Research Article
BibTex RIS Cite

Possibility Prediction Of Diabetes Mellitus At Early Stage Via Stacked Ensemble Deep Neural Network

Year 2021, , 812 - 819, 31.08.2021
https://doi.org/10.35414/akufemubid.946264

Abstract

Diabetes Mellitus is a chronic metabolic disease caused by the deficiency of insülin action or secretion, or both, one of the hormones that balance the blood glocose level. It is one of the health problems that negatively affect people's quality of life. If diabetes is not detected in the early stages, it can cause serious complications such as heart and renal diseases, retinopathy, stroke, digestive disorders, and amputation. Because of the presence of a long asymptomatic period, early detection of diabetes is not realised usually. For this reason, around 50% of diabetic patients are not received a treatment due to undiagnosed at early stages. This situation results other diseases mentioned above, which diabetes causes. On the other hand, ensemble learning is a machine learning model in which multiple models are trained to solve the same problem and combined to achieve better results. Deep neural networks are one of the machine learning algorithms and they are the multi-layered state of artificial neural networks developed inspired by the information processing method of the human brain. In this study, a stacked ensemble-based deep neural network approach is proposed for diabetes possibility assessment in the early stages. The proposed approach was tested on a dataset of 520 patients. As a result, the proposed method achieved the highest success rate with 99.36% accuracy and 99.19% AUC, although the test percentage was kept higher than the prediction studies conducted on the same dataset.

References

  • Alpan, K., and İlgi, G. S. 2020. Classification of Diabetes Dataset with Data Mining Techniques by Using WEKA Approach. 2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), IEEE, 1-7.
  • Awad M., Khanna R., 2015. Deep Neural Networks. Efficient Learning Machines. Apress, Berkeley, 127-147.
  • Coşansu, G., 2015. Diyabet: Küresel bir salgın hastalık. Okmeydanı Tıp Dergisi, 31(ek sayı), 1-6.
  • Davenport, T., and Kalakota, R. 2019. The potential for artificial intelligence in healthcare. Future healthcare journal, 6(2), 94-98.
  • Deshpande, A. D., Harris-Hayes, M., and Schootman, M. (2008). Epidemiology of diabetes and diabetes-related complications. Physical therapy, 88(11), 1254-1264.
  • Dua, D. and Graff, C., 2019. UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science.
  • Efron, B., Hastie, T., Johnstone, I., and Tibshirani, R. 2004. Least angle regression. Annals of statistics, 32(2), 407-499.
  • Federation, Internation Diabetes, 2019. IDF diabetes atlas. ninth edition, Dunia: IDF, 1-168.
  • Godfrey, K. R., 1980. Correlation methods. Automatica, 16(5), 527-534.
  • Hastie, T., Tibshirani, R. and Friedman, J., 2009. The elements of statistical learning: data mining, inference, and prediction, Springer, 1-764.
  • Hossain, M. A., Ferdousi, R., and Alhamid, M. F. 2020. Knowledge-driven machine learning based framework for early-stage disease risk prediction in edge environment. Journal of Parallel and Distributed Computing, 146, 25-34.
  • Hu, Q., Whitney, H. M., and Giger, M. L. 2020. A deep learning methodology for improved breast cancer diagnosis using multiparametric MRI. Scientific reports, 10(1), 1-11.
  • Islam, M. F., Ferdousi, R., Rahman, S., and Bushra, H. Y., 2020. Likelihood prediction of diabetes at early stage using data mining techniques. In Computer Visionand Machine Intelligence in Medical Image Analysis, Springer, 113-125.
  • Jinnai, S., Yamazaki, N., Hirano, Y., Sugawara, Y., Ohe, Y., and Hamamoto, R. 2020. The development of a skin cancer classification system for pigmented skin lesions using deep learning. Biomolecules, 10(8), 1123, 1-13.
  • Kitabchi, A. E., Umpierrez, G.E., Miles, J.M., and Fisher, J.N., 2009. Hyperglycemic crises in adult patients with diabetes. Diabetes care, 32(7), 1335-1343.
  • Le, T. M., Vo, T. M., Pham, T. N., & Dao, S. V. T. 2021. A Novel Wrapper–Based Feature Selection for Early Diabetes Prediction Enhanced With a Metaheuristic. IEEE Access, 9, 7869-7884.
  • Nair, M., 2007. Diabetes mellitus, part 1: physiology and complications. British journal of nursing, 16(3), 184-188.
  • Nelles O., 2020 Neural Networks. Nonlinear System Identification. Springer, Cham. 239-297.
  • Özer, İ., 2020 Uzun Kısa Dönem Bellek Ağlarını Kullanarak Erken Aşama Diyabet Tahmini. Mühendislik Bilimleri ve Araştırmaları Dergisi, 2(2), 50-57.
  • Smith, J. W., Everhart, J. E., Dickson, W. C., Knowler, W. C., and Johannes, R. S., 1988. Using the ADAP learning algorithm to forecast the onset of diabetes mellitus. Proceedings of the annual symposium on computer application in medical care, American Medical Informatics Association, 261-265.
  • Wolpert, D. H. 1992. Stacked generalization. Neural networks, 5(2), 241-259.
  • Zhao, L., Ren, H., Zhang, J., Cao, Y., Wang, Y., Meng, D., Wu, Y., Zhang, R., Zou, Y., Xu, H., Li, L., Zhang, J., Cooper, M.E., Tong, N., Liu, F., 2020. Diabetic retinopathy, classified using the lesion-aware deep learning system, predicts diabetic end-stage renal disease in Chinese patients. Endocrine Practice, 26(4), 429-443. Zhou Z.H., 2009. Ensemble Learning, Li S.Z., Jain A. (eds) Encyclopedia of Biometrics. Springer, Boston, 411-416.
  • 1-https://data.world/abelvikas/diabetes-type-dataset(30.05.2021)

