Research Article
BibTex RIS Cite

SOLUNUM SİSTEMİ HASTALIKLARININ TEŞHİSİNE YÖNELİK MAKİNE ÖĞRENMESİ TABANLI ANALİZ PROGRAMI GELİŞTİRİLMESİ

Year 2023, Volume: 26 Issue: 1, 126 - 138, 15.03.2023
https://doi.org/10.17780/ksujes.1181958

Abstract

Solunum sistemi hastalıkları hem dünyada hem ülkemizde milyonlarca kişinin ölümüne sebep olan tıbbi bir problemdir. Teknolojinin gelişmesi ile ortaya çıkan bilgisayar destekli tanı sistemleri solunum sistemi hastalıklarının erken teşhisinde umut vadetmektedir. Bu çalışmanın amacı sağlıklı ve çeşitli akciğer hastalıklarına sahip bireylerden alınan solunum seslerinin otomatik teşhisi ile hekime yardımcı olan ve Tıp eğitimi gören öğrencilerin solunum seslerini öğrenmesine imkan sağlayan tanı sistemi geliştirilmesidir. Çalışmadaki kullanılan solunum sesleri, Manisa Celal Bayar Üniversitesi Hafsa Sultan Hastahanesi Göğüs Hastalıkları Anabilim dalındaki uzman hekimler tarafından Littman 3200 Elektronik Stetoskop ile kaydedilmiştir. 105 gönüllüden kaydedilen yedi farklı solunum grubuna ait solunum sesleri filtreleme, öznitelik çıkarımı ve sınıflama gibi sinyal işleme yöntemlerine tabi tutularak otomatik teşhis gerçekleştirilme ve teşhis sonucuna göre hastanın sahip olabileceği olası hastalıklar Kullanıcı Ara yüzünde listelenmektedir. Geliştirilen programda kullanılan yöntemlerin eğitilmesi ve başarılarının test edilebilmesi amacıyla veriler, eğitim ve test verisi olarak ayrılmıştır. Eğitme aşamasında geçerlilik yöntemleri kullanılarak eğitim tutarlığı sağlanmıştır. Test verileri kullanılarak gerçekleştirilen analizler sonucunda Mel Frekansı Kepstral Katsayıları ve Destek Vektör Makineleri birlikte kullanıldığında en yüksek doğruluk oranı %94,5 olarak elde edilmiştir. Yüksek doğruluk oranı ile programın otomatik teşhisi başarılı bir şekilde gerçekleştirdiği kanıtlanmaktadır. Ayrıca Analiz programı Tıp öğrencilerinin kullanımına sunularak bir diğer hedefine de ulaşmıştır.

Supporting Institution

Manisa Celal Bayar Üniversitesi

Project Number

2017-191

Thanks

Çalışmaya destek olan Manisa Celal Bayar Üniversitesi Hafsa Sultan Hastanesi Göğüs Hastalıkları Anabilim Dalı üyelerine teşekkür ederiz.

