AI-Powered Post-Discharge Monitoring to Prevent Hospital Readmissions: A Global Scoping Review in Hospital Care

Hospital readmissions management poses a significant burden on healthcare systems, straining resources and negatively impacting patient treatment. Traditional post-discharge follow-up methods, such as phone calls, often lack efficiency and personalization. Artificial Intelligence (AI) (e.g., Machine Learning (ML)) offers a transformative approach with the potential to improve post-discharge care. This scoping review aimed to comprehensively map existing research on AI-powered solutions for post-discharge monitoring, focusing on their application in risk stratification and their potential for reducing hospital read-missions. Following PRISMA-ScR guidelines, a comprehensive search was conducted across four databases using keywords related to AI, post-discharge, and risk stratification. Studies published between 2018 and January 2024 were included if they described the development and application of an ML model in a post-discharge setting for risk stratification. Sixteen studies met the inclusion criteria. Tree-based algorithms, particularly XGBoost, were the predominant ML approach, with promising performance metrics for readmission risk prediction (AUC ranging from 0.69 to 0.994). However, limitations were identified, including restricted generalizability due to data source limitations and a lack of real-time implementation in many studies. This review highlights the potential of AI in post-discharge moni-toring, particularly the use of ML for risk stratification. While challenges remain regarding generalizability and real-world implementation, the findings suggest AI holds immense promise for improving post-discharge care, potentially reducing readmissions, and optimizing resource allocation. Future research with broader datasets and real-time applications can further solidify the role of AI in revolutionizing post-discharge monitoring and patient outcomes.