International Journal of Medical Informatics

Summary: A risk model that estimated the probability of receiving CKD diagnosis within the next year was developed and validated. Using EMRs of over 1.3 million patients in the state of Maine, the model was able to assign each individual a risk score based on the preceding 1-year clinical history. The model identified 72.90% of high-risk patients at least 3 months before the confirmatory diagnosis was made by physicians. Of those patients, 41.02% had diabetes or an abnormal glucose test result at the time they were identified at high risk for CKD. Implementation of lifestyle modifications at that time has the potential to mitigate adverse outcomes in those patients.