Juan Li

Intelligent Automation & Soft Computing, Vol.25, No.1, pp. 35-48, 2019, DOI:10.31209/2018.100000003

Abstract K-Nearest Neighbor algorithm (KNN) is a simple and mature classification method. However there are susceptible factors influencing the classification performance, such as k value determination, the overlarge search space, unbalanced and multi-class patterns, etc. To deal with the above problems, a new classification algorithm that absorbs tree structure, tree pruning and adaptive k value method was proposed. The proposed algorithm can overcome the shortcoming of KNN, improve the performance of multi-class and unbalanced classification, reduce the scale of dataset maintaining the comparable classification accuracy. The simulations are conducted and the proposed algorithm is compared with several existing More >

Dana Y. Fuhrman^1,2, Lan Nguyen³, Morgan Hindes³, John A. Kellum²

Congenital Heart Disease, Vol.14, No.6, pp. 963-967, 2019, DOI:10.1111/chd.12862

Abstract Background: There are significant implications for kidney disease in young adults with congenital heart disease. Prior investigations have not focused on the use of urinary tubular biomarkers for the early identification of kidney disease in this growing patient group.
Objective: Determine if young adults with congenital heart disease have differences in the baseline concentration of urinary tubular biomarkers when compared to healthy young adults.
Design/Methods: In a pilot case control study, 30 patients from 18 to 35 years of age with congenital heart disease and a normal serum creatinine were recruited during a routine follow-up visit. In the… More >

Alessandro Sgrò¹, Thomas M. Drake², Pedro Lopez‐Ayala³, Kevin Phan⁴

Congenital Heart Disease, Vol.14, No.6, pp. 1102-1112, 2019, DOI:10.1111/chd.12855

Abstract Background: Left cardiac sympathetic denervation (LCSD) has been proposed as useful therapy for long QT syndrome (LQTS) and catecholaminergic polymorphic ventricular tachycardia (CPVT), in addition to anti‐arrhythmic agents and implant‐ able cardioverter defibrillators. This study aimed to assess the current evidence for LCSD and compare the open vs the video‐assisted thoracoscopic surgery (VATS) approaches.
Methods: MEDLINE, Embase and Cochrane library databases were searched up to December 2018 for studies reporting the long‐term outcomes of LCSD in LQTS, CPVT patients. The incidence of cardiac events (CEs) before and after surgery, the change in QTc interval, and surgical complications… More >

Daniel McLennan, Dunbar Ivy, Gareth J. Morgan

Congenital Heart Disease, Vol.14, No.5, pp. 819-831, 2019, DOI:10.1111/chd.12816

Abstract Aims: To evaluate in domestic pigs the histopathological processes after implanting the Occlutech Atrial Flow Regulator (AFR).
Methods and Results: Eleven pigs were chosen and had successful implantation of the AFR. Five pigs were sacrificed at 28 days, and 5 pigs at 90 days. One pig was sacrificed at day 3 after device embolization. Each pig had echocardiography performed at 3 weeks to check patency. Post mortem evaluation included Gross evaluation, radiographic evaluation, histology, and electron microscopy. Nine of the 10 devices implanted remained patent at time of autopsy with no thrombus and minimal inflammation. One device More >

Anudeep K. Dodeja¹, Courtney Thomas¹, Curt J. Daniels^1,2, Naomi Kertesz^1,2, Anna Kamp^1,2

Congenital Heart Disease, Vol.14, No.5, pp. 745-751, 2019, DOI:10.1111/chd.12815

Abstract Background: Rhythm disorders are the leading cause of morbidity and mortality in adults with congenital heart disease (ACHD). Infrequent or asymptomatic arrhyth‐ mias may not be detected by routine monitoring. Implantable loop recorders (ILRs), such as the Reveal LINQ^TM, have been useful in long‐term monitoring for arrhythmias in adults with cryptogenic stroke.
Objective: We propose the Reveal LINQ^TM will detect arrhythmias, not documented by other monitoring modalities, resulting in change in management in ACHD patients.
Methods: This is a single center retrospective review of Reveal LINQ^TM use in ACHD patients from 2014‐2017. Medical records were reviewed to determine cardiac… More >

Jan Hinnerk Hansen¹, Lydia Kissner¹, Jana Logoteta¹, Olaf Jung¹, Peter Dütschke², Tim Attmann³, Jens Scheewe³, Hans‐Heiner Kramer^1,4

