Establishment of Risk Prediction Model for Retinopathy in Type 2 Diabetic Patients
Diabetic retinopathy (DR) is one of the complications of diabetes mellitus, which is an important manifestation of diabetic microangiopathy and major cause of vision loss in middle-aged and elderly people worldwide. Establishing a risk prediction model for diabetic retinopathy can discover high-risk groups and early warn diabetic retinopathy, which can effectively reduce the medical cost of diabetes. The experimental data was derived from the electronic medical records of a tertiary hospital of Beijing from 2013 to 2017, including 29 inspection indicators. In this study, we compared the predictive models of type 2 diabetes mellitus complicated with retinopathy, and finally selected the random forest method to construct the risk prediction model. The weights of each index are analyzed by linear regression algorithm, the combination of inspection indicators with the highest accuracy is selected, and the random forest model is optimized to improve the accuracy of the classification prediction model, accuracy increased by 3.7264%. The predictive model provides a basis for early diagnosis of diabetic retina and optimization of the diagnostic process.
KeywordsType 2 diabetic retinopathy Risk prediction model Random forest algorithm Linear regression analysis
This work is supported by the CERNET Innovation Project (No. NGII20170719) and the Beijing Municipal Education Commission.
- 1.Field, R.A.: The current status of hormonal suppression in the treatment of diabetic retinopathy. Trans. – Am. Acad. Ophthalmol. Otolaryngol. 72(2), 241–245 (1968)Google Scholar
- 2.Zheng, Z.: Clinical prevention and treatment of diabetic retinopathy: progress, challenges and prospects. Chin. J. Fundus Dis. 28(3), 209–213 (2012)Google Scholar
- 5.Levy, J.C., Cull, C.A., Stratton, I.M.: The UKPDS study on glycemic control and arterial hypertension in type II diabetes: objectives, structure and preliminary results. J. Annu. Diabetol. Hotel Dieu (1993)Google Scholar
- 8.Ge, L.I., Jin, L.Z.: Establishing a model for predicting diabetes complications based on the LVQ neural work. Chin. J. Nat. Med. (2006)Google Scholar
- 9.Wang, Z., Song, Z., Bai, J.: Decision tree analysis of nephropathy risk in patients with type 2 diabetes mellitus. Chin. J. Integr. Tradit. West. Med. Nephrol. 14(3), 238–239 (2013)Google Scholar
- 10.Geng, L., Li, X.: Research on KNN algorithm for big data classification. J. Comput. Appl. 31(5), 1342–1344 (2014)Google Scholar
- 12.Freund, Y., Mason, L.: The alternating decision tree learning algorithm. In: Proceeding of the, International Conference on Machine Learning, pp. 124–133. Morgan Kaufmann (1999)Google Scholar
- 15.Cutler, A., Cutler, D.R., Stevens, J.R.: Random forests. Mach. Learn. 45(1), 157–176 (2004)Google Scholar
- 20.Archer, K.J., Kimes, R.V.: Empirical characterization of random forest variable importance measures. Elsevier Science Publishers B. V. (2008)Google Scholar