Prediction and Key Characteristics of All-Cause Mortality in Maintenance Hemodialysis Patients

Abstract

Predict and analyze key features of all-cause death in maintenance hemodialysis patients to provide guidance for later diagnosis and treatment. Four machine learning methods were used to establish an all-cause death prediction model for maintenance hemodialysis patients and compare their performance. Analyze the key characteristics that have an important impact on all-cause death, and conduct user portraits for patients of different ages and genders. After comparison, the random forest algorithm works best, and an important factor affecting the all-cause death of patients is obtained. Among them, the all-cause death of all patients is related to factors such as albumin, blood potassium, blood magnesium, and urea; With age, the importance of factors such as blood sodium and phosphorus increases, and the importance of factors such as cardiac ultrasound ejection fraction decreases. Finally, there were also differences in the importance of analyzing patients of different ages and different sexes affecting their all-cause death. It is useful for residents to adjust their dialysis index timely.