Browsing by Author "Chien, Yin-Hsiu"

Now showing 1 - 10 of 10

A Multi Model Voting Enhancement for Newborn Screening Healthcare Information System
(2009)
Hsieh, Sung-Huai
;
Cheng, Po-Hsun
;
Hsieh, Sheau-Ling
;
Chen, Po-Hao
;
Weng, Yung-Ching
The clinical symptoms of metabolic disorders during neonatal period are often not apparent. If not treated early, irreversible damages such as mental retardation may occur, even death. Therefore, practicing newborn screening is essential, imperative to prevent neonatal from these damages. In the paper, we establish a newborn screening model that utilizes Support Vector Machines (SVM) techniques and enhancements to evaluate, interpret the Methylmalonic Acidemia (MMA) metabolic disorders. The model encompasses the Feature Selections, Grid Search, Cross Validations as well as multi model Voting Mechanism. In the model, the predicting accuracy, sensitivity and specificity of MMA can be improved dramatically. The model will be able to apply to other metabolic diseases as well.
Computational analysis of a novel mutation in ETFDH gene highlights its long-range effects on the FAD-binding motif
(2011-10-21)
Er, Tze-Kiong
;
Chen, Chih-Chieh
;
Liu, Yen-Yi
;
Chang, Hui-Chiu
;
Chien, Yin-Hsiu
Background: Multiple acyl-coenzyme A dehydrogenase deficiency (MADD) is an autosomal recessive disease caused by the defects in the mitochondrial electron transfer system and the metabolism of fatty acids. Recently, mutations in electron transfer flavoprotein dehydrogenase (ETFDH) gene, encoding electron transfer flavoprotein: ubiquinone oxidoreductase (ETF:QO) have been reported to be the major causes of riboflavin-responsive MADD. To date, no studies have been performed to explore the functional impact of these mutations or their mechanism of disrupting enzyme activity. Results: High resolution melting (HRM) analysis and sequencing of the entire ETFDH gene revealed a novel mutation (p.Phe128Ser) and the hotspot mutation (p.Ala84Thr) from a patient with MADD. According to the predicted 3D structure of ETF: QO, the two mutations are located within the flavin adenine dinucleotide (FAD) binding domain; however, the two residues do not have direct interactions with the FAD ligand. Using molecular dynamics (MD) simulations and normal mode analysis (NMA), we found that the p. Ala84Thr and p.Phe128Ser mutations are most likely to alter the protein structure near the FAD binding site as well as disrupt the stability of the FAD binding required for the activation of ETF: QO. Intriguingly, NMA revealed that several reported disease-causing mutations in the ETF: QO protein show highly correlated motions with the FAD-binding site. Conclusions: Based on the present findings, we conclude that the changes made to the amino acids in ETF: QO are likely to influence the FAD-binding stability.
Critical Trio Exome Benefits In-Time Decision-Making for Pediatric Patients With Severe Illnesses*
(2019-11-01)
Wu, En-Ting
;
Hwu, Wuh-Liang
;
Chien, Yin-Hsiu
;
Hsu, Ching
;
Chen, Ting-Fu
Objectives: Critical illnesses caused by undiagnosed genetic conditions are challenging in PICUs. Whole-exome sequencing is a powerful diagnostic tool but usually costly and often fail to arrive at a final diagnosis in a short period. We assessed the feasibility of our whole-exome sequencing as a tool to improve the efficacy of rare diseases diagnosis for pediatric patients with severe illness. Design: Observational analysis. Method: We employed a fast but standard whole-exome sequencing platform together with text mining-assisted variant prioritization in PICU setting over a 1-year period. Setting: A tertiary referral Children's Hospital in Taiwan. Patients: Critically ill PICU patients suspected of having a genetic disease and newborns who were suspected of having a serious genetic disease after newborn screening were enrolled. Interventions: None. Measurements and Main Results: Around 50,000 to 100,000 variants were obtained for each of the 40 patients in 5 days after blood sampling. Eleven patients were immediately found be affected by previously reported mutations after searching mutation databases. Another seven patients had a diagnosis among the top five in a list ranked by text mining. As a whole, 21 patients (52.5%) obtained a diagnosis in 6.2 +/- 1.1 working days (range, 4.3-9 d). Most of the diagnoses were first recognized in Taiwan. Specific medications were recommended for 10 patients (10/21, 47.6%), transplantation was advised for five, and hospice care was suggested for two patients. Overall, clinical management was altered in time for 81.0% of patients who had a molecular diagnosis. Conclusions: The current whole-exome sequencing algorithm, balanced in cost and speed, uncovers genetic conditions in infants and children in PICU, which helps their managements in time and promotes better utilization of PICU resources.
