Shared decision making (SDM) is a process in which clinicians and patients collaboratively work together to reach a shared medical decision, where the best medical evidence is presented, and the preferences and priorities of the patient are respected. In this paper, we developed an evidence-based platform that aims to facilitate communication between patients and clinicians. We mined the Healthcare Cost and Utilization Project dataset (H-CUP) and extracted medical knowledge personalized to the patient’s medical characteristics. Our platform is tailored toward the hospital readmission problem. First, we employed machine learning techniques to build models that can predict the readmission and mortality for newly admitted patients at the hospital. Second, we built a graph named Procedure Graph to visualize the primary procedures during the course of treatment and show the number of potential readmissions. Third, we personalized the procedure graph to the patient’s medical characteristics by applying our developed Rough Clustering technique. The developed platform is highly significant and novel within the context of hospital readmission. It can enhance the patient-clinician communication by providing a visualized evidence-based knowledge extracted from the electronic health records and personalized to the patient’s level.
CITATION STYLE
Mardini, M. T., Hashky, A., & Raś, Z. W. (2021). Personalizing Patients to Enable Shared Decision Making. In Studies in Computational Intelligence (Vol. 946, pp. 75–90). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-66450-3_5
Mendeley helps you to discover research relevant for your work.