A Novel Intelligent System for Detection of Type 2 Diabetes with Modified Loss Function and Regularization

Type 2 Diabetes (T2DM) makes up about 90% of diabetes cases, as well as tough restriction on continuous monitoring and detecting become one of key aspects in T2DM. This research aims to develop an ensemble of several machine learning and deep learning models for early detection of T2DM with high accuracy. With high diversity of models, the ensemble will provide more excessive performance than single models.  Methodology: The proposed system is modified enhanced ensemble of machine learning models for T2DM prediction. It is composed of Logistic Regression, Random Forest, SVM and Deep Neural Network models to generate a modified ensemble model.  Results: The output of each model in the modified ensemble is used to figure out the final output of the system. The datasets being used for these models include Practice Fusion HER, Pima Indians diabetic's data, UCI AIM94 Dataset and CA Diabetes Prevalence 2014. In comparison to the previous solutions, the proposed ensemble model solution exposes the effectiveness of accuracy, sensitivity, and specificity. It provides an accuracy of 87.5% from 83.51% in average, sensitivity of 35.8% from 29.59% as well as specificity of 98.9% from 96.27%. The processing time of the proposed model solution with 96.6ms is faster than the state-of-the-art with 97.5ms. Conclusion: The proposed modified enhanced system in this work improves the overall prediction capability of T2DM using an ensemble of several machine learning and deep learning models. A majority voting scheme utilizes the output from several models to make the final accurate prediction. Regularization function in this work is modified in order to include the regularization of all the models in ensemble, that helps prevent the overfitting and encourages the generalization capacity of the proposed system.

1. Bernardini M., Romeo L., Misericordia P., and Frontoni E. Discovering the Type 2 Diabetes in Electronic Health Records Using the Sparse Balanced Support Vector Machine. IEEE Journal of Biomedical and Health Informatics, vol. 24, no. 1, 2020, pp. 235-246.

2. Houri. O., Gil. Y., Berezowsky A., Wiznitzer A. et al. 339: Future Type-2 diabetes prediction following pregnancy – using a novel machine learning, American Journal of Obstetrics and Gynecology, vol. 222, issue 1, Supplement, 2020, p. S228.

3. Kölle Konstanze, Biester Torben, Christiansen Sverre et al. Pattern Recognition Reveals Characteristic Postprandial Glucose Changes: Non-Individualized Meal Detection in Diabetes Mellitus Type 1. IEEE Journal of Biomedical and Health Informatics, vol. 24, no. 2, 2020, pp. 594-602.

4. Kezhi Li, John Daniels, Chengyuan Liu et al. Convolutional Recurrent Neural Networks for Glucose Prediction. IEEE Journal of Biomedical and Health Informatics vol. 24, no. 2, 2020, pp. 603-613.

5. Binh P. Nguyen, Hung N Pham, Hop Tran et al. Predicting the onset of type 2 diabetes using wide and deep learning with electronic health records. Computer Methods and Programs in Biomedicine, vol. 182, 2019, article id 105055.

6. Perveen S., Shahbaz M., Saba T. et al. Handling irregularly sampled longitudinal data and prognostic modeling of diabetes using machine learning technique. IEEE Access, vol. 8, 2000, pp. 21875-21885.

7. Vivek Rai, Daniel X. Quang, Michael R. Erdos et al. Single-cell ATAC-Seq in human pancreatic islets and deep learning upscaling of rare cells reveals cell-specific type 2 diabetes regulatory signatures. Molecular Metabolism, vol. 32, 2020, pp. 109-121.

8. Ramazi Ramin, Perndorfer Christine, Soriano C.E. et al. Multi-modal Predictive Models of Diabetes Progression. In Proc. of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 2019, pp. 253-258.

9. Sierra-Sosa D., Garcia-Zapirain B., Castillo C. et al. Scalable Healthcare Assessment for Diabetic Patients Using Deep Learning on Multiple GPUs. IEEE Transactions on Industrial Informatics, vol. 15, no. 10, 2019, pp. 5682 – 5689.

10. Agata Wesolowska-Andersen, Grace Zhuo Yu, Vibe Nylander et al. Deep learning models predict regulatory variants in pancreatic islets and refine type 2 diabetes association signals. eLife 2020;9:e51503, 2020.

11. Tomohide Yamada, Kosuke Iwasaki, Shotaro Maedera et al. Myocardial infarction in type 2 diabetes using sodium–glucose co-transporter-2 inhibitors, dipeptidyl peptidase-4 inhibitors or glucagon-like peptide-1 receptor agonists: proportional hazards analysis by deep neural network based machine learning. Current Media Research and Option, vol. 36, no. 3, 2000, pp. 404-410.

12. Zaitcev A., Eissa R.M., Hui Z. et al. A Deep Neural Network Application for Improved Prediction of HbA1c in Type 1 Diabetes, IEEE Journal of Biomedical and Health Informatics, vol. 24, no. 10, 2020, pp. 2932-2941.

13. Xianglong Zeng, Haiquan Chen, Yuan Luo, and Wenbin Ye. Automated Diabetic Retinopathy Detection Based on Binocular Siamese-Like Convolutional Neural Network, IEEE Access, vol. 7, 2019, pp. 30744-30753.

14. Anuradha, Akansha Singh, and Gaurav Gupta. ANT FDCSM: A novel fuzzy rule miner derived from ant colony meta-heuristic for diagnosis of diabetic patients. Journal of Intelligent & Fuzzy Systems, vol. 36, no. 1, 2019, pp. 747-760.

15. Muhammad Fazal Ijaz, Ganjar Alfian, Muhammad Syafrudin, and Jongtae Rhee. Hybrid Prediction Model for Type 2 Diabetes and Hypertension Using DBSCAN-Based Outlier Detection, Synthetic Minority Over Sampling Technique (SMOTE), and Random Forest, Applied Sciences, vol. 8, no. 8, 2018, pp. 1-22.