Background: Among the problems caused by hypertension, the early renal damage is often ignored. It can not be diagnosed until the condition is serious and irreversible damage occurs. So we decide to screen and explore related risk factors for hypertensive patients with early renal damage, and establish early-warning model of renal damage based on the data-mining method to achieve early diagnosis for hypertensive patients with renal damage.
Methods: With the aid of electronic information management system for hypertensive specialist out-patient, we collected 513 cases of original untreated hypertensive patients, and recorded their demographic data, ambulatory blood pressure parameters, blood routine index and blood biochemical index to establish the clinical database, then we screen risk factors for early renal damage through feature engineering, and use Random Forest, Extra-Trees and XGBoost to build a early-warning model respectively. Finally, we build a new model by model fusion based on Stacking strategy. We use cross validation to evaluate the stability and reliability of each mode to determine the best risk assessment model.
Results: According to the degree of importance, the descending order of features selected by feature engineering is the drop rate of systolic blood pressure at night, the red blood cell distribution width, blood pressure circadian rhythm, the average diastolic blood pressure at daytime, body surface area, smoking, age and HDL. Among the early-warning models of renal damage without model fusion, XGBoost has the best effect, the average accuracy of 5-fold cross validation is 0.90457. And the average accuracy of the two-dimensional fusion model based on Stacking strategy is 0.91428, which is greatly improved.
Conclusions: Through feature engineering and risk factor analysis, we select the drop rate of systolic blood pressure at night, the red blood cell distribution width, blood pressure circadian rhythm and the average diastolic blood pressure at daytime as early-warning factors of early renal damage in patients with hypertension. On this basis, the two-dimensional fusion model based on Stacking strategy has a better effect than the single model, which can be used for risk assessment of early renal damage in hypertensive patients.