| CPC G16H 50/20 (2018.01) [G06Q 10/1095 (2013.01); G16H 20/30 (2018.01); G16H 50/30 (2018.01); G16H 50/50 (2018.01); G16H 10/60 (2018.01)] | 20 Claims |
|
1. A non-transitory computer readable storage medium having computer-executable instructions embodied thereon that, when executed by at least one processor, cause the at least one processor to perform operations, the operations comprising:
obtaining, at an electronic decision support tool embedded in an electronic health record (EHR) system, measurements of one or more physiological variables for an individual, the measurements including at least a longitudinal time series data of uric acid for the individual;
appending, at the electronic decision support tool, information of the individual to the measurements;
transforming the measurements of the one or more physiological variables to reflect non-linear relationships of the measurements, wherein a transformation process comprises one of logistic transformation, min-max transformation, or thresholding according to each physiological variable of the one or more physiological variables;
determining, at the electronic decision support tool, a uric acid quantile membership of the individual, wherein uric acid quantiles are determined by age groups;
computing, at the electronic decision support tool, a uric acid velocity based on temporal analysis of the longitudinal time series data of uric acid measurements of the individual;
determining statistically significant model variables based at least on the transformed measurements of the one or more physiological variables, the uric acid quantile membership, and the uric acid velocity;
accessing a predictive model by using the statistically significant model variables, wherein the predictive model is configured to estimate coefficients corresponding to the statistically significant model variables and to predict progression of stage 3 chronic kidney disease (CKD);
computing automatically, in real-time at the electronic decision support tool using the predictive model, a forecast probability that the individual will progress to stage 3 CKD within a future time interval;
comparing, at the electronic decision support tool, the forecast probability to one or more threshold probabilities; and
based on comparing the forecast probability to the one or more threshold probabilities, automatically generating and executing, by the electronic decision support tool, a health care software routine or software agent to at least initiate a signal that causes an alert to be presented to a medical professional that is indicative of risk of progression to stage 3 CKD of the individual and preparing a treatment plan, wherein the treatment plan for the individual includes administering a disease-modifying medication regimen for treating the individual, wherein the disease-modifying medication regimen comprises administering a diabetes therapy, a medication to reduce proteinuria, an aldosterone blockade, an angiotensin-converting-enzyme (ACE) inhibitor, an angiotensin receptor blocker (ARB), an erythropoietin therapy, an acidosis treatment, or a combination thereof.
|