머신러닝 분류기를 사용한 만성콩팥병 자동 진단 및 중증도 예측 연구
Automatic detection and severity prediction of chronic kidney disease using machine learning classifiers
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This paper proposes an optimal methodology for automatically diagnosing and predicting the severity of the chronic kidney disease (CKD) using patients’ utterances. In patients with CKD, the voice changes due to the weakening of respiratory and laryngeal muscles and vocal fold edema. Previous studies have phonetically analyzed the voices of patients with CKD, but no studies have been conducted to classify the voices of patients. In this paper, the utterances of patients with CKD were classified using the variety of utterance types (sustained vowel, sentence, general sentence), the feature sets [handcrafted features, extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS), CNN extracted features], and the classifiers (SVM, XGBoost). Total of 1,523 utterances which are 3 hours, 26 minutes, and 25 seconds long, are used. F1-score of 0.93 for automatically diagnosing a disease, 0.89 for a 3-classes problem, and 0.84 for a 5-classes problem were achieved. The highest performance was obtained when the combination of general sentence utterances, handcrafted feature set, and XGBoost was used. The result suggests that a general sentence utterance that can reflect all speakers’ speech characteristics and an appropriate feature set extracted from there are adequate for the automatic classification of CKD patients’ utterances.
Abstract
This paper proposes an optimal methodology for automatically diagnosing and predicting the severity of the chronic kidney disease (CKD) using patients’ utterances. In patients with CKD, the voice changes due to the weakening of respiratory and laryngeal muscles and vocal fold edema. Previous studies have phonetically analyzed the voices of patients with CKD, but no studies have been conducted to classify the voices of patients. In this paper, the utterances of patients with CKD were classified using the variety of utterance types (sustained vowel, sentence, general sentence), the feature sets [handcrafted features, extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS), CNN extracted features], and the classifiers (SVM, XGBoost). Total of 1,523 utterances which are 3 hours, 26 minutes, and 25 seconds long, are used. F1-score of 0.93 for automatically diagnosing a disease, 0.89 for a 3-classes problem, and 0.84 for a 5-classes problem were achieved. The highest performance was obtained when the combination of general sentence utterances, handcrafted feature set, and XGBoost was used. The result suggests that a general sentence utterance that can reflect all speakers’ speech characteristics and an appropriate feature set extracted from there are adequate for the automatic classification of CKD patients’ utterances.
참고문헌 (29)
- Abd El-gaber, F. M., "Acoustic characteristics of voice in patients with chronic kidney disease", International Journal of General Medicine, 14, pp.2465~2473 (2021)
- Ahn, H. K., "The H1*-H2* measure", Speech Sciences, 7(2), pp.85~95 (2000)
- Benba, A., "Voiceprints analysis using MFCC and SVM for detecting patients with Parkinson’s disease", Proceedings of the 2015 International Conference on Electrical and Information Technologies (ICEIT), pp.300~304 (2015)
- Boersma, P., "Praat, a system for doing phonetics by computer", Glot International, 5(9), pp.341~345 (2001)
- Darouiche, M. S., "An automatic voice disorder detection system based on extreme gradient boosting classifier", Proceedings of the 2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), pp.1~5 (2022)
- Eyben, F., "The Geneva minimalistic acoustic parameter set(GeMAPS)for voice research and affective computing", IEEE Transactions on Affective Computing, 7(2), pp.190~202 (2015)
- Eyben, F., "Opensmile:The munich versatile and fast open-source audio feature extractor", MM ‘10: Proceedings of the 18th ACM International Conference on Multimedia, pp.1459~1462 (2010)
- Harar, P., "Towards robust voice pathology detection", Neural Computing and Applications, 32(20), pp.15747~15757 (2020)
- Hassan, E. S., "Effect of chronic renal failure on voice : An acoustic and aerodynamic analysis", The Egyptian Journal of Otolaryngology, 30(1), pp.53~57 (2014)
- Hegde, S., "A survey on machine learning approaches for automatic detection of voice disorders", Journal of Voice, 33(6), pp.947.E11~947.E33 (2019)
- Hershey, S., "CNN architectures for large-scale audio classification", Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.131~135 (2017)
- Jung, S. Y., "Voice change in end-stage renal disease patients after hemodialysis : Correlation of subjective hoarseness and objective acoustic parameters", Journal of Voice, 28(2), pp.226~230 (2014)
- Kumar, R. B., "Voice in chronic renal failure", Journal of Voice, 24(6), pp.690~693 (2010)
- Lee, S. J., "Aging effect on Korean female voice : Acoustic and perceptual examinations of breathiness", Folia Phoniatrica et Logopaedica, 67(6), pp.300~307 (2015)
- Liu, Y., "Prediction of voice disorder severity: Contributions from sustained vowels and continuous speech", Proceedings of the 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP), pp.290~294 (2018)
- McFee, B., "Librosa: Audio and music signal analysis in Python", Proceedings of the 14th Python in Science Conference, pp.18~25 (2015)
- Moon, K. R., "Materials of acoustic analysis : Sustained vowel versus sentence", Journal of Voice, 26(5), pp.563~565 (2012)
- Mudawwar, W. A., "Effect of renal failure on voice", ENT: Ear, Nose &and Throat Journal, 96, pp.32~36 (2017)
- "A speech corpus for chronic kidney disease" (2022)[URL]
- Narendra, N. P., "Glottal source information for pathological voice detection", IEEE Access, 8, pp.67745~67755 (2020)
- Omeroglu, A. N., "Multi-modal voice pathology detection architecture based on deep and handcrafted feature fusion", Engineering Science and Technology, an International Journal, 36, pp.101148~ (2022)
- Shetty, S., "Classification of healthy and pathological voices using MFCC and ANN", Proceedings of the 2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC), pp.1~5 (2018)
- Speyer, R., "Maximum phonation time : Variability and reliability", Journal of Voice, 24(3), pp.281~284 (2010)
- Sun, Y., "Classification of imbalanced data : A review", International Journal of Pattern Recognition and Artificial Intelligence, 23(4), pp.687~719 (2009)
- Teixeira, J. P., "Vocal acoustic analysis–jitter, shimmer and hnr parameters", Procedia Technology, 9, pp.1112~1122 (2013)
- Triantafyllopoulos, A., "Distinguishing between pre- and post-treatment in the speech of patients with chronic obstructive pulmonary disease", Proceedings of the Interspeech 2022, pp.3623~3627 (2022)
- Korea. Webster, A. C., "Chronic kidney disease", The Lancet, 389(10075), pp.1238~1252 (2017)
- 여은정, "음질, 운율, 발음 특징을 이용한 마비말장애 중증도 자동 분류", 말소리와 음성과학, 13(2), pp.57~66 (2021), 한국음성학회[DOI]
- Zaky, E. A., "Voice problem in a patient with chronic renal failure", The Egyptian Journal of Otolaryngology, 36(1), pp.1~8 (2020)