Details
[Return to Previous Page]
- Under-documentation of Chronic Kidney Disease in the Electronic Health Record of Outpatients
- Date : November 5th, 2009
Time : 4:00PM - 5:00 PM
Location : VC05 Conference Room, Columbia University Medical Center
Event Speaker : Herb Chase, Professor of Clinical Medicine (in Biomedical Informatics) - There is an epidemic of chronic kidney disease (CKD) in the US and worldwide. The key to slowing the progression of CKD to end stage renal disease is early recognition so that optimal management can be implemented. We wondered to what extent providers caring for patients with CKD documented the illness in the electronic health record (EHR). To explore this issue we first identified a cohort of patients with CKD based on their creatinine values. Their outpatient notes were then extracted from the Clinical Data Warehouse. A lexical-based classification tool was developed to determine if documentation was present in the notes of patients with moderate CKD. The tool identified 20% of 108 patients with manually verified moderate CKD who did not have a single note documenting the illness. Compared to patients without any documentation, patients whose CKD had been documented had the illness for twice as long. Based on these findings, we plan to develop a CKD clinical decision support system that notifies providers who did not document their patients’ CKD in the EHR. We hypothesize that a tool that prompts recognition of CKD in a previously undocumented patient has the potential to improve clinical outcomes, by increasing the likelihood that guideline-based management will be instituted early in the course of the disease.
