Automated diagnosis of heart valve degradation using novelty detection algorithms and machine learning

English version

Autoři: Bernhard Vennemann ^aff001; Dominik Obrist ^aff002; Thomas Rösgen ^aff001
Působiště autorů: Institute of Fluid Dynamics, ETH Zürich, Zürich, Switzerland ^aff001; ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland ^aff002
Vyšlo v časopise: PLoS ONE 14(9)
Kategorie: Research Article
prolekare.web.journal.doi_sk: https://doi.org/10.1371/journal.pone.0222983

Souhrn

The blood flow through the major vessels holds great diagnostic potential for the identification of cardiovascular complications and is therefore routinely assessed with current diagnostic modalities. Heart valves are subject to high hydrodynamic loads which render them prone to premature degradation. Failing native aortic valves are routinely replaced with bioprosthetic heart valves. This type of prosthesis is limited by a durability that is often less than the patient’s life expectancy. Frequent assessment of valvular function can therefore help to ensure good long-term outcomes and to plan reinterventions. In this article, we describe how unsupervised novelty detection algorithms can be used to automate the interpretation of blood flow data to improve outcomes through early detection of adverse cardiovascular events without requiring repeated check-ups in a clinical environment. The proposed method was tested in an in-vitro flow loop which allowed simulating a failing aortic valve in a laboratory setting. Aortic regurgitation of increasing severity was deliberately introduced with tube-shaped inserts, preventing complete valve closure during diastole. Blood flow recordings from a flow meter at the location of the ascending aorta were analyzed with the algorithms introduced in this article and a diagnostic index was defined that reflects the severity of valvular degradation. The results indicate that the proposed methodology offers a high sensitivity towards pathological changes of valvular function and that it is capable of automatically identifying valvular degradation. Such methods may be a step towards computer-assisted diagnostics and telemedicine that provide the clinician with novel tools to improve patient care.

Klíčová slova:

Medical implants – Data acquisition – Machine learning algorithms – Support vector machines – Sensory physiology – Blood flow – Flow rate

Zdroje

1. Yacoub MH, Takkenberg JJM. Will heart valve tissue engineering change the world? Nat Clin Pract Cardiovasc Med. 2005 Feb;2(2):60–1. doi: 10.1038/ncpcardio0112 16265355

2. Grunkemeier GL, Anderson WN Jr. Clinical evaluation and analysis of heart valve substitutes. J Heart Valve Dis. 1998 Mar;7(2):163–169. 9587856

3. Grunkenmeier G, Jamieson W, Miller D, Starr A. Actuarial versus actual risk of porcine structural valve deterioration. J Thorac Cardiovasc Surg. 1994 Oct;108(4):709–18.

4. Rodriguez-Gabella T, Voisine P, Puri R, Pibarot P, Rodés-Cabau J. Aortic Bioprosthetic Valve Durability. J Am Coll Cardiol. 2017 Aug;70(8):1013–28. doi: 10.1016/j.jacc.2017.07.715 28818190

5. Koydemir HC, Ozcan A. Wearable and Implantable Sensors for Biomedical Applications. Annu Rev Anal Chem. 2018 Feb;11:127–146. doi: 10.1146/annurev-anchem-061417-125956

6. Ozcan A. Mobile phones democratize and cultivate next-generation imaging, diagnostics and measurement tools. Lab Chip. 2014 Sep;14(17):3187–94. doi: 10.1039/c4lc00010b 24647550

7. Vashist SK, Mudanyali O, Schneider EM, Zengerle R, Ozcan A. Cellphone-based devices for bioanalytical sciences. Anal Bioanal Chem. 2014 May;406(14):3263–77. doi: 10.1007/s00216-013-7473-1 24287630

8. Yu KH, Beam AL, Kohane IS. Artificial intelligence in healthcare. Nat Biomed Eng. 2018 2(10):719–731. doi: 10.1038/s41551-018-0305-z 31015651

