An AI-Based Long-Term Care Service System Rating Methodology Integrating Multiple Data Sources

Abstract

Abstract This study aims to develop an AI-based intelligent assessment system for assistive devices and accessibility services within the context of long-term care. Utilizing supervised learning algorithms from machine learning, the system analyzes care plan content recorded by case managers and care managers to provide decision-making assistance for the selection of appropriate assistive devices and accessibility services. The system optimizes the existing one-way flow process by proactively suggesting necessary assistive support items based on care plan analysis. Artificial intelligence technology is employed to analyze the contents of care plans recorded by case managers and photo specialists, enabling the system to provide auxiliary decision-making capabilities for assistive aids and barrier-free services. Through machine learning, the activities of daily living (ADLs) and instrumental activities of daily living (IADLs) in the care management evaluation scale are trained, generating a dataset for predicting the Long-Term Care Case-Mix System (CMS). This predictive capability can be utilized by medical staff, individual managers in unit A, or discharge preparation managers for evaluation and planning purposes. The system's integration of AI technology assists care managers in providing more efficient and personalized care services for their clients, simultaneously reducing their burden and enhancing the overall quality of long-term care services. This research contributes to the field of long-term care by introducing an AI intelligent assessment system that improves decision-making in selecting assistive devices and accessibility services. Leveraging machine learning algorithms and analyzing care plan content, the system enhances the efficiency and personalization of care services, benefiting both care managers and clients.