References

  • Altan, G., Kutlu, Y., & Allahverdi, N. (2020). Deep learning on computerized analysis of chronic obstructive pulmonary disease. IEEE Journal of Biomedical and Health Informatics, 24(5), 1344–1350. https://doi.org/10.1109/JBHI.2019.2931395
  • Bahoura, M. (2006, May). Separation of crackles from vesicular sounds using wavelet packet transform. In 2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings,(pp. 1076-1079). https://doi.org/10.1109/ICASSP.2006.1660533
  • Bahoura, M. (2009). Pattern recognition methods applied to respiratory sounds classification into normal and wheeze classes. Computers in Biology and Medicine, 39(9), 824–843. https://doi.org/10.1016/j.compbiomed.2009.06.011
  • Başer, F., & Apaydın, A. (2015). Sınıflandırma amaçlı destek vektör makinelerinin lojistik regresyon ile karşılaştırılması. Anadolu Üniversitesi Bilim Ve Teknoloji Dergisi - B Teorik Bilimler, 3(2), 53–65. https://doi.org/10.20290/btdb.67263
  • Demirci, B. A. (2019). Solunum sesleri ile göğüs hastalıklarının teşhisi. Yüksek Lisans Tezi. Manisa Celal Bayar Üniversitesi Fen Bilimleri Enstitüsü Elektrik-Elektronik Mühendisliği Anabilim Dalı, Manisa 104s.
  • Elmas, Ç. (2016). Yapay Zeka Uygulamaları (3rd ed.). Seçkin Yayıncılık. https://www.seckin.com.tr/kitap/n/224686494/title/yapay-zeka-uygulamalari-cetin-elmas.html
  • Gengeç, Ş. (2012). Akciğer seslerinden işaret işleme teknikleri kullanılarak özellik çıkarma ve sınıflandırma. Yüksek Lisans Tezi. Erciyes Üniversitesi Fen Bilimleri Enstitüsü Biyomedikal Mühendisliği Anabilim Dalı, Kayseri 116 s.
  • Göğüş, F. Z. (2015). Biyomedikal seslerin analizi ve sınıflandırılması. Yüksek Lisans Tezi. Selçuk Üniversitesi Fen Bilimleri Enstitüsü Bilgisayar Mühendisliği Anabilim Dalı, Konya 126 s. Güler, I., Polat, H., & Ergün, U. (2005). Combining neural network and genetic algorithm for prediction of lung sounds. Journal of Medical Systems, 29(3), 217–231. https://doi.org/10.1007/s10916-005-5182-9
  • Habukawa, C., Ohgami, N., Arai, T., Makata, H., Tomikawa, M., Fujino, T., Manabe, T., Ogihara, Y., Ohtani, K., Shirao, K., Sugai, K., Asai, K., Sato, T., & Murakami, K. (2021). Wheeze recognition algorithm for remote medical care device in children: validation study. JMIR Pediatric and Parenting 2021;4(2):E28865 Https://Pediatrics.Jmir.Org/2021/2/E28865, 4(2), e28865. https://doi.org/10.2196/28865
  • Haider, N. S., Singh, B. K., Periyasamy, R., & Behera, A. K. (2019). Respiratory Sound Based Classification of Chronic Obstructive Pulmonary Disease: a Risk Stratification Approach in Machine Learning Paradigm. Journal of Medical Systems, 43(8). https://doi.org/10.1007/s10916-019-1388-0
  • Homs-Corbera, A., Fiz, J. A., Morera, J., & Jané, R. (2004). Time-frequency detection and analysis of wheezes during forced exhalation. IEEE Transactions on Biomedical Engineering, 51(1), 182–186. https://doi.org/10.1109/TBME.2003.820359
  • Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Yen, N., Tung, C. C., & Liu, H. H. (1996). The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis. Royal Society of London Proceedings Series A, 454(1), 903–995. https://doi.org/10.1098/rspa.1998.0193
  • Lozano, M., Fiz, J. A., & Jané, R. (2016a). Automatic differentiation of normal and continuous adventitious respiratory sounds using ensemble empirical mode decomposition and ınstantaneous frequency. IEEE Journal of Biomedical and Health Informatics, 20(2), 486–497. https://doi.org/10.1109/JBHI.2015.2396636
  • Lozano, M., Fiz, J. A., & Jané, R. (2016b). Performance evaluation of the hilbert-huang transform for respiratory sound analysis and its application to continuous adventitious sound characterization. Signal Processing, 120, 99–116. https://doi.org/10.1016/j.sigpro.2015.09.005
  • Maruf, S. O., Azhar, M. U., Khawaja, S. G., & Akram, M. U. (2015, December). Crackle separation and classification from normal respiratory sounds using gaussian mixture model. In 2015 IEEE 10th International Conference on Industrial and Information Systems (ICIIS 2015) (pp. 267–271). https://doi.org/10.1109/ICIINFS.2015.7399022
  • Mukherjee, H., Sreerama, P., Dhar, A., Obaidullah, S. M., Roy, K., Mahmud, M., & Santosh, K. C. (2021). Automatic lung health screening using respiratory sounds. Journal of Medical Systems, 45(2). https://doi.org/10.1007/s10916-020-01681-9
  • Palaniappan, R., Sundaraj, K., Ahamed, N., Arjunan, A., & Sundaraj, S. (2013). Computer-based respiratory sound analysis: a systematic review. IETE Technical Review, 33(3), 248-256. https://doi.org/10.4103/0256-4602.113524
  • Pasterkamp, H., Kraman, S. S., & Wodicka, G. R. (1997). State of the art respiratory sounds advances beyond the stethoscope. American Journal of Respiratory and Critical Care Medicine, 156, 974–987. https://doi.org/10.1164/ajrccm.156.3.9701115
  • Pramono, X. A. R., Imtiaz, S. A., & Rodriguez-Villegas, E. (2019). Evaluation of features for classification of wheezes and normal respiratory sounds. PLoS One, 14(3): e0213659.
  • Rioul, O., & Vetterli, M. (1991). Wavelets and signal processing. IEEE Signal Processing Magazine, 8(4), 14–38. https://doi.org/10.1109/79.91217
  • Serbes, G., Sakar, C. O., Kahya, Y. P., & Aydin, N. (2011, August). Feature extraction using time-frequency/scale analysis and esemble of feature sets for crackle detection. In 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE) (pp. 3314-3317). https://doi.org/10.1109/IEMBS.2011.6090899
  • Sunil, N. K. B., & Ganesan, R. (2015). Adaptive neuro-fuzzy ınference system for classification of respiratory signals using cepstral features. International Journal of Applied Engineering Research, 10(28), 22121–22125. http://www.ripublication.com/Volume/ijaerv10n28spl.htm
  • Uysal, S. (2014). Ses Analizi İle Hastalık Teşhisi. Yüksek Lisans Tezi. Yıldız Teknik Üniversitesi Fen Bilimleri Enstitüsü Elektronik ve Haberleşme Mühendisliği Anabilim Dalı Elektronik Programı, İstanbul 82s.
  • Vapnik, V. N. (1998). Statistical learning theory. Wiley.
  • World Health Organization. (2015). WHO World Health Statistics. http://apps.who.int/iris/bitstream/10665/170250/1/9789240694439_eng.pdf?ua=1&ua=1 Accessed 05.03.23.