9. Sengur A. An expert system based on principal component analysis, artificial immune system and fuzzy k-NN for diagnosis of valvular heart diseases. Comput Biol Med. 2008 Mar;38(3):329–338. doi: 10.1016/j.compbiomed.2007.11.004 18177849

10. Sengur A. An expert system based on linear discriminant analysis and adaptive neuro-fuzzy inference system to diagnosis heart valve diseases. Expert Syst Appl. 2008 Jul;35(1):214–222. doi: 10.1016/j.eswa.2007.06.012

11. Sengur A, Turkoglu I. A hybrid method based on artificial immune system and fuzzy k-NN algorithm for diagnosis of heart valve diseases. Expert Syst Appl. 2008 Oct;35(3):1011–1020. doi: 10.1016/j.eswa.2007.08.003

12. Saraçoglu R. Hidden Markov model-based classification of heart valve disease with PCA for dimension reduction. Eng Appl Artif Intell. 2012 Oct;25(7):1523–1528. doi: 10.1016/j.engappai.2012.07.005

13. Uguz H, Arslan A, Turkoglu I. A biomedical system based on hidden Markov model for diagnosis of the heart valve diseases. Pattern Recognit Lett. 2007 Mar;28(4):395–404. doi: 10.1016/j.patrec.2006.08.009

14. Wang P, Lim CS, Chauhan S, Foo JYA, Anantharaman V. Phonocardiographic signal analysis method using a modified hidden Markov model. Ann Biomed Eng. 2007 Mar;35(3):367–74. doi: 10.1007/s10439-006-9232-3 17171300

15. Avci E. A new intelligent diagnosis system for the heart valve diseases by using genetic-SVM classifier. Expert Syst Appl. 2009 Sep;36(7):10618–10626. doi: 10.1016/j.eswa.2009.02.053

16. Bouril A, Aleinikava D, Guillem Sanchez M de la S, Mirsky G. Automated Classification of Normal and Abnormal Heart Sounds using Support Vector Machines. Comput in Cardiol Conf (CinC). 2017.

17. Choi S. Detection of valvular heart disorders using wavelet packet decomposition and support vector machine. Expert Syst Appl. 2008 Nov;35(4):1679–1687. doi: 10.1016/j.eswa.2007.08.078

18. Çomak E, Arslan A, Türkoǧlu I. A decision support system based on support vector machines for diagnosis of the heart valve diseases. Comput Biol Med. 2007 Jan;37(1):21–7. doi: 10.1016/j.compbiomed.2005.11.002 16426598

19. Çomak E, Arslan A. A biomedical decision support system using LS-SVM classifier with an efficient and new parameter regularization procedure for diagnosis of heart valve diseases. J Med Syst. 2012 Apr;36(2):549–56. doi: 10.1007/s10916-010-9500-5 20703696

20. Gharehbaghi A, Borga M, Sjöberg BJ, Ask P. A novel method for discrimination between innocent and pathological heart murmurs. Med Eng Phys. 2015 Jul;37(7):674–82 26003286

21. Maglogiannis I, Loukis E, Zafiropoulos E, Stasis A. Support Vectors Machine-based identification of heart valve diseases using heart sounds. Comput Methods Programs Biomed. 2009 Jul;95(1):47–61. doi: 10.1016/j.cmpb.2009.01.003 19269056

22. Redlarski G, Gradolewski D, Palkowski A. A system for heart sounds classification. PLoS One. 2014 May 2;11(5):e0154515.

23. Safara F, Doraisamy S, Azman A, Jantan A, Abdullah Ramaiah AR. Multi-level basis selection of wavelet packet decomposition tree for heart sound classification. Comput Biol Med. 2013 Oct;43(10):1407–14. doi: 10.1016/j.compbiomed.2013.06.016 24034732

24. Sengur A. Support vector machine ensembles for intelligent diagnosis of valvular heart disease. J Med Syst. 2012 Aug;36(4):2649–2655. doi: 10.1007/s10916-011-9740-z 21590303

25. Yaseen, Son G-Y, Kwon S. Classification of Heart Sound Signal Using Multiple Features. Appl Sci. 2018;8(12):2344. doi: 10.3390/app8122344

26. Andrisevic N, Ejaz K, Rios-Gutierrez F, Alba-Flores R, Nordehn G, Burns S. Detection of Heart Murmurs Using Wavelet Analysis and Artificial Neural Networks. J Biomech Eng. 2005 Nov;127(6):899–904. doi: 10.1115/1.2049327 16438225

27. Babaei S, Geranmayeh A. Heart sound reproduction based on neural network classification of cardiac valve disorders using wavelet transforms of PCG signals. Comput Biol Med. 2009 Jan;39(1):8–15. doi: 10.1016/j.compbiomed.2008.10.004 19081085

28. El-Ramsisi AM, Khalil HA. Diagnosis system based on wavelet transform, fractal dimension and neural network. J Appl Sci. 2007 Jun 15;163(1):145–60.

29. Gupta CN, Palaniappan R, Swaminathan S, Krishnan SM. Neural network classification of homomorphic segmented heart sounds. Appl Soft Comput J. 2007;4:4251–4.

30. Nassralla M, Zein Z El, Hajj H. Classification of normal and abnormal heart sounds. International Conference on Advances in Biomedical Engineering, ICABME. 2017.

31. Reed TR, Reed NE, Fritzson P. Heart sound analysis for symptom detection and computer-aided diagnosis. Simulation Modelling Practice and Theory. 2004 May;12(2):129–146. doi: 10.1016/j.simpat.2003.11.005

32. Sinha RK, Aggarwal Y, Das BN. Backpropagation artificial neural network classifier to detect changes in heart sound due to mitral valve regurgitation. J Med Syst. 2007 Jun;31(3):205–209. doi: 10.1007/s10916-007-9056-1 17622023

33. Turkoglu I, Arslan A, Ilkay E. An intelligent system for diagnosis of the heart valve diseases with wavelet packet neural networks. Computers in Biology and Medicine. 2003 Jul;33(4):319–31. doi: 10.1016/S0010-4825(03)00002-7 12791405

34. Uguz H. A Biomedical System Based on Artificial Neural Network and Principal Component Analysis for Diagnosis of the Heart Valve Diseases. J Med Syst. 2012 Feb;36(1):61–72. doi: 10.1007/s10916-010-9446-7 20703748

35. Zabihi M, Bahrami Rad A, Kiranyaz S, Gabbouj M, K. Katsaggelos A. Heart Sound Anomaly and Quality Detection using Ensemble of Neural Networks without Segmentation. Computing in Cardiology Conference (CinC) 2017.

36. Bozkurt B, Germanakis I, Stylianou Y. A study of time-frequency features for CNN-based automatic heart sound classification for pathology detection. Comput Biol Med. 2018 Sep;100:132–143. doi: 10.1016/j.compbiomed.2018.06.026 29990646

37. Deperlioglu O. Classification of Phonocardiograms with Convolutional Neural Networks. BRAIN Broad Res Artif Intell Neurosci. 2018;9(2).

38. Dominguez-Morales JP, Jimenez-Fernandez AF, Dominguez-Morales MJ, Jimenez-Moreno G. Deep Neural Networks for the Recognition and Classification of Heart Murmurs Using Neuromorphic Auditory Sensors. IEEE Trans Biomed Circuits Syst. 2018. doi: 10.1109/TBCAS.2017.2751545 28952948

39. Low JX, Choo KW. Classification of Heart Sounds Using Softmax Regression and Convolutional Neural Network. Int Conf Comm Eng Technol. 2018:18–21.

40. Noman F, Ting C-M, Salleh S-H, Ombao H. Short-segment heart sound classification using an ensemble of deep convolutional neural networks. ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019:1318–1322.

41. Rubin J, Abreu R, Ganguli A, Nelaturi S, Matei I, Sricharan K. Recognizing abnormal heart sounds using deep learning. CEUR Workshop Proceedings. 2017.

42. Rubin J, Abreu R, Ganguli A, Nelaturi S, Matei I, Sricharan K. Classifying Heart Sound Recordings using Deep Convolutional Neural Networks and Mel Frequency Cepstral Coefficients. Comput in Cardiol Conf (CinC). 2017.

43. Sujadevi VG, Soman KP, Vinayakumar R, Prem Sankar AU. Anomaly Detection in Phonocardiogram Employing Deep Learning. Adv in Intell Sys and Comput. 2019;711.

44. Latif S, Usman M, Rana R, Qadir J. Phonocardiographic Sensing Using Deep Learning for Abnormal Heartbeat Detection. IEEE Sens J. 2018. doi: 10.1109/JSEN.2018.2870759

45. Das R, Turkoglu I, Sengur A. Diagnosis of valvular heart disease through neural networks ensembles. Comput Methods Programs Biomed. 2009 Feb;93(2):185–91. doi: 10.1016/j.cmpb.2008.09.005 18951649

46. Das R, Sengur A. Evaluation of ensemble methods for diagnosing of valvular heart disease. Expert Syst Appl. 2010 Nov;107(11):592–8.

47. Nishimura RA, Otto CM, Bonow RO, Carabello BA, Erwin JP, Guyton RA, O’Gara PT, Ruiz CE, Skubas NJ, Sorajja P, Sundt TM, Thomas JD. 2014 AHA/ACC guideline for the management of patients with valvular heart disease: executive summary. J. Am. Coll. Cardiol. 2014 Jun;63(22):2438–2488. doi: 10.1016/j.jacc.2014.02.537 24603192

48. Vennemann B. Wireless Blood Flow Sensing for Automated Diagnostics. 2019 Apr.

49. Levenberg K. A method for the solution of certain non-linear problems in least squares. Q Appl Math. 1944; 2(2):164–168. doi: 10.1090/qam/10666

50. Marquardt DW. An Algorithm for Least-Squares Estimation of Nonlinear Parameters. J Soc Ind Appl Math J Soc Indust Appl Math. 1963; 11(2):431–441. doi: 10.1137/0111030

51. Geron A. Hands-on machine learning with scikit-learn & tensorflow 1st ed. Sebastopol: O’Reilly Media, Inc.; 2017.

52. Chandola V. Banerjee A. Kumar V. Anomaly Detection for Discrete Sequences: A Survey. ACM Comput Surv 2009 Jul;41(3):1–58.

53. Schölkopf B, Platt JC, Shawe-Taylor J, Smola AJ, Williamson RC. Estimating the support of a high-dimensional distribution. Neural Comput. 2001 Jul;13(7):1443–1471. doi: 10.1162/089976601750264965 11440593

54. Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. Proceedings of the fifth annual workshop on Computational learning theory. 1992:144–152.

55. Carabello BA. Valvular Heart Disease. Goldman’s Cecil Med. 2012 Jan;453–64. doi: 10.1016/B978-1-4377-1604-7.00075-0

56. Vennemann B, Rösgen T, Heinisch PP, Obrist D. Leaflet kinematics of mechanical and bioprosthetic aortic valve prostheses. ASAIO J. 2018 Sep/Oct;64(5):651–661. doi: 10.1097/MAT.0000000000000687 29045279

57. Okafor I, Raghav V, Condado JF, Midha PA, Kumar G, Yoganathan AP. Aortic regurgitation generates a kinematic obstruction which hinders left ventricular filling. Ann Biomed Eng. 2017 May;45(5):1305–1314. doi: 10.1007/s10439-017-1790-z 28091966

58. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 2011 Oct;12:2825–2830.

Automated diagnosis of heart valve degradation using novelty detection algorithms and machine learning

Souhrn

Klíčová slova:

Zdroje

PLOS One

Aktuální možnosti diagnostiky a léčby litiáz