Home >> Archive >> Vol:1, No:1 >> Audio Analysis Based Diagnosis of Hypoxic Ischemic Encephalopathy in Newborns

Audio Analysis Based Diagnosis of Hypoxic Ischemic Encephalopathy in Newborns

| Mehmet Satar | | Caglar Cengizler | | Serif Hamitoglu | | Mustafa Ozdemir |

Year:2022| Vol:1| No:1| PP 28-42
Abstract
Hypoxic Ischemic Encephalopathy (HIE) would be defined as functional brain disorder that occurs when the brain does not receive sufficient oxygen or blood flow for a certain period of time. existence and severity of the disorder is mostly diagnosed by an expert physician. In this study, implementation of a automated classification mechanism is aimed which is capable of diagnosing existence of HIE in newborns by analysing their crying audio. Accordingly crying sounds of newborns from HIE positive and negative groups were collected for forming a dataset. In this study several features of the collected audio data is examined for revealing sound characteristics that defines the disorder in search space. Deep learning approach is adapted for teaching implemented algorithm to classify HIE disorder on extracted feature space. Results are showing that presented classification approach is promising for a fully automated diagnosis system and computer is capable of discriminating crying sounds from HIE positive babies with 96% accuracy.

Keywords
Hypoxic Ischemic Encephalopathy; Newborn; Cry; Deep learning; Diagnosis
Full Paper (PDF)

Rights and permissions
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

References
  1. Wasz-H"ockert, O; Partanen, TJ; Vuorenkoski, V; Michelsson, K and Valanne, E The identification of some specific meanings in infant vocalization. In Experientia, 20 (3): 154-154, 1964.
  2. Maghfira, T. N.; Basaruddin, T and Krisnadhi, A. Infant cry classification using cnn--rnn. In Journal of Physics: Conference Series, pages 012019, 2020.
  3. Abdulaziz, Y. and Ahmad, S. M. S. An accurate infant cry classification system based on continuos Hidden Markov Model. In 2010 International Symposium on Information Technology, pages 1648-1652, 2010.
  4. Limantoro, W. S.; Fatichah, C. and Yuhana, U. L. Application development for recognizing type of infant's cry sound. In 2016 International Conference on Information & Communication Technology and Systems (ICTS), pages 157-161, 2016.
  5. Farsaie Alaie, H. and Tadj, C. Cry-based classification of healthy and sick infants using adapted boosting mixture learning method for gaussian mixture models. In Modelling and simulation in engineering, 2012, 2012.
  6. Ensefalopati, T. N. D. H. .Iskemik and Grubu, &. T"urkiye’de yenidougan yougun bakim "unitelerinde izlenen hipoksik iskemik ensefalopatili olgular, risk fakt"orleri, insidans ve kisa d"onem prognozlari. In Çocuk Saugliugi ve Hastaliklari Dergisi, 51 (3): 123-29, 2008.
  7. Douglas-Escobar, M. and Weiss, M. D Hypoxic-ischemic encephalopathy: a review for the clinician. In JAMA pediatrics, 169 (4): 397-403, 2015.
  8. Vannucci, R. C and Perlman, J. M Interventions for perinatal hypoxic--ischemic encephalopathy. In Pediatrics, 100 (6): 1004-1114, 1997.
  9. Papakostas, M.; Spyrou, E.; Giannakopoulos, T.; Siantikos, G.; Sgouropoulos, D.; Mylonas, P. and Makedon, F. Deep visual attributes vs. hand-crafted audio features on multidomain speech emotion recognition. In Computation, 5 (2): 26, 2017.
  10. Lim, W.; Jang, D. and Lee, T. Speech emotion recognition using convolutional and recurrent neural networks. In 2016 Asia-Pacific signal and information processing association annual summit and conference (APSIPA), pages 1-4, 2016.
  11. Stevens, S. S.; Volkmann, J. and Newman, E. B. A scale for the measurement of the psychological magnitude pitch. In The journal of the acoustical society of america, 8 (3): 185-190, 1937.
  12. Feijoo, S. and Hern'andez, C. Short-term stability measures for the evaluation of vocal quality. In Journal of Speech, Language, and Hearing Research, 33 (2): 324-334, 1990.
  13. Saudi, A. SM; Youssif, A. AA and Ghalwash, A. Z Computer aided recognition of vocal folds disorders by means of RASTA-PLP. In Computer and information Science, 5 (2): 39, 2012.
  14. Zheng, F.; Zhang, G. and Song, Z. Comparison of different implementations of MFCC. In Journal of Computer science and Technology, 16 (6): 582-589, 2001.
  15. Picone, J. W Signal modeling techniques in speech recognition. In Proceedings of the IEEE, 81 (9): 1215-1247, 1993.
  16. Mason, J. S and Zhang, X Velocity and acceleration features in speaker recognition. In Acoustics, Speech, and Signal Processing, IEEE International Conference on, pages 3673-3674, 1991.
  17. Rao, K S. and Nandi, D. Language identification using excitation source features. Springer, 2015.
  18. Valero, X. and Alias, F. Gammatone cepstral coefficients: Biologically inspired features for non-speech audio classification. In IEEE Transactions on Multimedia, 14 (6): 1684-1689, 2012.
  19. Peeters, G. A large set of audio features for sound description (similarity and classification) in the CUIDADO project. In CUIDADO Ist Project Report, 54 (0): 1-25, 2004.
  20. Vakkuri, A.; Yli-Hankala, A; Talja, P; Mustola, S; Tolvanen-Laakso, H; Sampson, Tl and Vierti"o-Oja, H Time-frequency balanced spectral entropy as a measure of anesthetic drug effect in central nervous system during sevoflurane, propofol, and thiopental anesthesia. In Acta Anaesthesiologica Scandinavica, 48 (2): 145-153, 2004.
  21. Scheirer, E. and Slaney, M. Construction and evaluation of a robust multifeature speech/music discriminator. In 1997 IEEE international conference on acoustics, speech, and signal processing, pages 1331-1334, 1997.
  22. Jain, A. and Zongker, D. Feature selection: Evaluation, application, and small sample performance. In IEEE transactions on pattern analysis and machine intelligence, 19 (2): 153-158, 1997.
  23. Bishop, C. M Pattern recognition. In Machine learning, 128 (9), 2006.