A Risk Prediction Framework to Optimize Remote Patient Monitoring Following Cardiothoracic Surgery

Remote Patient Monitoring (RPM) in cardiac surgery can become valuable for clinicians to follow patients post-discharge closely. However, these services require additional and frequently limited human and technical resources. We present the CardioFollow.AI Framework, a decision support system to assist doctors in selecting patients to be monitored remotely. Currently supporting a clinical trial, it leverages a Machine Learning model to predict the risk of post-discharge complications. Interpretable assessments are included so that clinicians can evaluate individual predictions. Additionally, the user-friendly interface of the CardioFollow.AI Framework enhances the follow-up of discharged patients by granting access to centralised information. This paper outlines the design and implementation of the CardioFollow.AI Framework and its potential impact on improving personalised patient careq.