Dataset Information

Identifying Patients with Atrioventricular Septal Defect in Down Syndrome Populations by Using Self-Normalizing Neural Networks and Feature Selection.

ABSTRACT: Atrioventricular septal defect (AVSD) is a clinically significant subtype of congenital heart disease (CHD) that severely influences the health of babies during birth and is associated with Down syndrome (DS). Thus, exploring the differences in functional genes in DS samples with and without AVSD is a critical way to investigate the complex association between AVSD and DS. In this study, we present a computational method to distinguish DS patients with AVSD from those without AVSD using the newly proposed self-normalizing neural network (SNN). First, each patient was encoded by using the copy number of probes on chromosome 21. The encoded features were ranked by the reliable Monte Carlo feature selection (MCFS) method to obtain a ranked feature list. Based on this feature list, we used a two-stage incremental feature selection to construct two series of feature subsets and applied SNNs to build classifiers to identify optimal features. Results show that 2737 optimal features were obtained, and the corresponding optimal SNN classifier constructed on optimal features yielded a Matthew's correlation coefficient (MCC) value of 0.748. For comparison, random forest was also used to build classifiers and uncover optimal features. This method received an optimal MCC value of 0.582 when top 132 features were utilized. Finally, we analyzed some key features derived from the optimal features in SNNs found in literature support to further reveal their essential roles.

SUBMITTER: Pan X

PROVIDER: S-EPMC5924550 | biostudies-literature | 2018 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identifying Patients with Atrioventricular Septal Defect in Down Syndrome Populations by Using Self-Normalizing Neural Networks and Feature Selection.

Pan Xiaoyong X Hu Xiaohua X Zhang Yu Hang YH Feng Kaiyan K Wang Shao Peng SP Chen Lei L Huang Tao T Cai Yu Dong YD

Genes 20180412 4

Atrioventricular septal defect (AVSD) is a clinically significant subtype of congenital heart disease (CHD) that severely influences the health of babies during birth and is associated with Down syndrome (DS). Thus, exploring the differences in functional genes in DS samples with and without AVSD is a critical way to investigate the complex association between AVSD and DS. In this study, we present a computational method to distinguish DS patients with AVSD from those without AVSD using the newl ...[more]

PMID: 29649131

Similar Datasets

Project description:Background: Left atrioventricular valve (LAVV) stenosis following an atrioventricular septal defect (AVSD) repair is a rare but potentially life-threatening complication. While echocardiographic quantification of diastolic transvalvular pressure gradients is paramount in the evaluation of a newly corrected valve function, it is hypothesized that these measured gradients are overestimated immediately following a cardiopulmonary bypass (CPB) due to the altered hemodynamics when compared to postoperative valve assessments using awake transthoracic echocardiography (TTE) upon recovery after surgery. Methods: Out of the 72 patients screened for inclusion at a tertiary center, 39 patients undergoing an AVSD repair with both intraoperative transesophageal echocardiograms (TEE, performed immediately after a CPB) and an awake TTE (performed prior to hospital discharge) were retrospectively selected. The mean (MPGs) and peak pressure gradients (PPGs) were quantified using a Doppler echocardiography and other measures of interest were recorded (e.g., a non-invasive surrogate of the cardiac output and index (CI), left ventricular ejection fraction, blood pressures and airway pressures). The variables were analyzed using the paired Student’s t-tests and Spearman’s correlation coefficients. Results: The MPGs were significantly higher in the intraoperative measurements when compared to the awake TTE (3.0 ± 1.2 vs. 2.3 ± 1.1 mmHg; p < 0.01); however, the PPGs did not significantly differ (6.6 ± 2.7 vs. 5.7 ± 2.8 mmHg; p = 0.06). Although the assessed intraoperative heart rates (HRs) were also higher (132 ± 17 vs. 114 ± 21 bpm; p < 0.001), there was no correlation found between the MPG and the HR, or any other parameter of interest, at either time-point. In a further analysis, a moderate to strong correlation was observed in the linear relationship between the CI and the MPG (r = 0.60; p < 0.001). During the in-hospital follow-up period, no patients died or required an intervention due to LAVV stenosis. Conclusions: The Doppler-based quantification of diastolic transvalvular LAVV mean pressure gradients using intraoperative transesophageal echocardiography seems to be prone to overestimation due to altered hemodynamics immediately after an AVSD repair. Thus, the current hemodynamic state should be taken into consideration during the intraoperative interpretation of these gradients.

Project description:Due to advances in corrective surgery, congenital heart disease has an ever growing patient population. Atrial arrhythmias are frequently observed pre- and post-surgical correction. Pharmaceutical antiarrhythmic therapy is not always effective, therefore many symptomatic patients undergo catheter ablation therapy. In patients with atrioventricular septal defects (AVSD), ablation therapy itself has mixed success; arrhythmogenic recurrences are common, and because of the anatomical displacement of the atrioventricular node, 3-degree heart block post-ablation is a real concern. In order to develop optimal and safe ablation strategies, the field of congenital cardiac electrophysiology must combine knowledge from clinical electrophysiology with a thorough understanding of the anatomical substrates for arrhythmias. Using image-based analysis and multi-cellular mathematical modeling of electrical activation, we show how the anatomical alterations characteristic of an AVSD serve as arrhythmogenic substrates. Using ex-vivo contrast enhanced micro-computed tomography we imaged post-mortem the heart of a 5 month old male with AVSD at an isometric spatial resolution of 38 ?m. Morphological analysis revealed the 3D disposition of the cardiac conduction system for the first time in an intact heart with this human congenital malformation. We observed displacement of the compact atrioventricular node inferiorly to the ostium of the coronary sinus. Myocyte orientation analysis revealed that the normal arrangement of the major atrial muscle bundles was preserved but was modified in the septal region. Models of electrical activation suggest the disposition of the myocytes within the atrial muscle bundles associated with the "fast pathway," together with the displaced atrioventricular node, serve as potential substrates for re-entry and possibly atrial fibrillation. This study used archived human hearts, showing them to be a valuable resource for the mathematical modeling community, and opening new possibilities for the investigations of arrhythmogenesis and ablation strategies in the congenitally malformed heart.

Dataset Information

Identifying Patients with Atrioventricular Septal Defect in Down Syndrome Populations by Using Self-Normalizing Neural Networks and Feature Selection.

Publications

Identifying Patients with Atrioventricular Septal Defect in Down Syndrome Populations by Using Self-Normalizing Neural Networks and Feature Selection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets