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 … Show more
“…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.…”
Section: Methodsmentioning
confidence: 99%
“…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.…”
Section: Methodsmentioning
confidence: 99%
“…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 ).…”
Section: Methodsmentioning
confidence: 99%
“…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.…”
Section: Methodsmentioning
confidence: 99%
“…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 ).…”
ObjectiveTo screen for predictive obesity factors in overweight populations using an optimal and interpretable machine learning algorithm.MethodsThis cross-sectional study was conducted between June 2011 and January 2012. The participants were randomly selected using a simple random sampling technique. Seven commonly used machine learning methods were employed to construct obesity risk prediction models. A total of 5,236 Chinese participants from Ningde City, Fujian Province, Southeast China, participated in this study. The best model was selected through appropriate verification and validation and suitably explained. Subsequently, a minimal set of significant predictors was identified. The Shapley additive explanation force plot was used to illustrate the model at the individual level.ResultsMachine learning models for predicting obesity have demonstrated strong performance, with CatBoost emerging as the most effective in both model validity and net clinical benefit. Specifically, the CatBoost algorithm yielded the highest scores, registering 0.91 in the training set and an impressive 0.83 in the test set. This was further corroborated by the area under the curve (AUC) metrics, where CatBoost achieved 0.95 for the training set and 0.87 for the test set. In a rigorous five-fold cross-validation, the AUC for the CatBoost model ranged between 0.84 and 0.91, with an average AUC of ROC at 0.87 ± 0.022. Key predictors identified within these models included waist circumference, hip circumference, female gender, and systolic blood pressure.ConclusionCatBoost may be the best machine learning method for prediction. Combining Shapley’s additive explanation and machine learning methods can be effective in identifying disease risk factors for prevention and control.
“…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.…”
Section: Methodsmentioning
confidence: 99%
“…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.…”
Section: Methodsmentioning
confidence: 99%
“…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 ).…”
Section: Methodsmentioning
confidence: 99%
“…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.…”
Section: Methodsmentioning
confidence: 99%
“…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 ).…”
ObjectiveTo screen for predictive obesity factors in overweight populations using an optimal and interpretable machine learning algorithm.MethodsThis cross-sectional study was conducted between June 2011 and January 2012. The participants were randomly selected using a simple random sampling technique. Seven commonly used machine learning methods were employed to construct obesity risk prediction models. A total of 5,236 Chinese participants from Ningde City, Fujian Province, Southeast China, participated in this study. The best model was selected through appropriate verification and validation and suitably explained. Subsequently, a minimal set of significant predictors was identified. The Shapley additive explanation force plot was used to illustrate the model at the individual level.ResultsMachine learning models for predicting obesity have demonstrated strong performance, with CatBoost emerging as the most effective in both model validity and net clinical benefit. Specifically, the CatBoost algorithm yielded the highest scores, registering 0.91 in the training set and an impressive 0.83 in the test set. This was further corroborated by the area under the curve (AUC) metrics, where CatBoost achieved 0.95 for the training set and 0.87 for the test set. In a rigorous five-fold cross-validation, the AUC for the CatBoost model ranged between 0.84 and 0.91, with an average AUC of ROC at 0.87 ± 0.022. Key predictors identified within these models included waist circumference, hip circumference, female gender, and systolic blood pressure.ConclusionCatBoost may be the best machine learning method for prediction. Combining Shapley’s additive explanation and machine learning methods can be effective in identifying disease risk factors for prevention and control.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.