Development and Validation of an Insulin Resistance Model for a Population with Chronic Kidney Disease Using a Machine Learning Approach

Abstract

Background: Chronic kidney disease (CKD) is a complex syndrome without a definitive treatment. For these patients, insulin resistance (IR) is associated with worse renal and patient outcomes. Until now, no predictive model using machine learning (ML) has been reported on IR in CKD patients. Methods: The CKD population studied was based on results from the National Health and Nutrition Examination Survey (NHANES) of the USA from 1999 to 2012. The homeostasis model assessment of IR (HOMA-IR) was used to assess insulin resistance. We began the model building process via the ML algorithm (random forest (RF), eXtreme Gradient Boosting (XGboost), logistic regression algorithms, and deep neural learning (DNN)). We compared different receiver operating characteristic (ROC) curves from different algorithms. Finally, we used SHAP values (SHapley Additive exPlanations) to explain how the different ML models worked. Results: In this study population, 71,916 participants were enrolled. Finally, we analyzed 1,229 of these participants. Their data were segregated into the IR group (HOMA IR > 3, n = 572) or non-IR group (HOMR IR ≤ 3, n = 657). In the validation group, RF had a higher accuracy (0.77), specificity (0.81), PPV (0.77), and NPV (0.77). In the test group, XGboost had a higher AUC of ROC (0.78). In addition, XGBoost also had a higher accuracy (0.7) and NPV (0.71). RF had a higher accuracy (0.7), specificity (0.78), and PPV (0.7). In the RF algorithm, the body mass index had a much larger impact on IR (0.1654), followed by triglyceride (0.0117), the daily calorie intake (0.0602), blood HDL value (0.0587), and age (0.0446). As for the SHAP value, in the RF algorithm, almost all features were well separated to show a positive or negative association with IR. Conclusion: This was the first study using ML to predict IR in patients with CKD. Our results showed that the RF algorithm had the best AUC of ROC and the best SHAP value differentiation. This was also the first study that included both macronutrients and micronutrients. We concluded that ML algorithms, particularly RF, can help determine risk factors and predict IR in patients with CKD.

Keywords: HOMA-IR; artificial intelligence; chronic kidney disease; deep learning; insulin resistance; machine learning; national health and nutrition examination survey (NHANES).

Figure 1

Algorithm of groping in patients with CKD. Initially, all 71,916 participants were enrolled in this study. After exclusion, all 1229 participants with CKD with complete data were analyzed. We separated all 1229 participants into three groups: 675 for train group, 185 for validation group, and 369 for test group. All algorithms were compared via AUC.

Figure 2

Prediction of insulin resistance in patients with CKD using XGboost, random forest, logistic regression, and DNN in train (A), validation (B), and test group (C). In the train group (A), RF had the highest AUC (0.94), followed by XGboost (0.91). In the validation group (B), AUCs of ROC were all >0.8 (highest being RF, 0.83). RF had higher accuracy (0.77), specificity (0.81), PPV (0.77), and NPV (0.77). The sensitivity was highest in DNN (0.74). In the testing group (C), all AUCs of ROC were >0.76 (highest being XGboost, 0.78). In addition, XGBoost also had higher accuracy (0.7) and NPV (0.71). RF had higher accuracy (0.7), specificity (0.78), and PPV (0.7). DNN had higher sensitivity (0.66) and NPV (0.71).

Figure 3

Feature importance. (A) XGboost algorithm. (B) RF algorithm. In the XGBoost algorithm (A), BMI had a large impact on IR (0.1262), followed by triglyceride (0.0754), protein intake ratio (0.0537), age (0.0487), blood total cholesterol value (0.0433), daily cholesterol intake (0.0430), daily calorie intake (0.0429), blood HDL value (0.0424), daily zinc intake (0.0420), and daily saturated fatty acid intake (0.0414). In the RF algorithm (B), similarly, BMI had a large impact on IR (0.1654), followed by triglyceride (0.0117), daily calorie intake (0.0602), blood HDL value (0.0587), and age (0.0446). (The dark red line indicated group name and the blue line indicated individual item name).

Figure 3

Feature importance. (A) XGboost algorithm. (B) RF algorithm. In the XGBoost algorithm (A), BMI had a large impact on IR (0.1262), followed by triglyceride (0.0754), protein intake ratio (0.0537), age (0.0487), blood total cholesterol value (0.0433), daily cholesterol intake (0.0430), daily calorie intake (0.0429), blood HDL value (0.0424), daily zinc intake (0.0420), and daily saturated fatty acid intake (0.0414). In the RF algorithm (B), similarly, BMI had a large impact on IR (0.1654), followed by triglyceride (0.0117), daily calorie intake (0.0602), blood HDL value (0.0587), and age (0.0446). (The dark red line indicated group name and the blue line indicated individual item name).

Figure 4

Positive and negative impact explanation of features for predicting insulin resistance using SHAP values. (A) for XGBoost and (B) for RF. Well separated to show a positive or negative association with IR in terms of SHAP value for the XGBoost algorithm (A), including blood triglyceride value (strongly positive impact), BMI (strongly positive impact), daily calorie intake (medium negative impact), and blood total cholesterol value (medium negative impact). For the RF algorithm (B), almost all features were well separated to show a positive or negative association with IR in terms of SHAP value. (A) Explanation of each feature impact on the IR in the prediction model using the SHAP values in the XGBoost algorithm. (B) Explanation of each feature impact on the IR in the prediction model using the SHAP values in the RF algorithm.

Figure 4

Positive and negative impact explanation of features for predicting insulin resistance using SHAP values. (A) for XGBoost and (B) for RF. Well separated to show a positive or negative association with IR in terms of SHAP value for the XGBoost algorithm (A), including blood triglyceride value (strongly positive impact), BMI (strongly positive impact), daily calorie intake (medium negative impact), and blood total cholesterol value (medium negative impact). For the RF algorithm (B), almost all features were well separated to show a positive or negative association with IR in terms of SHAP value. (A) Explanation of each feature impact on the IR in the prediction model using the SHAP values in the XGBoost algorithm. (B) Explanation of each feature impact on the IR in the prediction model using the SHAP values in the RF algorithm.