Intelligent Identification of Childhood Musical Murmurs

Heart murmurs are often the first signs of heart valvular disorders. However, most heart murmurs detected in children are innocent musical murmurs (also called Still’s murmurs), which should be distinguished from other murmur types that are mostly pathological, such as regurgitant, obstructive, and flow murmurs. In order to reduce both unnecessary healthcare expenditures and parental anxiety, this study aims to develop algorithms for intelligently identifying musical murmurs in children. Discrete wavelet transform was applied to phonocardiographic signals to extract features. Singular value decomposition was applied on the matrix derived from continuous wavelet transform to extract extra features. The sequential forward feature selection algorithm was then utilized to select significant features. Musical murmurs were subsequently differentiated via a classification procedure consisting of three classification techniques: discriminant analysis, support vector machine, and artificial neural network. The results of 89.02% sensitivity, 84.76% specificity and 87.36% classification accuracy were achieved.

[1]  David Joyner,et al.  Linear Algebra with Applications , 1998 .

[2]  E. Etchells,et al.  Does this patient have an abnormal systolic murmur? , 1997, JAMA.

[3]  A. Pelech,et al.  The physiology of cardiac auscultation. , 2004, Pediatric clinics of North America.

[4]  B. McCrindle,et al.  An Evaluation of Parental Concerns and Misperceptions About Heart Murmurs , 1995, Clinical pediatrics.

[5]  Peter Hult,et al.  Feature Extraction for Systolic Heart Murmur Classification , 2006, Annals of Biomedical Engineering.

[6]  Tamer Ölmez,et al.  Classification of heart sounds using an artificial neural network , 2003, Pattern Recognit. Lett..

[7]  A heart sound segmentation and feature extraction algorithm using wavelets , 2004, First International Symposium on Control, Communications and Signal Processing, 2004..

[8]  Jacques P. de Vos,et al.  Automated Pediatric Cardiac Auscultation , 2007, IEEE Transactions on Biomedical Engineering.

[9]  D. Mozaffarian,et al.  Executive summary: heart disease and stroke statistics--2010 update: a report from the American Heart Association. , 2010, Circulation.

[10]  Jiaquan Xu,et al.  Deaths: final data for 2006. , 2009, National vital statistics reports : from the Centers for Disease Control and Prevention, National Center for Health Statistics, National Vital Statistics System.

[11]  Jelena Kovacevic,et al.  Wavelets and Subband Coding , 2013, Prentice Hall Signal Processing Series.

[12]  Mostefa Mesbah,et al.  Time-Frequency Feature Extraction of Newborn EEG Seizure Using SVD-Based Techniques , 2004, EURASIP J. Adv. Signal Process..

[13]  Shankar M. Krishnan,et al.  Neural network classification of homomorphic segmented heart sounds , 2007, Appl. Soft Comput..

[14]  Jasminka M Vukanovic-Criley,et al.  Competency in cardiac examination skills in medical students, trainees, physicians, and faculty: a multicenter study. , 2006, Archives of internal medicine.

[15]  D. Mozaffarian,et al.  Heart disease and stroke statistics--2010 update: a report from the American Heart Association. , 2010, Circulation.

[16]  M.S. Zainal,et al.  Analysis and classification of heart sounds and murmurs based on the instantaneous energy and frequency estimations , 2000, 2000 TENCON Proceedings. Intelligent Systems and Technologies for the New Millennium (Cat. No.00CH37119).

[17]  R. Sepponen,et al.  Phono-spectrographic analysis of heart murmur in children , 2007, BMC pediatrics.

[18]  G. Lightbody,et al.  Heart rate based automatic seizure detection in the newborn. , 2010, Medical engineering & physics.

[19]  Goutam Saha,et al.  In search of an optimization technique for Artificial Neural Network to classify abnormal heart sounds , 2009, Appl. Soft Comput..

[20]  Leon Resnekov.  Understanding Heart Sounds and Murmurs, With an Introduction to Lung Sounds , 1985 .

[21]  Rocio Alba-Flores,et al.  Detection of heart murmurs using wavelet analysis and artificial neural networks. , 2005, Journal of biomechanical engineering.

[22]  W. W. Myint,et al.  An electronic stethoscope with diagnosis capability , 2001, Proceedings of the 33rd Southeastern Symposium on System Theory (Cat. No.01EX460).

[23]  Hanqing Cao,et al.  Hemodynamic Instability Prediction Through Continuous Multiparameter Monitoring in ICU , 2010 .

[24]  Rocío Alba-Flores,et al.  Detection and Classification of Cardiac Murmurs using Segmentation Techniques and Artificial Neural Networks , 2007, 2007 IEEE Symposium on Computational Intelligence and Data Mining.

[25]  W. R. Thompson,et al.  Automated Cardiac Auscultation for Detection of Pathologic Heart Murmurs , 2001, Pediatric Cardiology.

[26]  Peter Hult,et al.  Distinguishing Innocent Murmurs from Murmurs caused by Aortic Stenosis by Recurrence Quantification Analysis , 2008 .

[27]  Nancy E. Reed,et al.  Heart sound analysis for symptom detection and computer-aided diagnosis , 2004, Simul. Model. Pract. Theory.

[28]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[29]  R. Mcfee,et al.  Clinical auscultation skills in pediatric residents. , 2001, Pediatrics.

[30]  Paul R. White,et al.  Analysing heart murmurs using time-frequency methods , 1996, Proceedings of Third International Symposium on Time-Frequency and Time-Scale Analysis (TFTS-96).

[31]  Teri L. Turner,et al.  Accuracy of clinical assessment of heart murmurs by office based (general practice) paediatricians. , 2000 .

[32]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[33]  Raimo Sepponen,et al.  How to recognize the innocent vibratory murmur , 2000, Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163).

[34]  Philip S. Wang,et al.  Parental anxiety associated with referral of a child to a pediatric cardiologist for evaluation of a Still's murmur. , 2002, The Journal of pediatrics.