Intelligent Case Manage Platform to Improve Self-management and Health-related Outcome Among Liver Transplant Recipients: Connection With Artificial Intelligence and Deep Learning
Intelligent Case Manage Platform to Improve Self-management and Health-related Outcome Among Liver Transplant Recipients: Connection With Artificial Intelligence and Deep Learning
This study is a prospective, quasi-experimental design, with an experimental group and a control group, will be created. The aims of this study are as follows: 1. Describe the self-management and information needs of liver transplant recipients, 2. Create content or modules related to the self-management of liver transplant recipients, 3. Build an intelligent case management platform, 4. Evaluate the usability of the platform, and 5. Conduct deep learning and examine the effects of the intelligent case management platform on self-efficacy, self-management, health outcomes, and health-related quality of life. Data will be collected at discharge (baseline data) and 1, 3, 6, 9, and 12 months after discharge. An estimated 133 patients will be involved in this experiment: 44 in the experimental group and 89 in the control group. Statistical package software (SPSS 22.0) will be used to analyze the data. A generalized estimation equation model will examine the differences in self-efficacy, self-management, and health-related quality of life between the experimental and control groups. Survival analysis and the Kaplan-Meier method will be used to analyze health outcomes, including hospital readmission, emergency visits, episodes of infection and rejection of organs, and death.
Background: Liver transplant recipients require proper self-management to avoid the risk of various complications, reduce hospital readmission and medical costs, and improve their quality of life. They also face diverse challenges in self-management. Therefore, enhancing the self-management of liver transplant recipients after liver transplantation is important. Hospitals and medical facilities taking care of such patients should facilitate individualized care, access to healthcare resources, and planned post-discharge support. The use of information technology, artificial intelligence, and deep learning to identify and confirm the characteristics and types of self-management requirements of liver transplant recipients and provide individualized self-management may help improve their self-management skills and health outcomes. The quality and continuity of care can also be improved. However, no studies have been conducted in this regard.
Purpose: To establish an intelligent case management platform that combines artificial intelligence and deep learning to enhance the self-efficacy and self-management of liver transplant recipients, thereby improving clinical outcomes and health-related quality of life. The aims of this study are as follows: 1. Describe the self-management and information needs of liver transplant recipients, 2. Create content or modules related to self-management of liver transplant recipients, 3. Build an intelligent case management platform, 4. Evaluate the usability of the platform, and 5. Conduct deep learning and examine the effects of the intelligent case management platform on self-efficacy, self-management, health outcomes, and health-related quality of life.
Methods and materials: This study is a prospective, quasi-experimental design, with an experimental group and a control group, will be created. First, the self-management care and information needs of liver transplant patients will be integrated to create the foundation of the intelligent case management platform. For this purpose, an estimated 50 liver transplant recipients and 10 medical staff will be interviewed. The data will be analyzed by qualitative content analysis. Based on these contents, the intelligent case management platform will be developed and evaluated. For the evaluation, data from 200 liver transplant recipients will be collected to assess platform availability, performance, and usage status. Data related to the recipient's use of the platform and reception of self-management from the platform will also be collected for deep learning. The importance and clinical relevance of self-management provided by the platform will be assessed by the medical staff involved in liver transplant care. Deep learning techniques will be utilized, and the effectiveness of the intelligent case management platform in terms of self-efficacy, self-management, health outcomes, and health-related quality of life will be examined. An estimated 133 patients will be involved in this experiment: 44 in the experimental group and 89 in the control group. Data will be collected at discharge (baseline data) and 1, 3, 6, 9, and 12 months after discharge from the hospital. Statistical package software (SPSS 22.0) will be used to analyze the data. A generalized estimation equation model will analyze the differences in self-efficacy, self-management, and health-related quality of life over time between the experimental and control groups. This study proposes innovative applications for information technology, deep learning, and artificial intelligence. It is hoped that multidisciplinary cooperation can improve liver transplant recipients' self-management and health outcomes.
Inclusion Criteria:
Exclusion Criteria: