Research on the Analysis Model of Senile Frailty Syndrome Based on Machine Learning
YUE Wei
XIE Jun
ZHOU Manman
MA Hua
Abstract：Objective To establish a diagnostic model of senile frailty syndrome based on machine learning,so as to provide a reference for clinical practice.Methods Based on clinically diagnosed data,Monte Carlo simulation was used to train the diagnostic model based on machine-learning classification methods including logistic regression(LR),decision tree(DT),support vector machines(SVM),random forest(RF)and K-nearest neighbor(KNN)for investigating the factors affecting senile frailty syndromes deeply.Results By feeding the quantified senile frailty data into the classifiers for training,it was learned that the SVM classification model achieved the highest accuracy on the test set;by analyzing the effects of various characteristics on the accuracy of the RF model and the effects of deleting the characteristics on the model,it was confirmed that senile frailty characteristics such as depression,anxiety,polypharmacy and comorbidities were the main risk factors for the disease.Conclusion The machine learning methods can effectively tap the risk factors affecting senile frailty syndrome,provide effective identification and reliable reference for the diagnosis of senile frailty,and contribute a new idea for the development and application of artificial intelligence technology in the field of senile health care.
Keywords：Machine learningSenile frailty syndromeAnalysis and interventionData mining
Publication Date：2023-12-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：4( 1019-1022 )