Yığılmış Topluluk Derin Sinir Ağı Aracılığıyla Erken Evrede Diyabet Olasılık Tahmini

Year 2021, , 812 - 819, 31.08.2021
https://doi.org/10.35414/akufemubid.946264

Abstract

Diyabet, kan glikoz düzeyini dengeleyen hormonlardan birisi olan insülin etkisinin veya salgılanmasının ya da her ikisinin eksikliğinden kaynaklanan kronik metabolik bir hastalıktır. İnsanların yaşam kalitesini olumsuz etkileyen sağlık sorunlarından biridir. Şeker hastalığı erken evrelerde tespit edilmezse kalp ve böbrekhastalıkları, retinopati, felç, sindirim bozuklukları ve ampütasyon gibi ciddi komplikasyonlara neden olabilir. Uzun bir asemptomatik dönemin varlığı nedeniyle, şeker hastalığının erken teşhisi genellikle yapılamamaktadır. Bu nedenle diyabet hastalarının yaklaşık %50'si erken evrede teşhis edilemediği için tedavi alamamaktadır. Bu durum diyabetin neden olduğu yukarıda saydığımız diğer hastalıkları da beraberinde getirir. Öte yandan, toplu öğrenme, aynı sorunu çözmek için birden fazla modelin eğitildiği ve daha iyi sonuçlar elde etmek için birleştirildiği bir makine öğrenimi modelidir. Derin sinir ağları, makine öğrenme algoritmalarından biridir ve insan beyninin bilgi işleme yönteminden esinlenerek geliştirilen yapay sinir ağlarının çok katmanlı halidir. Bu çalışmada, erken aşamalarda diyabet olasılık değerlendirmesi için yığılmış topluluk tabanlı bir derin sinir ağı yaklaşımı önerilmiştir. Önerilen yaklaşım, 520 hastadan oluşan bir veri seti üzerinde test edildi. Sonuç olarak önerilen yöntem, aynı veri seti üzerinde yapılan tahmin çalışmalarına göre test yüzdesi daha yüksek tutulmasına rağmen % 99.36 doğruluk ve % 99.19 AUC ile en yüksek başarı oranını elde etmiştir.

