Deriving a Sophisticated Clinical Pathway Based on Patient Conditions from Electronic Health Record Data

Clinical pathway (CP), a standardized treatment process based on a clinical guideline, is widely used to reduce costs while maintaining or improving patient care quality. However, there is a gap between the actual clinical process and the guideline, that causes CP application to be disturbed. A study on developing a data-driven automated clinical pathway to obtain insight into real clinical processes has been conducted. Still, patient characteristics and conditions, which could cause a variation, have not been fully considered. In this study, we aimed to develop a framework to derive a sophisticated clinical pathway from electronic health records (EHRs) data by exploring process variations according to the patient characteristics and conditions. To validate the applicability of the proposed framework, We conducted a case study using the Total Laparoscopic Hysterectomy (TLH) CP data, which was retrieved from an EHR system of a tertiary general hospital in South Korea between January 2012 and April 2016. We found that diabetic TLH patients show different medical performances with other TLH patients. We developed a tailored CP that adds eleven orders over the standard TLH CP, and experts evaluated it as meaningful.