Prediction of Diabetes Mellitus Using LightGBM Classifier with RF-RFECV

doi:10.3969/j.issn.1006-2475.2023.11.006

Abstract

Abstract: Abstract: In order to find the high-risk population of diabetes in China as early as possible and provide targeted intervention measures， the data set of China Health and Retirement Longitudinal Study （CHARLS）， which represents the Chinese population， was selected as the research object， and a hybrid algorithm based on RF-RFECV and LightGBM （RF-RFECV-LightGBM） was proposed， and compared with five other algorithms through experiments. The results show that RF-RFECV- LightGBM has the best overall performance， the accuracy， precision， recall， F1 value and AUC value are 0.9772， 0.9952， 0.8178， 0.8978， and 0.9357， respectively. The prediction time is 0.0428 s， which is 0.0549 s shorter than the prediction time of LightGBM before feature selection （increased by 56.19%）， indicating the effectiveness of RF-RFECV algorithm. Finally， the same prediction process was tested on the Pima Indian dataset， and the results achieved an accuracy of 0.9415， further verifying the excellent performance of the proposed algorithm RF-RFECV-LightGBM， which can assist in clinical diagnosis and treatment of diabetes.

Key words: Key words: LightGBM, RF-RFECV, prediction of diabetes, CHARLS, Pima

CLC Number:

TP391

LIU Jing-le, LUO Xiang, GONG Cheng-rong, ZHANG Guo-peng. Prediction of Diabetes Mellitus Using LightGBM Classifier with RF-RFECV[J]. Computer and Modernization, 2023, 0(11): 36-43.

References ［26］

［1］	JAISWAL V， NEGI A， PAL T. A review on current advances in machine learning based diabetes prediction［J］. Primary Care Diabetes， 2021，15（3）:435-443.
［2］	WANG X C， ZHAI M M， REN Z P， et al. Exploratory study on classification of diabetes mellitus through a combined Random Forest Classifier［J］. BMC Medical Informatics and Decision Making， 2021，21（1）:105. DOI: 10.1186/s12911-021-01471-4.
［3］	GÜNDOĞDU S. Efficient prediction of early-stage diabetes using XGBoost classifier with random forest feature selection technique［J］. Multimedia Tools and Applications， 2023，82:34163-34181.
［4］	LI Z J， PANG S L， QU H Y， et al. Logistic regression prediction models and key influencing factors analysis of diabetes based on algorithm design［J］. Neural Computing and Applications， 2023. DOI: 10.1007/s00521-023-08447-7.
［5］	XIONG X L， ZHANG R X， BI Y， et al. Machine learning models in type 2 diabetes risk prediction: Results from a cross-sectional retrospective study in Chinese adults［J］. Current Medical Science， 2019，39（4）:582-588.
［6］	SAI M J， CHETTRI P， PANIGRAHI R， et al. An ensemble of light gradient boosting machine and adaptive boosting for prediction of type-2 diabetes［J］. International Journal of Computational Intelligence Systems， 2023，16. DOI: 10.1007/s44196-023-00184-y.
［7］	AZAD C， BHUSHAN B， SHARMA R， et al. Prediction model using SMOTE， genetic algorithm and decision tree （PMSGD） for classification of diabetes mellitus［J］. Multimedia Systems， 2022，28（4）:1289-1307.
［8］	KUMAR P B M， PERUMAL R S， NADESH R K， et al. Type 2: Diabetes mellitus prediction using deep neural networks classifier［J］. International Journal of Cognitive Computing in Engineering， 2020，1:55-61.
［9］	王鑫，廖彬，李敏，等. 融合LightGBM与SHAP的糖尿病预测及其特征分析方法［J］. 小型微型计算机系统， 2022，43（9）:1877-1885.
［10］	GLUMER C， VISTISEN D， BORCH-JOHNSEN K， et al. Risk scores for type 2 diabetes can be applied in some populations but not all［J］. Diabetes Care， 2006，29（2） 410-414.
［11］	张乐，王如意，杨慧，等. 重采样技术在中老年居民糖尿病不平衡数据分类中的应用［J］. 现代预防医学， 2023，50（7）:1339-1344.
［12］	ZHENG X W， JIANG M L， REN X， et al. The longitudinal association of remnant cholesterol with diabetes in middle-aged and elderly Chinese: A nationwide population
	-based cohort study［J］. Journal of Diabetes and its Complications， 2023，37（1）:108360.
［13］	CHEN X， CRIMMINS E， HU P P， et al. Venous blood-based biomarkers in the China health and retirement longitudinal study: Rationale， design， and results from the 2015 wave［J］. American Journal of Epidemiology， 2019，188（11）:1871-1877.
［14］	王富军，王文琦.《中国2型糖尿病防治指南（2020年版）》解读［J］. 河北医科大学学报， 2021， 42（12）:1365-1371.
［15］	吴辰文，梁靖涵，王伟，等. 基于递归特征消除方法的随机森林算法［J］. 统计与决策， 2017（21）:60-63.
［16］	任高科，莫秀良. 基于PRF-RFECV特征优选的GA-LightGBM的网络安全态势评估［J］. 计算机科学， 202350（S1）:769-774.
［17］	张伟，王连彪，张广帅. 基于RF-RFECV和PSO-SVM的化工过程故障诊断方法［J］. 青岛科技大学学报（自然科学版）， 2022，43（5）:101-108.
［18］	张兵，张校梁，屈永强，等. 采用特征变量选择和长短期记忆网络的高速公路交通事件检测研究［J］. 重庆理工大学学报， 2023，37（8）:157-165.
［19］	KE G L， MENG Q， FINLEY T， et al．LightGBM: A highly efficient gradient boosting decision tree［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems（ NIPS'17）. 2017:3149-3157.
［20］	QI H M， SONG X M， LIU S Z， et al. KFPredict: An ensemble learning prediction framework for diabetes based on fusion of key features［J］. Computer Methods and Programs in Biomedicine， 2023，231:107378.
［21］	KUMARI S， KUMAR D， MITTAL M. An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier［J］. International Journal of Cognitive Computing in Engineering， 2021，2:40-46.
［22］	ISHWARYA M S， CHERUKURI A K. Quantum-inspired ensemble approach to multi-attributed and multi-agent decision-making［J］. Applied Soft Computing， 2021，106:107283. DOI: 10.1016/j.asoc.2021.107283.
［23］	SISODIA D， SISODIA D S. Prediction of diabetes using classification algorithms［J］. Procedia Computer Science， 2018，132:1578-1585.
［24］	欧阳平，李小溪，冷芬，等. 机器学习算法在体检人群糖尿病风险预测中的应用［J］. 中华疾病控制杂志， 2021，25（7）:849-853.
［25］	LAI H， HUANG H X， KESHAVJEE K， et al. Predictive models for diabetes mellitus using machine learning techniques［J］. BMC Endocrine Disorders. 2019，19:101. DOI:10.1186/s12902-019-0436-6.
［26］	WANG K， GONG M H， XIE S P， et al. Nomogram prediction for the 3-year risk of type 2 diabetes in healthy mainland China residents［J］. EPMA Journal. 2019，10（3）:227-237.