DEVELOPMENT OF MACHINE LEARNING BASED ANALYSIS PROGRAM FOR DIAGNOSIS OF RESPIRATORY SYSTEM DISEASES

Year 2023, Volume: 26 Issue: 1, 126 - 138, 15.03.2023
https://doi.org/10.17780/ksujes.1181958

Abstract

Respiratory system diseases are medical problem that causes the death of millions of people in the World. Recently, computer aided diagnosis systems are promising in the early diagnosis of respiratory system diseases. The purpose of this study is to develop a diagnostic system that assists the physician with the automatic diagnosis of respiratory sounds from individuals with healthy and varied lung diseases and to allows medical education students to learn their respiratory sounds. In this study, analysis is performed by applying various signal processing methods such as filtering, feature extraction and classification to respiratory sounds. As a result of the analysis, automatic diagnosis is made and possible diseases that the patient may have according to the diagnosis result are listed in the User Interface. The data is divided into training and testing data so that the methods used in the developed program can be trained and tested for their success. Analysis using test data results in the highest accuracy of 94.5% when combined with the Mel Frequency Cepstral Coefficients and Support Vector Machines. High accuracy rate proves that the program successfully performs automatic-diagnosis. The analysis program has been made available to Medical students and so it has achieved another goal.

Project Number

2017-191

References

  • Altan, G., Kutlu, Y., & Allahverdi, N. (2020). Deep learning on computerized analysis of chronic obstructive pulmonary disease. IEEE Journal of Biomedical and Health Informatics, 24(5), 1344–1350. https://doi.org/10.1109/JBHI.2019.2931395
  • Bahoura, M. (2006, May). Separation of crackles from vesicular sounds using wavelet packet transform. In 2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings,(pp. 1076-1079). https://doi.org/10.1109/ICASSP.2006.1660533
  • Bahoura, M. (2009). Pattern recognition methods applied to respiratory sounds classification into normal and wheeze classes. Computers in Biology and Medicine, 39(9), 824–843. https://doi.org/10.1016/j.compbiomed.2009.06.011
  • Başer, F., & Apaydın, A. (2015). Sınıflandırma amaçlı destek vektör makinelerinin lojistik regresyon ile karşılaştırılması. Anadolu Üniversitesi Bilim Ve Teknoloji Dergisi - B Teorik Bilimler, 3(2), 53–65. https://doi.org/10.20290/btdb.67263
  • Demirci, B. A. (2019). Solunum sesleri ile göğüs hastalıklarının teşhisi. Yüksek Lisans Tezi. Manisa Celal Bayar Üniversitesi Fen Bilimleri Enstitüsü Elektrik-Elektronik Mühendisliği Anabilim Dalı, Manisa 104s.
  • Elmas, Ç. (2016). Yapay Zeka Uygulamaları (3rd ed.). Seçkin Yayıncılık. https://www.seckin.com.tr/kitap/n/224686494/title/yapay-zeka-uygulamalari-cetin-elmas.html
  • Gengeç, Ş. (2012). Akciğer seslerinden işaret işleme teknikleri kullanılarak özellik çıkarma ve sınıflandırma. Yüksek Lisans Tezi. Erciyes Üniversitesi Fen Bilimleri Enstitüsü Biyomedikal Mühendisliği Anabilim Dalı, Kayseri 116 s.
  • Göğüş, F. Z. (2015). Biyomedikal seslerin analizi ve sınıflandırılması. Yüksek Lisans Tezi. Selçuk Üniversitesi Fen Bilimleri Enstitüsü Bilgisayar Mühendisliği Anabilim Dalı, Konya 126 s. Güler, I., Polat, H., & Ergün, U. (2005). Combining neural network and genetic algorithm for prediction of lung sounds. Journal of Medical Systems, 29(3), 217–231. https://doi.org/10.1007/s10916-005-5182-9
  • Habukawa, C., Ohgami, N., Arai, T., Makata, H., Tomikawa, M., Fujino, T., Manabe, T., Ogihara, Y., Ohtani, K., Shirao, K., Sugai, K., Asai, K., Sato, T., & Murakami, K. (2021). Wheeze recognition algorithm for remote medical care device in children: validation study. JMIR Pediatric and Parenting 2021;4(2):E28865 Https://Pediatrics.Jmir.Org/2021/2/E28865, 4(2), e28865. https://doi.org/10.2196/28865
  • Haider, N. S., Singh, B. K., Periyasamy, R., & Behera, A. K. (2019). Respiratory Sound Based Classification of Chronic Obstructive Pulmonary Disease: a Risk Stratification Approach in Machine Learning Paradigm. Journal of Medical Systems, 43(8). https://doi.org/10.1007/s10916-019-1388-0
