Abstract
Voice disorders are a widespread and significant health problem. In the United States, estimates of prevalence range from 3% to 7% of the general population and the number increases significantly in the rural US areas due to lack of availability of highly trained medical professionals and access to specialty voice care centers. Untreated, the voice disorders cost billions of dollars in lost productivity and much of the cost is paid by the tax payers. Early identification, prognosis, is a game changer as it provides a clinical pathway to reduce the impact of the disease. The goal of this paper is to develop artificial intelligent diagnostic tool that can detect voice disorders in clinical and outpatient settings through the application of advanced machine learning and neural networks techniques. Our innovation is to democratize diagnostic tool so that the disparity of access in rural areas can be reduced by bridging the gap between access and availability of specialty care through data science and machine learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
THE PROBLEM OF LIMITED HEALTH CARE COVERAGE VOICE DISORDER TREATMENT [TRANSCRIPT] - https://blog.asha.org/the-problem-of-limited-health-care-coverage-voice-disorder-treatment-transcript/.
- 2.
Chennai doctors help patients find their voice - https://timesofindia.indiatimes.com/city/chennai/Chennai-doctors-help-patients-find-their-voice/articleshow/16886456.cms.
- 3.
Leading causes of death in Rural America - http://www.ncsl.org/research/health/leading-causes-of-death-in-rural-america-postcard.aspx.
- 4.
LibROSA Library - https://librosa.github.io/librosa/.
- 5.
Voice disorder ICD Codes - https://www.icd10data.com/ICD10CM/Codes/R00-R99/R47-R49/R49-.
- 6.
J. Deep Learning in Python by Francois Chollet.
- 7.
TensorFlow Workflow - https://www.tensorflow.org/lite/guide/get_started.
References
Piczak, K.J.: Environmental sound classification with convolutional neural networks. In: 2015 IEEE International Workshop on Machine Learning for Signal Processing, 17–20 September 2015, Boston, USA (2015)
Mitrovic, D., Zeppelzauer, M., Breiteneder, C.: Discrimination and retrieval of animal sounds. In: 2006 12th International Multi-Media Modelling Conference, Beijing, p. 5 (2006). https://doi.org/10.1109/MMMC.2006.1651344. http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1651344&isnumber=34625
Le-Qing, Z.: Insect sound recognition based on MFCC and PNN. In: 2011 International Conference on Multimedia and Signal Processing, Guilin, China, pp. 42–46 (2011). https://doi.org/10.1109/cmsp.2011.100. http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5957464&isnumber=5957439
Appleton, J., Perera, P. (eds.): The mel scale as a function of frequency. In: The Development and Practice of Electronic Music, p. 56. Prentice-Hall (1975). After Stevens and Davis, Hearing; used by permission
Salamon, J., Bello, J.P.: Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Sign. Process. Lett. 24, 279–283 (2016)
Fayek, H.: Speech processing for machine learning: filter banks, Mel-Frequency Cepstral Coefficients (MFCCs) and What’s In-Between, 21 April 2016. https://haythamfayek.com/2016/04/21/speech-processing-for-machine-learning.html. Accessed 11 Nov 2018
Mel Frequency Cepstral Coefficient (MFCC) tutorial. http://practicalcryptography.com/miscellaneous/machine-learning/guide-mel-frequency-cepstral-coefficients-mfccs/. Accessed 11 Nov 2018
Pons, J., Serra, X.: Randomly weighted CNNs for (music) audio classification, arXiv:1805.00237 [cs.SD]
Mesaros, A., Heittola, T., Virtanen, T.: A multi-device dataset for urban acoustic scene classification, arXiv:1807.09840 [eess.AS]
Lee, J., Kim, T., Park, J., Nam, J.: Sound raw waveform-based audio classification using sample-level CNN architectures, arXiv:1712.00866 [cs.SD]
Chollet, F.: Deeplearning with Python, Manning Publications, 1 edn. 22 December 2017. ISBN-13: 978-1617294433
Acknowledgment
We sincerely thank you to the team in Far Eastern Memorial Hospital (FEMH) for providing valuable voice data without the development of Neural Network is impossible. We acknowledge and sincerely credit the support of FEMH.
Additionally, we would thank the management of Hanumayamma Innovations and Technologies, Inc., for active support they provided in helping and providing resources needed to work on the challenge. We have tested and deployed voice disorder diagnostic mobile app with Sanjeevani Electronic Health Records (www.sanjeevani-ehr.com). We have several Senior Citizen Users that are using the system and providing valuable healthcare data (see Fig. 12).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Vuppalapati, J.S., Kedaru, S., Kedari, S., Ilapakurti, A., Vuppalapati, C. (2020). Artificial Intelligent (AI) Clinical Edge for Voice Disorder Detection. In: Bi, Y., Bhatia, R., Kapoor, S. (eds) Intelligent Systems and Applications. IntelliSys 2019. Advances in Intelligent Systems and Computing, vol 1038. Springer, Cham. https://doi.org/10.1007/978-3-030-29513-4_56
Download citation
DOI: https://doi.org/10.1007/978-3-030-29513-4_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29512-7
Online ISBN: 978-3-030-29513-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)