Congenital Heart Disease, Vol.14, No.3, pp. 427-437, 2019, DOI:10.1111/chd.12741

Abstract Objectives: Neonates and infants undergoing surgery for congenital heart disease are at risk for developmental impairment. Hypoxic‐ischemic brain injury might be one contributing factor. We aimed to investigate the perioperative release of the astro‐ cyte protein S100B and its relation to cerebral oxygenation.
Methods: Serum S100B was measured before and 0, 12, 24, and 48 hours after sur‐ gery. Cerebral oxygen saturation was derived by near‐infrared spectroscopy. S100B reference values based on preoperative samples; concentrations above the 75th per‐ centile were defined as elevated. Patients with elevated S100B at 24 or 48 hours were compared to cases… More >

Karen E. Schultz¹, George K. Lui^1,2, Doff B. McElhinney¹, Jin Long³, Vidhya Balasubramanian³, Charlotte Sakarovitch³, Susan M. Fernandes^1,2, Anne M. Dubin¹, Ian S. Rogers^1,2, Anitra W. Romfh^1,2, Kara S. Motonaga¹, Mohan N. Viswanathan², Scott R. Ceresnak¹

Congenital Heart Disease, Vol.14, No.3, pp. 410-418, 2019, DOI:10.1111/chd.12736

Abstract Background: Arrhythmias are a leading cause of death in adults with congenital heart disease (ACHD). While 24‐48‐hour monitors are often used to assess arrhythmia burden, extended continuous ambulatory rhythm monitors (ECAM) can record 2 weeks of data. The utility of this device and the arrhythmia burden identified beyond 48‐hour monitoring have not been evaluated in the ACHD population. Additionally, the impact of ECAM has not been studied to determine management recommendations.
Objective: To address the preliminary question, we hypothesized that clinically sig‐ nificant arrhythmias would be detected on ECAM beyond 48 hours and this would lead to… More >

Varun Aggarwal¹, Christopher J. Petit², Andrew C. Glatz^3，4, Bryan H. Goldstein⁵, Athar M. Qureshi¹

Congenital Heart Disease, Vol.14, No.1, pp. 110-115, 2019, DOI:10.1111/chd.12709

Abstract The use of prostaglandin‐E1 immediately after birth and subsequent surgical crea‐ tion of the modified Blalock‐Taussig shunt (BTS) shunt have remarkably improved the prognosis and survival of children with congenital heart disease and ductal‐depend‐ ent pulmonary blood flow (PBF). Despite the advancement in surgical techniques, bypass strategies, and postoperative management, significant morbidity and mortal‐ ity after BTS still remain. Patent ductus arteriosus stenting has been shown to be as an acceptable alternative to BTS placement in select infants with ductal‐dependent PBF. Newer procedural techniques and equipment, along with operator experience have all contributed to procedural More >

Yanqiang Sun¹, Hongfang Chen^1,*, Liang Tang¹, Shuang Zhang¹

CMES-Computer Modeling in Engineering & Sciences, Vol.121, No.3, pp. 1011-1028, 2019, DOI:10.32604/cmes.2019.07950

Abstract A gear fault detection analysis method based on Fractional Wavelet Transform (FRWT) and Back Propagation Neural Network (BPNN) is proposed. Taking the changing order as the variable, the optimal order of gear vibration signals is determined by discrete fractional Fourier transform. Under the optimal order, the fractional wavelet transform is applied to eliminate noise from gear vibration signals. In this way, useful components of vibration signals can be successfully separated from background noise. Then, a set of feature vectors obtained by calculating the characteristic parameters for the de-noised signals are used to characterize the gear More >

Sasan Saqaeeyan¹, Hamid Haj Seyyed Javadi^1,2,*, Hossein Amirkhani^1,3

CMES-Computer Modeling in Engineering & Sciences, Vol.121, No.3, pp. 815-834, 2019, DOI:10.32604/cmes.2019.07848

Abstract Anomaly detection in smart homes provides support to enhance the health and safety of people who live alone. Compared to the previous studies done on this topic, less attention has been given to hybrid methods. This paper presents a two-steps hybrid probabilistic anomaly detection model in the smart home. First, it employs various algorithms with different characteristics to detect anomalies from sensory data. Then, it aggregates their results using a Bayesian network. In this Bayesian network, abnormal events are detected through calculating the probability of abnormality given anomaly detection results of base methods. Experimental evaluation More >