  • Homs-Corbera, A., Fiz, J. A., Morera, J., & Jané, R. (2004). Time-frequency detection and analysis of wheezes during forced exhalation. IEEE Transactions on Biomedical Engineering, 51(1), 182–186. https://doi.org/10.1109/TBME.2003.820359
  • Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Yen, N., Tung, C. C., & Liu, H. H. (1996). The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis. Royal Society of London Proceedings Series A, 454(1), 903–995. https://doi.org/10.1098/rspa.1998.0193
  • Lozano, M., Fiz, J. A., & Jané, R. (2016a). Automatic differentiation of normal and continuous adventitious respiratory sounds using ensemble empirical mode decomposition and ınstantaneous frequency. IEEE Journal of Biomedical and Health Informatics, 20(2), 486–497. https://doi.org/10.1109/JBHI.2015.2396636
  • Lozano, M., Fiz, J. A., & Jané, R. (2016b). Performance evaluation of the hilbert-huang transform for respiratory sound analysis and its application to continuous adventitious sound characterization. Signal Processing, 120, 99–116. https://doi.org/10.1016/j.sigpro.2015.09.005
  • Maruf, S. O., Azhar, M. U., Khawaja, S. G., & Akram, M. U. (2015, December). Crackle separation and classification from normal respiratory sounds using gaussian mixture model. In 2015 IEEE 10th International Conference on Industrial and Information Systems (ICIIS 2015) (pp. 267–271). https://doi.org/10.1109/ICIINFS.2015.7399022
  • Mukherjee, H., Sreerama, P., Dhar, A., Obaidullah, S. M., Roy, K., Mahmud, M., & Santosh, K. C. (2021). Automatic lung health screening using respiratory sounds. Journal of Medical Systems, 45(2). https://doi.org/10.1007/s10916-020-01681-9
  • Palaniappan, R., Sundaraj, K., Ahamed, N., Arjunan, A., & Sundaraj, S. (2013). Computer-based respiratory sound analysis: a systematic review. IETE Technical Review, 33(3), 248-256. https://doi.org/10.4103/0256-4602.113524
  • Pasterkamp, H., Kraman, S. S., & Wodicka, G. R. (1997). State of the art respiratory sounds advances beyond the stethoscope. American Journal of Respiratory and Critical Care Medicine, 156, 974–987. https://doi.org/10.1164/ajrccm.156.3.9701115
  • Pramono, X. A. R., Imtiaz, S. A., & Rodriguez-Villegas, E. (2019). Evaluation of features for classification of wheezes and normal respiratory sounds. PLoS One, 14(3): e0213659.
  • Rioul, O., & Vetterli, M. (1991). Wavelets and signal processing. IEEE Signal Processing Magazine, 8(4), 14–38. https://doi.org/10.1109/79.91217
  • Serbes, G., Sakar, C. O., Kahya, Y. P., & Aydin, N. (2011, August). Feature extraction using time-frequency/scale analysis and esemble of feature sets for crackle detection. In 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE) (pp. 3314-3317). https://doi.org/10.1109/IEMBS.2011.6090899
  • Sunil, N. K. B., & Ganesan, R. (2015). Adaptive neuro-fuzzy ınference system for classification of respiratory signals using cepstral features. International Journal of Applied Engineering Research, 10(28), 22121–22125. http://www.ripublication.com/Volume/ijaerv10n28spl.htm
  • Uysal, S. (2014). Ses Analizi İle Hastalık Teşhisi. Yüksek Lisans Tezi. Yıldız Teknik Üniversitesi Fen Bilimleri Enstitüsü Elektronik ve Haberleşme Mühendisliği Anabilim Dalı Elektronik Programı, İstanbul 82s.
  • Vapnik, V. N. (1998). Statistical learning theory. Wiley.
  • World Health Organization. (2015). WHO World Health Statistics. http://apps.who.int/iris/bitstream/10665/170250/1/9789240694439_eng.pdf?ua=1&ua=1 Accessed 05.03.23.
There are 25 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Electrical and Electronics Engineering
Authors

Burcu Acar Demirci 0000-0002-7328-1267

Yücel Koçyiğit 0000-0003-1785-198X

Project Number 2017-191
Publication Date March 15, 2023
Submission Date September 29, 2022
Published in Issue Year 2023Volume: 26 Issue: 1

Cite

APA Acar Demirci, B., & Koçyiğit, Y. (2023). SOLUNUM SİSTEMİ HASTALIKLARININ TEŞHİSİNE YÖNELİK MAKİNE ÖĞRENMESİ TABANLI ANALİZ PROGRAMI GELİŞTİRİLMESİ. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 26(1), 126-138. https://doi.org/10.17780/ksujes.1181958