Abstract

To evaluate the health-related quality of life(HRQoL)status of elderly patients with hypertensive stroke, to understand the factors influencing it, and to provide a basis for the development of health intervention policies. This study used the EQ-5D-3L scale to assess the HRQoL among elderly patients who experienced a stroke related to high blood pressure. Various analytical methods were employed to examine the factors that influenced the patient's quality of life. Univariate analysis, Tobit regression, random forest, and XGBoost models were applied to analyze the HRQoL of the patients. Furthermore, to interpret the machine learning results, the SHAP method was utilized. This method involved assessing the importance of each feature, examining the effect of each feature on the prediction result of a single sample, and determining the impact of individual features on the overall prediction. The study found that the median health utility value for elderly patients with hypertensive stroke was 0.427, with an interquartile range of 0.186 to 0.745. The results of the Tobit regression model, Random Forest, and XGBoost model were compared. The results of the model evaluation show that the performance of the machine learning model and the Tobit regression model are not very different. The XGBoost model performs slightly better relative to the random forest model. The factors that strongly influenced the health utility value of patients included BMI, social activities, smoking, education level, alcohol consumption, urban/rural residence, annual income, physical activity level, and hours of sleep at night. Health-related quality of life in hypertensive stroke patients is influenced by a variety of factors. Health-related quality of life can be positively influenced by modifying these factors and making lifestyle adjustments. Maintaining a healthy weight, being socially active, quitting smoking, improving living conditions, increasing physical activity levels and getting enough sleep are recommended. Lifestyle changes need to be developed for each individual on a case-by-case basis and by medical advice.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call