References

  • Alpan, K., and İlgi, G. S. 2020. Classification of Diabetes Dataset with Data Mining Techniques by Using WEKA Approach. 2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), IEEE, 1-7.
  • Awad M., Khanna R., 2015. Deep Neural Networks. Efficient Learning Machines. Apress, Berkeley, 127-147.
  • Coşansu, G., 2015. Diyabet: Küresel bir salgın hastalık. Okmeydanı Tıp Dergisi, 31(ek sayı), 1-6.
  • Davenport, T., and Kalakota, R. 2019. The potential for artificial intelligence in healthcare. Future healthcare journal, 6(2), 94-98.
  • Deshpande, A. D., Harris-Hayes, M., and Schootman, M. (2008). Epidemiology of diabetes and diabetes-related complications. Physical therapy, 88(11), 1254-1264.
  • Dua, D. and Graff, C., 2019. UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science.
  • Efron, B., Hastie, T., Johnstone, I., and Tibshirani, R. 2004. Least angle regression. Annals of statistics, 32(2), 407-499.
  • Federation, Internation Diabetes, 2019. IDF diabetes atlas. ninth edition, Dunia: IDF, 1-168.
  • Godfrey, K. R., 1980. Correlation methods. Automatica, 16(5), 527-534.
  • Hastie, T., Tibshirani, R. and Friedman, J., 2009. The elements of statistical learning: data mining, inference, and prediction, Springer, 1-764.
  • Hossain, M. A., Ferdousi, R., and Alhamid, M. F. 2020. Knowledge-driven machine learning based framework for early-stage disease risk prediction in edge environment. Journal of Parallel and Distributed Computing, 146, 25-34.
  • Hu, Q., Whitney, H. M., and Giger, M. L. 2020. A deep learning methodology for improved breast cancer diagnosis using multiparametric MRI. Scientific reports, 10(1), 1-11.
  • Islam, M. F., Ferdousi, R., Rahman, S., and Bushra, H. Y., 2020. Likelihood prediction of diabetes at early stage using data mining techniques. In Computer Visionand Machine Intelligence in Medical Image Analysis, Springer, 113-125.
  • Jinnai, S., Yamazaki, N., Hirano, Y., Sugawara, Y., Ohe, Y., and Hamamoto, R. 2020. The development of a skin cancer classification system for pigmented skin lesions using deep learning. Biomolecules, 10(8), 1123, 1-13.
  • Kitabchi, A. E., Umpierrez, G.E., Miles, J.M., and Fisher, J.N., 2009. Hyperglycemic crises in adult patients with diabetes. Diabetes care, 32(7), 1335-1343.
  • Le, T. M., Vo, T. M., Pham, T. N., & Dao, S. V. T. 2021. A Novel Wrapper–Based Feature Selection for Early Diabetes Prediction Enhanced With a Metaheuristic. IEEE Access, 9, 7869-7884.
  • Nair, M., 2007. Diabetes mellitus, part 1: physiology and complications. British journal of nursing, 16(3), 184-188.
  • Nelles O., 2020 Neural Networks. Nonlinear System Identification. Springer, Cham. 239-297.
  • Özer, İ., 2020 Uzun Kısa Dönem Bellek Ağlarını Kullanarak Erken Aşama Diyabet Tahmini. Mühendislik Bilimleri ve Araştırmaları Dergisi, 2(2), 50-57.
  • Smith, J. W., Everhart, J. E., Dickson, W. C., Knowler, W. C., and Johannes, R. S., 1988. Using the ADAP learning algorithm to forecast the onset of diabetes mellitus. Proceedings of the annual symposium on computer application in medical care, American Medical Informatics Association, 261-265.
  • Wolpert, D. H. 1992. Stacked generalization. Neural networks, 5(2), 241-259.
  • Zhao, L., Ren, H., Zhang, J., Cao, Y., Wang, Y., Meng, D., Wu, Y., Zhang, R., Zou, Y., Xu, H., Li, L., Zhang, J., Cooper, M.E., Tong, N., Liu, F., 2020. Diabetic retinopathy, classified using the lesion-aware deep learning system, predicts diabetic end-stage renal disease in Chinese patients. Endocrine Practice, 26(4), 429-443. Zhou Z.H., 2009. Ensemble Learning, Li S.Z., Jain A. (eds) Encyclopedia of Biometrics. Springer, Boston, 411-416.
  • 1-https://data.world/abelvikas/diabetes-type-dataset(30.05.2021)
There are 23 citations in total.

