Predictive Modeling Using a Nationally Representative Database to Identify Patients at Risk of Developing Microalbuminuria

Abstract

Background: Predictive models allow clinicians to more accurately identify higher- and lower-risk patients and make more targeted treatment decisions, which can help improve efficiency in health systems. Microalbuminuria (MA) is a condition characterized by the presence of albumin in the urine below the threshold detectable by a standard dipstick. Its presence is understood to be an early marker for cardiovascular disease. Therefore, identifying patients at risk for MA and intervening to treat or prevent conditions associated with MA, such as high blood pressure or high blood glucose, may support cost-effective treatment. Methods: The National Health and Nutrition Examination Survey (NHANES) was utilized to create predictive models for MA. This database includes clinical, medical and laboratory data. The dataset was split into thirds; one-third was used to develop the model, while the other two-thirds were utilized to validate the model. Univariate logistic regression was performed to identify variables related with MA. Stepwise multivariate logistic regression was performed to create the models. Model performance was evaluated using three criteria: 1) receiver operator characteristic (ROC) curves; 2) pseudo R-squared; and 3) goodness of fit (Hosmer-Lemeshow). The predictive models were then used to develop risk-scores. Results: Two models were developed using variables that had significant correlations in the univariate analysis (p-value<0.05). For Model A, variables included in the final model were: systolic blood pressure (SBP); fasting glucose; C-reactive protein; blood urea nitrogen (BUN); and alcohol consumption. For Model B, the variables were: SBP; glycohemoglobin; BUN; smoking status; and alcohol consumption. Both models performed well in the creation dataset and no significant difference between the models was found when they were evaluated in the validation set. A 0-18 risk score was developed utilizing Model A, and the predictive probability of developing MA was calculated. Conclusion: The predictive models developed provide new evidence about which variables are related with MA and may be used by clinicians to identify at-risk patients and to tailor treatment. Furthermore, the risk score developed using Model A may allow clinicians to more easily measure patient risk. Both predictive models will require external validation before they can be applied to other populations.