NCT06923514

Health Literacy, Stress and Quality of Life in Heart Failure Patients

Using Machine Learning to Analyze the Prediction and Correlation of Health Literacy, Stress and Quality of Life in Heart Failure Patients

• Status: Completed
• Phase: —
• Study type: Observational
• Enrollment: 158 (actual)
• Sponsor: Cheng-Hsin General Hospital · Academic / Other
• Sex: All
• Age: 18 Years – 65 Years
• Healthy volunteers: Not accepted

Summary

Heart failure is showing a trend of affecting younger individuals. Middle-aged heart failure patients are often the economic backbone of their families. Studies have also pointed out that approximately 38.5% of patients with acute heart failure are re-hospitalized within a year of discharge due to worsening symptoms. Patients with lower health literacy tend to have poorer health outcomes and higher re-hospitalization rates. However, there is limited research on the life and work stress, health literacy, and quality of life of middle-aged heart failure patients. Therefore, this study aims to use machine learning to analyze and predict the correlations between health literacy, stress, and quality of life in heart failure patients. This research is a cross-sectional correlational study, adopting convenience sampling. The study subjects are cardiology patients aged 18-65 diagnosed with heart failure classified as NYHA II or above by specialists at a regional teaching hospital in northern Taiwan. Data collection took place in the outpatient and inpatient departments of cardiology and cardiothoracic surgery. Structured questionnaires were used for one-on-one interviews, including basic demographic information of heart failure patients, the Chinese version of the European Health Literacy Survey Questionnaire (HLS-EU-Q47), the Chinese version of the Brief Resilience Scale (BRS), the Perceived Stress Scale (PSS), and the Minnesota Living with Heart Failure Questionnaire (MLHFQ). Data will be recorded using Excel, and statistical analysis will be conducted using SPSS version 22. Descriptive statistics such as percentages, means, and standard deviations will be used to describe the demographic and variable distributions. Independent t-tests, ANOVA, and Pearson correlation coefficient will be used to analyze correlations between variables. Machine learning will be employed to analyze and predict quality of life factors in heart failure patients. It is hoped that the results of this study can provide references for nursing practice, help with clinical patient assessment, and improve the quality of care for patients.

Conditions

• Heart Failure

Timeline

• Start date: 2024-11-20
• Primary completion: 2025-11-03
• Completion: 2025-11-03
• First posted: 2025-04-11
• Last updated: 2026-03-19

Locations

1 site across 1 country: Taiwan