[1]	TANG Shi-qi, ZHOU Rui-ping, XIE Shi-bin, LIU Meng-chi, XIAO Wen, . Cross-language Multi-label Sentiment Classification Based on Stacked Denoising AutoEncoder [J]. Computer and Modernization, 2023, 0(11): 6-12.
[2]	LUO Ming-jie, FENG Kai-ping. Lightweight Facial Expression Recognition Method Based on Sandglass Structure and Attention Mechanism [J]. Computer and Modernization, 2023, 0(11): 89-94.
[3]	YAN Zi-xian, DONG Bao-liang, TANG Si-mi. Improved YOLOv7 Algorithm for Low-resolution Ship Object Detection in Complex Backgrounds#br# [J]. Computer and Modernization, 2023, 0(11): 120-126.
[4]	ZHENG Hai-li, CHEN Ping-hua. Sequence Recommendation Model Based on Dynamic Convolution and Self-attention [J]. Computer and Modernization, 2023, 0(10): 9-16.
[5]	JIA Xiao-yao, . Breast Cancer Prediction and Feature Analysis Model Based on CatBoost and SHAP [J]. Computer and Modernization, 2023, 0(10): 32-38.
[6]	XING Shi-shuai, LIU Dan-feng, WANG Li-guo, PAN Yue-tao, MENG Ling-hong, YUE Xiao-han. Image Super-resolution Reconstruction Based on Spatial Attention Residual Network [J]. Computer and Modernization, 2023, 0(10): 45-52.
[7]	LIU Xin, LIU Yi. Two-factor Authentication Scheme Based on Smart Contract [J]. Computer and Modernization, 2023, 0(10): 121-126.
[8]	GONG Dingxi, CAO Changrong. Plant Leaf Classification Based on CNN [J]. Computer and Modernization, 2014, 0(4): 12-15.
[9]	WU Ning, GUAN Shengqi, XU Shuaihua. Fabric Defect Detection Based on Periodicity and Local Directivity of Texture Edge [J]. Computer and Modernization, 2014, 0(4): 16-19.
[10]	YIN Shile， ZENG Zhiyong. An Improved Nystrom Spectral Clustering for Image Segmentation [J]. Computer and Modernization, 2014, 0(4): 20-23.
[11]	SUI Jiankai1, LIU Huiyi1,YAN Shuo2. Feature Matching Method Based on Random Forests Classifier [J]. Computer and Modernization, 2014, 0(4): 81-85.
[12]	WU Chun， LIANG Zhengyou. Cochannel Speech Separation Based on Clustering [J]. Computer and Modernization, 2014, 0(4): 86-88.
[13]	LIU Yang, FU Zhonghua, TANG Ling. A Dualchannel Acoustic Echo Canceler on Windows Platform [J]. Computer and Modernization, 2014, 0(4): 199-202.