Objective: This study aimed to perform a systematic review to describe the achievements made by the researchers, summarizing findings that have been found by previous researchers in feature extraction and CTG classification, to determine criteria and evaluation methods to the taxonomies of the proposed literature in the CTG field and to distinguish aspects from relevant research in the field of CTG.
Methods: Article search was done systematically using three databases: IEEE Xplore digital library, Science Direct, and Web of Science over a period of 5 years. The literature in the medical sciences and engineering was included in the search selection to provide a broader understanding for researchers.
Results: After screening 372 articles, and based on our protocol of exclusion and inclusion criteria, for the final set of articles, 50 articles were obtained. The research literature taxonomy was divided into four stages. The first stage discussed the proposed method which presented steps and algorithms in the pre-processing stage, feature extraction and classification as well as their use in CTG (20/50 papers). The second stage included the development of a system specifically on automatic feature extraction and CTG classification (7/50 papers). The third stage consisted of reviews and survey articles on automatic feature extraction and CTG classification (3/50 papers). The last stage discussed evaluation and comparative studies to determine the best method for extracting and classifying features with comparisons based on a set of criteria (20/50 articles).
Discussion: This study focused more on literature compared to techniques or methods. Also, this study conducts research and identification of various types of datasets used in surveys from publicly available, private, and commercial datasets. To analyze the results, researchers evaluated independent datasets using different techniques.
Conclusions: This systematic review contributes to understand and have insight into the relevant research in the field of CTG by surveying and classifying pertinent research efforts. This review will help to address the current research opportunities, problems and challenges, motivations, recommendations related to feature extraction and CTG classification, as well as the measurement of various performance and various data sets used by other researchers.
METHODS: A retrospective review of clinical records of all patients with CT scan evidence of tracheobronchial compression from January 2007 to December 2017 at National Heart Institute. Cardiovascular causes of tracheobronchial compression were divided into three groups; group I: vascular ring/pulmonary artery sling, II: abnormally enlarged or malposition cardiovascular structure due to CHD, III: post-CHD surgery.
RESULTS: Vascular tracheobronchial compression was found in 81 out of 810 (10%) patients who underwent CT scan. Group I lesions were the leading causes of vascular tracheobronchial compression (55.5%), followed by group II (34.6%) and group III (9.9%). The median age of diagnosis in groups I, II, and III were 16.8 months, 3 months, and 15.6 months, respectively. Half of group I patients are manifested with stridor and one-third with recurrent chest infections. Persistent respiratory symptoms, lung atelectasis, or prolonged respiratory support requirement were clues in groups II and III. Higher morbidity and mortality in younger infants with severe obstructive airway symptoms, associated airway abnormalities, and underlying complex cyanotic CHD.
CONCLUSIONS: Vascular ring/pulmonary artery sling and abnormally enlarged or malposition cardiovascular structure were the leading causes of cardiovascular airway compression. A high index of suspicion is needed for early detection due to its non-specific presentation. The outcome often depends on the severity of airway obstruction and complexity of cardiac lesions.
METHODS AND RESULTS: We recruited 101 normotensive young adults (n = 47 born preterm; 32.8 ± 3.2 weeks' gestation and n = 54 term-born controls). Peak VO2 was determined by cardiopulmonary exercise testing (CPET), and lung function assessed using spirometry. Percentage predicted values were then calculated. HRR was defined as the decrease from peak HR to 1 min (HRR1) and 2 min of recovery (HRR2). Four-chamber echocardiography views were acquired at rest and exercise at 40% and 60% of CPET peak power. Change in left ventricular ejection fraction from rest to each work intensity was calculated (EFΔ40% and EFΔ60%) to estimate myocardial functional reserve. Peak VO2 and per cent of predicted peak VO2 were lower in preterm-born young adults compared with controls (33.6 ± 8.6 vs. 40.1 ± 9.0 mL/kg/min, P = 0.003 and 94% ± 20% vs. 108% ± 25%, P = 0.001). HRR1 was similar between groups. HRR2 decreased less in preterm-born young adults compared with controls (-36 ± 13 vs. -43 ± 11 b.p.m., P = 0.039). In young adults born preterm, but not in controls, EFΔ40% and EFΔ60% correlated with per cent of predicted peak VO2 (r2 = 0.430, P = 0.015 and r2 = 0.345, P = 0.021). Similarly, EFΔ60% correlated with HRR1 and HRR2 only in those born preterm (r2 = 0.611, P = 0.002 and r2 = 0.663, P = 0.001).
CONCLUSIONS: Impaired myocardial functional reserve underlies reductions in peak VO2 and HRR in young adults born moderately preterm. Peak VO2 and HRR may aid risk stratification and treatment monitoring in this population.