With the development of artificial intelligence, society will definitely become smarter in the future. More and more intelligent and convenient products will appear in everyone's life. For the medical industry, the huge amount of data generated is a valuable asset. How to discover the patterns of diseases in these data and improve the efficiency and accuracy of disease prediction through scientific means has become a hot issue for research nowadays. The main objective of this paper is to investigate the prediction of diabetes based on the RFA. In this paper, the RF algorithm (RFA) is used to analyse diabetes data, and the method is proposed based on the study of different DP models to improve the effectiveness of diabetes prediction (DP). Based on the RF-based ranking of feature importance, the features are added to the set of features to be evaluated in order of importance; for the proposed model is unable to perform effective feature selection, greedy feature selection based on RF is incorporated to further improve the accuracy of the DP model. The system was tested and experimented with, and the results showed that the prototype system of the DP model can effectively achieve the prediction function of diabetes.

Jie Cai. Diabetes Prediction Based on Random Forest Algorithm. Machine Learning Theory and Practice (2021), Vol. 2, Issue 4: 1-9. https://doi.org/10.38007/ML.2021.020401.

[1] Leila Yousefi, Allan Tucker: Identifying latent variables in Dynamic Bayesian Networks with bootstrapping applied to Type 2 Diabetes complication prediction. Intell. Data Anal. 26(2): 501-524 (2021). https://doi.org/10.3233/IDA-205570

[2] Jafar Abdollahi, Babak Nouri-Moghaddam: Hybrid stacked ensemble combined with genetic algorithms for DP. Iran J. Comput. Sci. 5(3): 205-220 (2021). 

[3] Mohammad Zubair Khan, Mangayarkarasi Ramaiah, Vanmathi Chandrasekaran, M. Angulakshmi: Bio-Inspired PSO for Improving Neural Based DP System. J. ICT Stand. 10(2): 179-200 (2021).

[4] Chandrashekhar Azad, Bharat Bhushan, Rohit Sharma, Achyut Shankar, Krishna Kant Singh, Aditya Khamparia: Prediction model using SMOTE, genetic algorithm and decision tree (PMSGD) for classification of diabetes mellitus. Multim. Syst. 28(4): 1289-1307 (2021). https://doi.org/10.1007/s00530-021-00817-2

[5] Suja A. Alex, J. Jesu Vedha Nayahi, H. Shine, Vaisshalli Gopirekha: Deep convolutional neural network for diabetes mellitus prediction. Neural Comput. Appl. 34(2): 1319-1327 (2021). https://doi.org/10.1007/s00521-021-06431-7

[6] Nora El-Rashidy, Nesma E. ElSayed, Amir El-Ghamry, Fatma M. Talaat: Prediction of gestational diabetes based on explainable deep learning and fog computing. Soft Comput. 26(21): 11435-11450 (2021). 

[7] Simone Faccioli, Andrea Facchinetti, Giovanni Sparacino, Gianluigi Pillonetto, Simone Del Favero: Linear Model Identification for Personalized Prediction and Control in Diabetes. IEEE Trans. Biomed. Eng. 69(2): 558-568 (2021). https://doi.org/10.1109/TBME.2021.3101589

[8] Julian Theis, William L. Galanter, Andrew D. Boyd, Houshang Darabi: Improving the In-Hospital Mortality Prediction of Diabetes ICU Patients Using a Process Mining/Deep Learning Architecture. IEEE J. Biomed. Health Informatics 26(1): 388-399 (2021). https://doi.org/10.1109/JBHI.2021.3092969

[9] Hatice Nizam Ozogur, Gokhan Ozogur, Zeynep Orman: Blood glucose level prediction for diabetes based on modified fuzzy time series and particle swarm optimization. Comput. Intell. 37(1): 155-175 (2021). https://doi.org/10.1111/coin.12396

[10] Jobeda Jamal Khanam, Simon Y. Foo: A comparison of machine learning algorithms for DP. ICT Express 7(4): 432-439 (2021). https://doi.org/10.1016/j.icte.2021.02.004

[11] Anand Kumar Srivastava, Yugal Kumar, Pradeep Kumar Singh: Artificial Bee Colony and Deep Neural Network-Based Diagnostic Model for Improving the Prediction Accuracy of Diabetes. Int. J. E Health Medical Commun. 12(2): 32-50 (2021). https://doi.org/10.4018/IJEHMC.2021030102

[12] Asma Ahmed Abokhzam, N. K. Gupta, Dipak Kumar Bose: Efficient diabetes mellitus prediction with grid based RF classifier in association with natural language processing. Int. J. Speech Technol. 24(3): 601-614 (2021). https://doi.org/10.1007/s10772-021-09825-z

[13] P. Preethy Rebecca, S. Allwin: Detection of DR from retinal fundus images using prediction ANN classifier and RG based threshold segmentation for diabetes. J. Ambient Intell. Humaniz. Comput. 12(12): 10733-10740 (2020). https://doi.org/10.1007/s12652-020-02882-3

[14] Shiva Shankar Reddy, Nilambar Sethi, R. Rajender: Rigorous assessment of data mining algorithms in gestational diabetes mellitus prediction. Int. J. Knowl. Based Intell. Eng. Syst. 25(4): 369-383 (2021). https://doi.org/10.3233/KES-210081