A5101502114- Biosensors and Analytical Detection
- Hearing, Cochlea, Tinnitus, Genetics
- Microfluidic and Bio-sensing Technologies
- Cryptography and Data Security
- Vestibular and auditory disorders
- Advanced biosensing and bioanalysis techniques
- Ultrasound and Hyperthermia Applications
- Microfluidic and Capillary Electrophoresis Applications
- Photoacoustic and Ultrasonic Imaging
- Cosmology and Gravitation Theories
- Ear Surgery and Otitis Media
- Black Holes and Theoretical Physics
- Advanced Authentication Protocols Security
- Privacy-Preserving Technologies in Data
- Ear and Head Tumors
- Hearing Loss and Rehabilitation
- Cardiovascular Function and Risk Factors
- Ultrasound and Cavitation Phenomena
- ECG Monitoring and Analysis
- Network Security and Intrusion Detection
- Tracheal and airway disorders
- Advanced Biosensing Techniques and Applications
- Geophysics and Gravity Measurements
- Noise Effects and Management
- Ovarian cancer diagnosis and treatment
National Defense Medical Center
2016-2025
Tri-Service General Hospital
2016-2025
Taipei Veterans General Hospital
2024-2025
National Tsing Hua University
2015-2024
National Cheng Kung University
1998-2024
Taipei City Hospital
2024
Wuhan Institute of Technology
2023-2024
National Taiwan University Hospital
2024
National Chiayi University
2013-2023
Mukogawa Women's University
2023
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...
This study reports a new diagnostic assay for the rapid detection of methicillin-resistant Staphylococcus aureus (MRSA) by combing nucleic acid extraction and isothermal amplification target acids in magnetic bead-based microfluidic system. By using specific probe-conjugated beads, deoxyribonucleic (DNA) MRSA can be specifically recognized hybridized onto surface beads which are then mixed with clinical sample lysates. is followed purifying concentrating DNA from lysates applying field....
Abstract Every year cervical cancer affects more than 300,000 people, and on average one woman is diagnosed with every minute. Early diagnosis classification of lesions greatly boosts up the chance successful treatments patients, automated from Papanicolaou (Pap) smear images have become highly demanded. To authors’ best knowledge, this first study fully analysis whole slide (WSIs) conventional Pap samples. The presented deep learning-based system demonstrated to be able detect high grade...
COVID-19 has spread globally. SARS-CoV-2 variants of concern (VOCs) are leading the next waves pandemic.
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...
We devised an innovative method for automated sorting of extracellular vesicles (EVs) employing optically-induced dielectrophoresis on integrated microfluidic chip. EVs three distinct size categories could be isolated in 1 h at a purity 86%.
An integrated microfluidic system was developed to perform the entire SELEX process and positive/negative screening isolate aptamers for InfA/H1N1.
Ovarian cancer (OvCa) is the second most common type of gynecological cancer. More seriously, prognosis for survival relatively poor if an early OvCa diagnosis not achieved. However, it extremely challenging to diagnose very stage OvCa, when treatments are effective, because lack specific and sensitive biomarkers. Therefore, in order achieve detection screening identifying biomarkers with high specificity affinity greatly needed. In this study, integrated microfluidic system capable...
Ovarian cancer is a common malignant gynecological disease. Molecular target therapy, i.e., antiangiogenesis with bevacizumab, was found to be effective in some patients of epithelial ovarian (EOC). Although careful patient selection essential, there are currently no biomarkers available for routine therapeutic usage. To the authors’ best knowledge, this first automated precision oncology framework effectively identify and select EOC peritoneal serous papillary carcinoma (PSPC) positive...
Colorectal cancer (CRC) is the most frequently diagnosed around world, causing about 700,000 deaths every year. It clear now that a small fraction of CRC, named colorectal stem cells (CSCs) exhibiting self-renewal and extensive proliferative activities, are hard to be eradicated. Unfortunately, highly specific biomarkers for CSC (CR-CSCs) lacking prohibits development effective therapeutic strategies. This study designed manufactured novel microfluidic system capable performing fully...
Industry 4.0, smart manufacturing and its related technologies are now becoming the leading trend in development of industry. One key drivers 4.0 is big data analytics, which can transform large amounts into useful information, enabling astute rapid decision-making strategies when combined with expert domain knowledge. The semiconductor industry most important high-tech Taiwan, but it also one energy-consuming industries country. Therefore, critical to improve efficiency process reduce...
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,...
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...