Diabetes Prediction Using Bi-directional Long Short-Term Memory

被引：0

作者：

Jaiswal S. ^{[1
]}

Gupta P. ^{[1
]}

机构：

[1] Computer Science & Information Technology, Guru Ghasidas Vishwavidyalaya, C.G., Bilaspur

来源：

SN Computer Science | / 4卷 / 4期

关键词：

BLSTM; Classification; DM; LSTM; ML; PID;

D O I：

10.1007/s42979-023-01831-z

中图分类号：

学科分类号：

摘要：

The chronic nature of diabetes makes it the most complex and lethal health issue globally. This creates difficulties in managing this illness in the day-to-day life of a large population of affected people. Diabetes is also known as diabetes mellitus (DM). This research aims to reduce diabetic patients’ pain and make their lives easier and more comfortable. This paper describes an expert system for diabetes mellitus classification. This study's evaluations presided over the Pima Indian Diabetes (PID) data set. We proposed a bi-directional long short-term memory (BLSTM)-based approach to diagnose diabetes mellitus at an earlier stage. The proposed methodology is novel, and the model is tuned for maximum attainment by varying the divergent range of parameters. The network attributes are trained using a tenfold cross-validation approach. Data pre-processing techniques play a vital role in this case. The class-balancer synthetic minority oversampling technique (SMOTE) was used to balance the data. The proposed BLSTM model provides better accuracy, sensitivity, specificity, and F1 score with values of 94%, 96%, 91%, and 93%, respectively. Our results demonstrate that the proposed model outperforms earlier studies in classifying diabetic patients. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

引用

共 46 条

[1] Dremin V., Marcinkevics Z., Zherebtsov E., Popov A., Grabovskis A., Kronberga H., Geldnere K., Doronin A., Meglinski I., Bykov A., Skin complications of diabetes mellitus revealed by polarized hyperspectral imaging and machine learning, IEEE Trans Med Imaging, 40, 4, pp. 1207-1216, (2021)
[2] Krishnamoorthi R., Joshi S., Almarzouki H.Z., Shukla P.K., Rizwan A., Kalpana C., Tiwari B., A novel diabetes healthcare diabetes prediction framework using machine learning techniques, J Healthc Eng, (2022)
[3] Saxena R., Sharma S.K., Gupta M., Sampada G.C., A novel approach for feature selection and classification of diabetes mellitus: machine learning methods, Comput Intell Neurosci, (2022)
[4] Sivashankari R., Sudha M., Hasan M.K., Saeed R.A., Alsuhibany S.A., Abdel-Khalek S., An empirical model to predict the diabetic positive using stacked ensemble approach, Front Public Health, 9, (2022)
[5] Wu H., Et al., Type 2 diabetes mellitus prediction model based on data mining, Inform Med Unlock, 10, pp. 100-107, (2018)
[6] Syed A.H., Khan T., Machine learning-based application for predicting risk of type 2 diabetes mellitus (T2DM) in Saudi Arabia: a retrospective cross-sectional study, IEEE Access, 8, pp. 199539-199561, (2020)
[7] Choubey D.K., Kumar P., Tripathi S., Kumar S., Performance evaluation of classification methods with PCA and PSO for diabetes, Netw Model Anal Health Inform Bioinform, (2020)
[8] Katarya R., Jain S., Comparison of Different Machine Learning Models for diabetes detection, IEEE International Conference on Advances and Developments in Electrical and Electronics Engineering (ICADEE), pp. 1-5, (2020)
[9] Kulkarni B.P., Analysis of classifiers for prediction of type II diabetes mellitus, Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), pp. 1-6, (2018)
[10] Woldemichael F.G., Menaria S., Prediction of diabetes using data mining techniques, 2Nd International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, pp. 414-418, (2018)

← 1 2 3 4 5 →