Application of Improved LightGBM Model in Blood Glucose Prediction

In recent years, with increasing social pressure and irregular schedules, many people have developed unhealthy eating habits, which has resulted in an increasing number of patients with diabetes, a disease that cannot be cured under the current medical conditions, and can only be mitigated by early detection and prevention. A lot of human and material resources are required for the detection of the blood glucose of a large number of people in medical examination, while the integrated learning model based on machine learning can quickly predict the blood glucose level and assist doctors in treatment. Therefore, an improved LightGBM model based on the Bayesian hyper-parameter optimization algorithm is proposed for the prediction of blood glucose, namely HY_LightGBM, which optimizes parameters using a Bayesian hyper-parameter optimization algorithm based on LightGBM. The Bayesian hyper-parameter optimization algorithm is a model-based method for finding the minimum value of the function so as to obtain the optimal parameters of the LightGBM model. Experiments have demonstrated that the parameters obtained by the Bayesian hyper-parameter optimization algorithm are superior to those obtained by a genetic algorithm and random search. The improved LightGBM model based on the Bayesian hyper-parameter optimization algorithm achieves a mean square error of 0.5961 in blood glucose prediction, with a higher accuracy than the XGBoost model and CatBoost model.

[1]  Haiyong Luo,et al.  A Human Activity Recognition Algorithm Based on Stacking Denoising Autoencoder and LightGBM , 2019, Sensors.

[2]  Jin Hur,et al.  An Ensemble Learner-Based Bagging Model Using Past Output Data for Photovoltaic Forecasting , 2020, Energies.

[3]  Yuquan Wei,et al.  Prediction models of human plasma protein binding rate and oral bioavailability derived by using GA-CG-SVM method. , 2008, Journal of pharmaceutical and biomedical analysis.

[4]  J. Shaw,et al.  IDF Diabetes Atlas: Global estimates of diabetes prevalence for 2017 and projections for 2045. , 2018, Diabetes research and clinical practice.

[5]  Cheng Chen,et al.  LightGBM-PPI: Predicting protein-protein interactions through LightGBM with multi-information fusion , 2019, Chemometrics and Intelligent Laboratory Systems.

[6]  Bharti Suri,et al.  On the Effectiveness of Using Elitist Genetic Algorithm in Mutation Testing , 2019, Symmetry.

[7]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[8]  Guilherme Ottoni,et al.  Constrained Bayesian Optimization with Noisy Experiments , 2017, Bayesian Analysis.

[9]  V. S. Shankar Sriram,et al.  An efficient intrusion detection system based on hypergraph - Genetic algorithm for parameter optimization and feature selection in support vector machine , 2017, Knowl. Based Syst..

[10]  Yinglai Liu,et al.  A Machine-Learning-Based Prediction Method for Hypertension Outcomes Based on Medical Data , 2019, Diagnostics.

[11]  Yinglin Wang,et al.  Genetic algorithm based feature selection and parameter optimization for support vector regression applied to semantic textual similarity , 2015, Journal of Shanghai Jiaotong University (Science).

[12]  Qing-Guo Wang,et al.  XGBoost Model for Chronic Kidney Disease Diagnosis , 2020, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[13]  Wenbing Chang,et al.  Probability Analysis of Hypertension-Related Symptoms Based on XGBoost and Clustering Algorithm , 2019, Applied Sciences.

[14]  Dorte Vistisen,et al.  Global healthcare expenditure on diabetes for 2010 and 2030. , 2010, Diabetes research and clinical practice.

[15]  Da-ping Yu,et al.  Copy number variation in plasma as a tool for lung cancer prediction using Extreme Gradient Boosting (XGBoost) classifier , 2019, Thoracic cancer.

[16]  Sayan Putatunda,et al.  A Comparative Analysis of Hyperopt as Against Other Approaches for Hyper-Parameter Optimization of XGBoost , 2018, SPML '18.

[17]  Mario R. Eden,et al.  Formation lithology classification using scalable gradient boosted decision trees , 2019, Comput. Chem. Eng..

[18]  Xiaojun Ma,et al.  Study on a prediction of P2P network loan default based on the machine learning LightGBM and XGboost algorithms according to different high dimensional data cleaning , 2018, Electron. Commer. Res. Appl..

[19]  José A. López-Campos,et al.  A genetic algorithm for the characterization of hyperelastic materials , 2018, Appl. Math. Comput..

[20]  Arif Budiarto,et al.  Features Importance in Classification Models for Colorectal Cancer Cases Phenotype in Indonesia , 2019 .

[21]  O. Postolache,et al.  Child’s Target Height Prediction Evolution , 2019 .