基于慢性肾脏病数据集的卷积神经网络对慢性肾脏病进展的预测价值研究

Background  Early and accurate prediction of the risk of developing end-stage renal diseaseESRD is essential for medical decision-making. In the field of chronic kidney diseaseCKDmany scholars are exploring the impact of various factors and the percentage decline in estimated glomerular filtration rateeGFRin the previous 2 years on the development of ESRD from a medical perspective. Traditional risk assessment methods usually rely on expert experiencesimple statistical analysesand limited biomarkerswhich face obvious limitations when dealing with complexmultidimensional health datawhereas the use of machine learning algorithmssuch as artificial neural networkscan significantly improve the accuracysensitivityand specificity of risk prediction.Objective  Based on multiple algorithmswe explored the predictive value of 2-year mean levels of clinical parameters and the rate of change of eGFR over a period of 2 years in the progression of CKD to ESRD. Methods  The dataset for this study was obtained from a retrospective cohort of the Japanese CKD population at Teikyo University HospitalJapanfrom 2008 to 2014700 patients were enrolled in the study cohort. Two datasets were obtained based on this cohorta baseline dataset and a 2-year time-averaged dataset. Logistic regressionLRmultilayer perceptual machineMLPsupport vector machineSVMextreme gradient boosting treeXGBoostand two-dimensional convolutional neural networkCNNalgorithms were used to predict whether a patient would reach ESRD after several years and to derive probabilities. The dataset is balanced at both the data and algorithmic levelsand medical significance is demonstrated using comparative trials.Results  Using LRMLPSVMand XGBoost as the baseline modelsthe comparison experiments show that the CNN model performs the bestwith an accuracy of 94.8%precision of 80.3%recall of 78.2%and F1 score of 78.4%. The evaluation metrics of the five models on the two-year time-averaged dataset were significantly higher than those on the baseline datasetespecially the recall rate. In additionmodels that included the eGFR decline rate variable over two years outperformed models that did not include this variable. Recall improved considerably after addressing the imbalance in the dataset categories. Conclusion  This study demonstrates that a two-dimensional CNN model based on the CKD dataset can guide healthcare professionals to make better clinical treatment decisionsthat the mean level of clinical parameters in the first 2 years and the percentage decline in eGFR over 2 years are significant in predicting dialysis eventsand that comprehensive management in the first 2 years is essential to delay the onset of ESRD.