Details

Primary Language English
Subjects Artificial Intelligence
Journal Section Articles
Authors

Ahmet Haşim Yurttakal 0000-0001-5170-6466

Hatice Baş 0000-0001-8296-0360

Publication Date August 31, 2021
Submission Date June 1, 2021
Published in Issue Year 2021

Cite

APA Yurttakal, A. H., & Baş, H. (2021). Possibility Prediction Of Diabetes Mellitus At Early Stage Via Stacked Ensemble Deep Neural Network. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, 21(4), 812-819. https://doi.org/10.35414/akufemubid.946264
AMA Yurttakal AH, Baş H. Possibility Prediction Of Diabetes Mellitus At Early Stage Via Stacked Ensemble Deep Neural Network. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi. August 2021;21(4):812-819. doi:10.35414/akufemubid.946264
Chicago Yurttakal, Ahmet Haşim, and Hatice Baş. “Possibility Prediction Of Diabetes Mellitus At Early Stage Via Stacked Ensemble Deep Neural Network”. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi 21, no. 4 (August 2021): 812-19. https://doi.org/10.35414/akufemubid.946264.
EndNote Yurttakal AH, Baş H (August 1, 2021) Possibility Prediction Of Diabetes Mellitus At Early Stage Via Stacked Ensemble Deep Neural Network. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi 21 4 812–819.
IEEE A. H. Yurttakal and H. Baş, “Possibility Prediction Of Diabetes Mellitus At Early Stage Via Stacked Ensemble Deep Neural Network”, Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, vol. 21, no. 4, pp. 812–819, 2021, doi: 10.35414/akufemubid.946264.
ISNAD Yurttakal, Ahmet Haşim - Baş, Hatice. “Possibility Prediction Of Diabetes Mellitus At Early Stage Via Stacked Ensemble Deep Neural Network”. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi 21/4 (August 2021), 812-819. https://doi.org/10.35414/akufemubid.946264.
JAMA Yurttakal AH, Baş H. Possibility Prediction Of Diabetes Mellitus At Early Stage Via Stacked Ensemble Deep Neural Network. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi. 2021;21:812–819.
MLA Yurttakal, Ahmet Haşim and Hatice Baş. “Possibility Prediction Of Diabetes Mellitus At Early Stage Via Stacked Ensemble Deep Neural Network”. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, vol. 21, no. 4, 2021, pp. 812-9, doi:10.35414/akufemubid.946264.
Vancouver Yurttakal AH, Baş H. Possibility Prediction Of Diabetes Mellitus At Early Stage Via Stacked Ensemble Deep Neural Network. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi. 2021;21(4):812-9.

Cited By

INTERNET OF THINGS BOTNET DETECTION VIA ENSEMBLE DEEP NEURAL NETWORKS
International Journal of 3D Printing Technologies and Digital Industry
https://doi.org/10.46519/ij3dptdi.1293277


Bu eser Creative Commons Atıf-GayriTicari 4.0 Uluslararası Lisansı ile lisanslanmıştır.