Development of a Risk Model for Predicting Microalbuminuria in the Chinese Population Using Machine Learning Algorithms

Abstract

ObjectiveMicroalbuminuria (MAU) occurs due to universal endothelial damage, which is strongly associated with kidney disease, stroke, myocardial infarction, and coronary artery disease. Screening patients at high risk for MAU may aid in the early identification of individuals with an increased risk of cardiovascular events and mortality. Hence, the present study aimed to establish a risk model for MAU by applying machine learning algorithms.MethodsThis cross-sectional study included 3,294 participants ranging in age from 16 to 93 years. R software was used to analyze missing values and to perform multiple imputation. The observed population was divided into a training set and a validation set according to a ratio of 7:3. The first risk model was constructed using the prepared data, following which variables with P <0.1 were extracted to build the second risk model. The second-stage model was then analyzed using a chi-square test, in which a P ≥ 0.05 was considered to indicate no difference in the fit of the models. Variables with P <0.05 in the second-stage model were considered important features related to the prevalence of MAU. A confusion matrix and calibration curve were used to evaluate the validity and reliability of the model. A series of risk prediction scores were established based on machine learning algorithms.ResultsSystolic blood pressure (SBP), diastolic blood pressure (DBP), fasting blood glucose (FBG), triglyceride (TG) levels, sex, age, and smoking were identified as predictors of MAU prevalence. Verification using a chi-square test, confusion matrix, and calibration curve indicated that the risk of MAU could be predicted based on the risk score.ConclusionBased on the ability of our machine learning algorithm to establish an effective risk score, we propose that comprehensive assessments of SBP, DBP, FBG, TG, gender, age, and smoking should be included in the screening process for MAU.

Predicting risk of obesity in overweight adults using interpretable machine learning algorithms

“…Body mass index (BMI) was calculated as the weight in kilograms divided by the height in meters squared. Obesity ( 12 , 17 ) was defined as BMI ≥ 28; overweight as 28 > BMI ≥ 24; normal weight as 24 > BMI ≥ 18.5; and low weight as BMI < 18.5. ( 3 ) The inclusion criteria were individuals who were defined as overweight or obese.…”

“…All participants were required to complete a standard questionnaire on age, sex, personal medical history, and habits. Further, the height, waist circumference (WC), hip circumstance (HC), and weight were measured by nurses with ten years of experience, and measured to 0.1 cm, 0.1 cm, 0.1 cm, and 0.1 kg, respectively ( 12 ). WC was measured at the middle point of the iliac crest and costal margin.…”

“…Heart rate, systolic blood pressure (SBP), and diastolic blood pressure (DBP) were measured three times using a standard electronic sphygmomanometer (OMRON HEM-7111, Kyoto, Japan), and the mean of the three readings was used for analysis. Hypertension was defined as SBP ≥140 mmHg and/or DBP ≥90 mmHg or the use of antihypertensive medications ( 12 ).…”

“…Type-2 DM was defined ( 18 ) as fasting blood glucose (FBG) ≥ 7.0 mmol/L, 2-h postprandial blood glucose (PBG) ≥ 11.1 mmol/L, previous diagnosis of type-2 DM, or use of hypoglycemic medications ( 18 ). Insulin resistance from fasting insulin and glucose was calculated using the following formula: Homeostasis Model Assessment of Insulin Resistance (HOMA-IR) = Fasting Insulin (µU/ml) Fasting Glucose (mg/dl)/(22.5 × 18) ( 12 ). HbA1c was measured by high-performance liquid chromatography using the VARIANT II Hemoglobin Testing System (Bio-Rad, China) in the National Glycohemoglobin Standardization Program certified central laboratory.…”

“…Machine learning has received significant attention owing to its excellent ability to perform reliable predictive analysis ( 9 – 11 ). Compared with traditional methods ( 12 ), recent studies have indicated the applications of machine learning in the analysis of high-dimensional datasets and the complex relationships between many multiple variables ( 13 ). Hitherto, most previous machine learning models have focused on the prediction of childhood obesity ( 14 ).…”