Development of a feasible assay for the detection of GAA mutations in patients with Pompe disease
(2014-02-15)
Er, Tze-Kiong
;
Chen, Chih-Chieh
;
Chien, Yin-Hsiu
;
Liang, Wen-Chen
;
Kan, Tzu-Min
Background: Pompe disease is an inherited autosomal recessive deficiency of acid alpha-glucosidase (GAA) and is due to pathogenic sequence variants in the corresponding GM gene. While the analysis of enzyme activity remains the diagnostic test of choice for individuals with Pompe disease, mutation analysis remains for establishing a definitive diagnosis. Methods: High resolution melting (HRM) analysis was performed to screen GM mutations. Genomic DNA was extracted from peripheral blood samples of the two patients with Pompe disease and 250 normal controls. Exons 2 through 20 of the GM gene were screened by the HEM analysis. The results were subsequently confirmed by direct sequencing. Results: This assay proved to be feasible in detecting seven known (c2T>C, c.1726G>A, c.1845G>A, c.1935C>A, c.1958C>A, c.2238G>C, and c2815_2816del) GM mutations. Each mutation could be readily and accurately identified in the difference plot curves. We estimated the carrier frequency of the most common mutation, c.1935G>A (p.D645E), in the Taiwanese population to be 02%. Conclusions: In clinical practice, we suggest that HEM analysis is assumed as a fast and reliable method for screening GM gene mutations especially the most common mutations which are responsible for Pompe disease among the Taiwanese populations. (C) 2013 Elsevier B.V. All rights reserved.
Earlier and higher dosing of alglucosidase alfa improve outcomes in patients with infantile -onset Pompe disease: Evidence from real -world experiences
(2020-06-01)
Chien, Yin-Hsiu
;
Tsai, Wen-Hui
;
Chang, Chaw-Liang
;
Chiu, Pao-Chin
;
Chou, Yen-Yin
Newborn Screening for Phenylketonuria: Machine Learning vs Clinicians
(2012)
Chen, Wei-Hsin
;
Chen, Han-Ping
;
Tseng, Yi-Ju
;
Hsu, Kai-Ping
;
Hsieh, Sheau-Ling
The metabolic disorders may hinder an infant\'s normal physical or mental development during the neonatal period. The metabolic diseases can be treated by effective therapies if the diseases are discovered in the early stages. Therefore, newborn screening program is essential to prevent neonatal from these damages. In the paper, a support vector machine (SVM) based algorithm is introduced in place of cut-off value decision to evaluate the analyte elevation raw data associated with Phenylketonuria. The data were obtained from tandem mass spectrometry (MS/MS) for newborns. In addition, a combined feature selection mechanism is proposed to compare with the cut-off scheme. By adapting the mechanism, the number of suspected cases is reduced substantially; it also handles the medical resources effectively and efficiently.
Newborn Screening Healthcare Information System Based on Service-Oriented Architecture
(2010-08-01)
Hsieh, Sung-Huai
;
Hsieh, Sheau-Ling
;
Chien, Yin-Hsiu
;
Weng, Yung-Ching
;
Hsu, Kai-Ping
In this paper, we established a newborn screening system under the HL7/Web Services frameworks. We rebuilt the NTUH Newborn Screening Laboratory's original standalone architecture, having various heterogeneous systems operating individually, and restructured it into a Service-Oriented Architecture (SOA), distributed platform for further integrity and enhancements of sample collections, testing, diagnoses, evaluations, treatments or follow-up services, screening database management, as well as collaboration, communication among hospitals; decision supports and improving screening accuracy over the Taiwan neonatal systems are also addressed. In addition, the new system not only integrates the newborn screening procedures among phlebotomy clinics, referral hospitals, as well as the newborn screening center in Taiwan, but also introduces new models of screening procedures for the associated, medical practitioners. Furthermore, it reduces the burden of manual operations, especially the reporting services, those were heavily dependent upon previously. The new system can accelerate the whole procedures effectively and efficiently. It improves the accuracy and the reliability of the screening by ensuring the quality control during the processing as well.
Newborn Screening System Based on Adaptive Feature Selection and Support Vector Machines
(2009-01-01)
Hsieh, Sung-Huai
;
Chien, Yin-Hsiu
;
Shen, Chia-Ping
;
Chen, Wei-Hsin
;
Chen, Po-Hao
The clinical symptoms of metabolic disorders during neonatal period are often not apparent, if not treated early irreversible damages such as mental retardation may occur, even death. Therefore, practicing newborn screening is very important to prevent neonatal from these damages. In this paper, the newborn screening system used support vector machines (SVM) classification technique is proposed in place of cut-off value decision to evaluate the metabolic substances concentration raw data obtained from tandem mass spectrometry (MS/MS) and determine whether the newborn has some kinds of metabolic disorder diseases. On the basis of the proposed features, new analytic combinations are identified with superior discriminatory performance compared with the best published combinations. Classifiers built with the feature selection to find C3/C2, C3 and C16 of three key point features achieved diagnostic sensitivities, specificities and accuracy approaching 100%.
