Search

Your search keyword '"Ying Feng Chang"' showing total 2 results
Start Over Author "Ying Feng Chang" Publisher mdpi ag
2 results on '"Ying Feng Chang"'

1. Enhanced Plasmonic Biosensor Utilizing Paired Antibody and Label-Free Fe3O4 Nanoparticles for Highly Sensitive and Selective Detection of Parkinson’s α-Synuclein in Serum

Author

Samuel Husin Surya Mandala, Tai-Jan Liu, Chiung-Mei Chen, Kuo-Kang Liu, Mochamad Januar, Ying-Feng Chang, Chao-Sung Lai, Kuo-Hsuan Chang, and Kou-Chen Liu

Subjects
α-synuclein, Parkinson’s disease, surface plasmon resonance, Fe3O4 nanoparticles, paired antibody, human serum, Biotechnology, TP248.13-248.65
Abstract

Parkinson’s disease (PD) is an acute and progressive neurodegenerative disorder, and diagnosis of the disease at its earliest stage is of paramount importance to improve the life expectancy of patients. α-Synuclein (α-syn) is a potential biomarker for the early diagnosis of PD, and there is a great need to develop a biosensing platform that precisely detects α-syn in human body fluids. Herein, we developed a surface plasmon resonance (SPR) biosensor based on the label-free iron oxide nanoparticles (Fe3O4 NPs) and paired antibody for the highly sensitive and selective detection of α-syn in serum samples. The sensitivity of the SPR platform is enhanced significantly by directly depositing Fe3O4 NPs on the Au surface at a high density to increase the decay length of the evanescent field on the Au film. Moreover, the utilization of rabbit-type monoclonal antibody (α-syn-RmAb) immobilized on Au films allows the SPR platform to have a high affinity-selectivity binding performance compared to mouse-type monoclonal antibodies as a common bioreceptor for capturing α-syn molecules. As a result, the current platform has a detection limit of 5.6 fg/mL, which is 20,000-fold lower than that of commercial ELISA. The improved sensor chip can also be easily regenerated to repeat the α-syn measurement with the same sensitivity. Furthermore, the SPR sensor was applied to the direct analysis of α-syn in serum samples. By using a format of paired α-syn-RmAb, the SPR sensor provides a recovery rate in the range from 94.5% to 104.3% to detect the α-syn in diluted serum samples precisely. This work demonstrates a highly sensitive and selective quantification approach to detect α-syn in human biofluids and paves the way for the future development in the early diagnosis of PD.

Published
2021
Full Text
View/download PDF

2. Machine Learning Approaches to Predict In-Hospital Mortality among Neonates with Clinically Suspected Sepsis in the Neonatal Intensive Care Unit

Author

Chun Yuan Lin, Jen-Fu Hsu, Chi Yang, Hui Jun Cheng, Shih-Ming Chu, Hsuan Rong Huang, Ming-Horng Tsai, Ming-Chou Chiang, Hsiao Chin Wang, and Ying Feng Chang

Subjects
Neonatal intensive care unit, neonatal mortality, Medicine (miscellaneous), Machine learning, computer.software_genre, Article, Sepsis, 03 medical and health sciences, 0302 clinical medicine, Cohen's kappa, 030225 pediatrics, medicine, Intravascular volume status, 030212 general & internal medicine, early prediction, In hospital mortality, Receiver operating characteristic, business.industry, medicine.disease, artificial intelligence, Confidence interval, machine learning, big data analysis, Cohort, Medicine, Artificial intelligence, business, computer
Abstract

Background: preterm and critically ill neonates often experience clinically suspected sepsis during their prolonged hospitalization in the neonatal intensive care unit (NICU), which can be the initial sign of final adverse outcomes. Therefore, we aimed to utilize machine learning approaches to predict neonatal in-hospital mortality through data-driven learning. Methods: a total of 1095 neonates who experienced clinically suspected sepsis in a tertiary-level NICU in Taiwan between August 2017 and July 2020 were enrolled. Clinically suspected sepsis was defined based on clinical features and laboratory criteria and the administration of empiric antibiotics by clinicians. The variables used for analysis included patient demographics, clinical features, laboratory data, and medications. The machine learning methods used included deep neural network (DNN), k-nearest neighbors, support vector machine, random forest, and extreme gradient boost. The performance of these models was evaluated using the area under the receiver operating characteristic curve (AUC). Results: the final in-hospital mortality of this cohort was 8.2% (90 neonates died). A total of 765 (69.8%) and 330 (30.2%) patients were randomly assigned to the training and test sets, respectively. Regarding the efficacy of the single model that most accurately predicted the outcome, DNN exhibited the greatest AUC (0.923, 95% confidence interval [CI] 0.953–0.893) and the best accuracy (95.64%, 95% CI 96.76–94.52%), Cohen’s kappa coefficient value (0.74, 95% CI 0.79–0.69) and Matthews correlation coefficient value (0.75, 95% CI 0.80–0.70). The top three most influential variables in the DNN importance matrix plot were the requirement of ventilator support at the onset of suspected sepsis, the feeding conditions, and intravascular volume expansion. The model performance was indistinguishable between the training and test sets. Conclusions: the DNN model was successfully established to predict in-hospital mortality in neonates with clinically suspected sepsis, and the machine learning algorithm is applicable for clinicians to gain insights and have better communication with families in advance.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results