gradient boosting regression support vector...
Bone marrow aspiration and biopsy remain the gold standard for diagnosis of hematological diseases despite development flow cytometry (FCM) molecular gene analyses. However, interpretation results is laborious operator dependent. Furthermore, obtained exhibit inter- intravariations among specialists. Therefore, it important to develop a more objective automated analysis system. Several deep learning models have been developed applied in medical image but not field histology, especially bone...
Abstract ‘Federated Learning’ (FL) is a method to train Artificial Intelligence (AI) models with data from multiple sources while maintaining anonymity of the thus removing many barriers sharing. During SARS-COV-2 pandemic, 20 institutes collaborated on healthcare FL study predict future oxygen requirements infected patients using inputs vital signs, laboratory data, and chest x-rays, constituting “EXAM” (EMR CXR AI Model) model. EXAM achieved an average Area Under Curve (AUC) over 0.92,...
BACKGROUND: The ejection fraction (EF) provides critical information about heart failure (HF) and its management. Electrocardiography (ECG) is a noninvasive screening tool for cardiac electrophysiological activities that has been used to detect patients with low EF based on deep learning model (DLM) trained via large amounts of data. However, no studies have widely investigated clinical impacts. OBJECTIVE: This study developed DLM estimate ECG (ECG-EF). We further the relationship between...
The electrocardiogram (ECG) may be the most popular test in management of cardiovascular disease (CVD). Although wide applications artificial intelligence (AI)-enabled ECG have been developed, an integrating indicator for CVD risk stratification was not investigated. Since mortality important global outcome, this study aimed to develop a survival deep learning model (DLM) establish critical value and explore associations with various events.We trained DLM 451,950 12-lead resting ECGs...
Background Diagnosing osteoporosis is challenging due to its often asymptomatic presentation, which highlights the importance of providing screening for high-risk populations. Purpose To evaluate effectiveness dual-energy x-ray absorptiometry (DXA) in patients with identified by an artificial intelligence (AI) model using chest radiographs. Materials and Methods This randomized controlled trial conducted at academic medical center included participants 40 years age or older who had undergone...
DNA methylation is associated with cancer, metabolic, neurological, and autoimmune disorders. Hypomethylation of aryl hydrocarbon receptor repressor (AHRR) especially at cg05575921 smoking lung cancer. Studies on the association between AHRR sources polycyclic aromatic (PAH) other than are limited. The aim our study was to assess pattern blood in non-smoking Taiwanese adults living areas different PM2.5 levels. Data methylation, smoking, residence were retrieved from Taiwan Biobank dataset...
Although digoxin is important in heart rate control, the utilization of declining due to its narrow therapeutic window. Misdiagnosis or delayed diagnosis toxicity common lack awareness and time-consuming laboratory work that involved. Electrocardiography (ECG) may be able detect potential based on characteristic presentations. Our study attempted develop a deep learning model ECG manifestations. This included 61 ECGs from patients with 177,066 emergency room November 2011 February 2019. The...
Background: glycated hemoglobin (HbA1c) provides information on diabetes mellitus (DM) management. Electrocardiography (ECG) is a noninvasive test of cardiac activity that has been determined to be related DM and its complications. This study developed deep learning model (DLM) estimate HbA1c via ECG. Methods: there were 104,823 ECGs with corresponding or fasting glucose which utilized train DLM for calculating ECG-HbA1c. Next, 1539 cases from outpatient departments health examination...
Hyperkalemia can be detected by point-of-care (POC) blood testing and artificial intelligence- enabled electrocardiography (ECG). These 2 methods of detecting hyperkalemia have not been compared.