Presymptomatic Diagnosis of Spinal Muscular Atrophy Through Newborn Screening
(2017-11-01)
Chien, Yin-Hsiu
;
Chiang, Shu-Chuan
;
Weng, Wen-Chin
;
Lee, Ni-Chung
;
Lin, Ching-Jie
Objective To demonstrate the feasibility of presymptomatic diagnosis of spinal muscular atrophy (SMA) through newborn screening (NBS). Study design We performed a screening trial to assess all newborns who underwent routine newborn metabolic screening at the National Taiwan University Hospital newborn screening center between November 2014 and September 2016. A real-time polymerase chain reaction (RT-PCR) genotyping assay for the SMN1/SMN2 intron 7 c. 888+100A/G polymorphism was performed to detect homozygous SMN1 deletion using dried blood spot (DBS) samples. Then the exon 7 c. 840C>T mutation and SMN2 copy number were determined by both droplet digital PCR (ddPCR) using the original screening DBS and multiplex ligation-dependent probe amplification (MLPA) using a whole blood sample. Results Of the 120 267 newborns, 15 tested positive according to the RT-PCR assay. The DBS ddPCR assay excluded 8 false-positives, and the other 7 patients were confirmed by the MLPA assay. Inclusion of the second-tier DBS ddPCR screening assay resulted in a positive prediction value of 100%. The incidence of SMA was 1 in 17 181 (95% CI, 1 in 8323 to 1 in 35 468). Two of the 3 patients with 2 copies of SMN2 and all 4 patients with 3 or 4 copies of SMN2 were asymptomatic at the time of diagnosis. Five of the 8 false-positives were caused by intragenic recombination between SMN1 and SMN2. Conclusion Newborn screening can detect patients affected by SMA before symptom onset and enable early therapeutic intervention. A combination of a RT-PCR and a second-tier ddPCR can accurately diagnose SMA from DBS samples with no false-positives.
Web-Based Newborn Screening System for Metabolic Diseases: Machine Learning Versus Clinicians
(2013-05-01)
Chen, Wei-Hsin
;
Hsieh, Sheau-Ling
;
Hsu, Kai-Ping
;
Chen, Han-Ping
;
Su, Xing-Yu
Background: A hospital information system (HIS) that integrates screening data and interpretation of the data is routinely requested by hospitals and parents. However, the accuracy of disease classification may be low because of the disease characteristics and the analytes used for classification. Objective: The objective of this study is to describe a system that enhanced the neonatal screening system of the Newborn Screening Center at the National Taiwan University Hospital. The system was designed and deployed according to a service-oriented architecture (SOA) framework under the Web services. NET environment. The system consists of sample collection, testing, diagnosis, evaluation, treatment, and follow-up services among collaborating hospitals. To improve the accuracy of newborn screening, machine learning and optimal feature selection mechanisms were investigated for screening newborns for inborn errors of metabolism. Methods: The framework of the Newborn Screening Hospital Information System (NSHIS) used the embedded Health Level Seven (HL7) standards for data exchanges among heterogeneous platforms integrated by Web services in the C# language. In this study, machine learning classification was used to predict phenylketonuria (PKU), hypermethioninemia, and 3-methylcrotonyl-CoA-carboxylase (3-MCC) deficiency. The classification methods used 347,312 newborn dried blood samples collected at the Center between 2006 and 2011. Of these, 220 newborns had values over the diagnostic cutoffs (positive cases) and 1557 had values that were over the screening cutoffs but did not meet the diagnostic cutoffs (suspected cases). The original 35 analytes and the manifested features were ranked based on F score, then combinations of the top 20 ranked features were selected as input features to support vector machine (SVM) classifiers to obtain optimal feature sets. These feature sets were tested using 5-fold cross-validation and optimal models were generated. The datasets collected in year 2011 were used as predicting cases. Results: The feature selection strategies were implemented and the optimal markers for PKU, hypermethioninemia, and 3-MCC deficiency were obtained. The results of the machine learning approach were compared with the cutoff scheme. The number of the false positive cases were reduced from 21 to 2 for PKU, from 30 to 10 for hypermethioninemia, and 209 to 46 for 3-MCC deficiency. Conclusions: This SOA Web service-based newborn screening system can accelerate screening procedures effectively and efficiently. An SVM learning methodology for PKU, hypermethioninemia, and 3-MCC deficiency metabolic diseases classification, including optimal feature selection strategies, is presented. By adopting the results of this study, the number of suspected cases could be reduced dramatically.