Paediatric heart sound signal analysis towards classification using multifractal spectra

Abstract

Healthy versus unhealthy heart sound computer-aided classification tools are very popular for supporting clinical decisions. In this paper a new method is proposed for the classification of heart sound recordings from a statistical standpoint without detection and localization of fundamental heart sounds (S1, S2). This study analyzes the possibility of detecting healthy heart sound signal from a large set of measurements, corresponding to different pathologies, such as aortic regurgitation, mitral regurgitation, aortic stenosis and ventricular septal defects. The proposed method employs singularity spectra analysis and long-term dependency of irregular structures. Healthy signals are firstly separated from the rest of the recordings. In the second step, the signals with a click syndrome, used here as a reference, are detected in the unhealthy group. Innocent murmurs have not been considered in this paper. Each auscultatory recording is classified into one of the following classes: healthy; click syndrome; and other heart dysfunctions. The results of the proposed method provided high recall and precision values for each of the three classes. Since the presence of additive noise may affect the classification, we also analyzed the possibility of classifying signals in such circumstances. The method was tested, verified and showed high accuracy.

Diagnostic Accuracy of Machine Learning Models to Identify Congenital Heart Disease: A Meta-Analysis

“…We excluded 74 studies and the remaining 16 studies were included in the review. Out of the 16 included studies; meta-analysis was conducted for seven studies while nine studies were narratively synthesized (refer to Figure 1 for the study flow diagram) ( DeGroff et al, 2001 ; Yang et al, 2002 ; Bhatikar et al, 2005 ; Higuchi et al, 2006 ; De Vos and Blanckenberg, 2007 ; Ye et al, 2011 ; Gharehbaghi et al, 2015 ; Zhang and Pohl, 2015 ; Gavrovska et al, 2016 ; Kotb et al, 2016 ; Sepehri et al, 2016 ; Karar et al, 2017 ; Pereira et al, 2017 ; Meza et al, 2018 ; Diller et al, 2019a ; Bahado-Singh et al, 2020 ). The characteristics of included studies ( n = 16) have been outlined in Table 2 .…”

“…Due to the small number of studies for each of these diagnostic conditions, these were all labeled as an umbrella term of CHD for the purpose of this review. The reference standard for most of the studies was echocardiography ( n = 9, 56.3%) ( DeGroff et al, 2001 ; Yang et al, 2002 ; Bhatikar et al, 2005 ; Higuchi et al, 2006 ; De Vos and Blanckenberg, 2007 ; Gharehbaghi et al, 2015 ; Gavrovska et al, 2016 ; Kotb et al, 2016 ; Meza et al, 2018 ) or the expert clinician ( n = 7, 43.7%) ( Ye et al, 2011 ; Zhang and Pohl, 2015 ; Sepehri et al, 2016 ; Karar et al, 2017 ; Pereira et al, 2017 ; Diller et al, 2019b ; Bahado-Singh et al, 2020 ) who made the final diagnosis.…”

“…Risk of Bias assessment reported that eleven studies (69%) ( DeGroff et al, 2001 ; Yang et al, 2002 ; Bhatikar et al, 2005 ; De Vos and Blanckenberg, 2007 ; Ye et al, 2011 ; Zhang and Pohl, 2015 ; Karar et al, 2017 ; Pereira et al, 2017 ; Meza et al, 2018 ; Diller et al, 2019a ; Bahado-Singh et al, 2020 ) had high risk of patient selection bias due to the study design (case control) while the remaining five studies (31%) ( Higuchi et al, 2006 ; Gharehbaghi et al, 2015 ; Gavrovska et al, 2016 ; Kotb et al, 2016 ; Sepehri et al, 2016 ) were unclear risk. The index test interpretation bias was unclear in nine studies (56%) ( DeGroff et al, 2001 ; Yang et al, 2002 ; Bhatikar et al, 2005 ; Higuchi et al, 2006 ; De Vos and Blanckenberg, 2007 ; Gharehbaghi et al, 2015 ; Sepehri et al, 2016 ; Pereira et al, 2017 ; Diller et al, 2019a ), high in six studies (37%) ( Ye et al, 2011 ; Zhang and Pohl, 2015 ; Gavrovska et al, 2016 ; Karar et al, 2017 ; Meza et al, 2018 ; Bahado-Singh et al, 2020 ) and low in only one study (7%) ( Kotb et al, 2016 ). The main contributor to the unclear risk was the unavailability of information regarding theblinding status in these studies.…”

“…The main contributor to the unclear risk was the unavailability of information regarding theblinding status in these studies. Majority of the studies (n 10, 62%) had low risk of reporting bias (DeGroff et al, 2001;Yang et al, 2002;De Vos and Blanckenberg, 2007;Zhang and Pohl, 2015;Gavrovska et al, 2016;Sepehri et al, 2016;Karar et al, 2017;Pereira et al, 2017;Meza et al, 2018;Diller et al, 2019a) while five reported unclear risk (31%) (Bhatikar et al, 2005;Higuchi et al, 2006;Gharehbaghi et al, 2015;Kotb et al, 2016;Bahado-Singh et al, 2020) and one reported high risk (7%) (Ye et al, 2011). The reference standard that was used mainly included expert opinion along with gold standard imaging modalities such as echocardiography, thus reducing the likelihood of bias.…”

Classification of Heart Sounds Based on the Wavelet Fractal and Twin Support Vector Machine

“…The slope of the fitting line is the estimated value of . It can be seen that when estimating box dimension , the range and variation of grid scale have the important influences on the accuracy and the speed of estimating [ 29 , 30 , 31 ].…”