Machine Learning Approach for Chronic Kidney Disease Risk Prediction Combining Conventional Risk Factors and Novel Metabolic Indices

Abstract

Patients at risk of chronic kidney disease (CKD) must be identified early and precisely in order to prevent complications, save lives, and limit expenditures for patients and health systems. This study aimed to develop a simple, high-precision machine learning model to identify individuals at risk of developing CKD in the near future, using a novel metabolic index with or without creatinine. This retrospective cohort study used data from the MJ medical record database collected between 2001 and 2015 in Taiwan. We used Cox hazard regression to identify potential predictors, including the novel metabolic index, for use as variables in the models. To develop a machine learning-based CKD risk model with fewer variables, we performed several experimental analyses to combine interacting variables into subsets. Those subsets were used to train three models, random forest, logistic regression, and XGBoost, with or without adding creatinine. The study included 12,189 participants, 20% with and 80% without CKD. The most important conventional predictors of CKD are age and gender. The novel metabolic index, TyG-Index, TG/HDL-ratio and VAI, had stronger predictive power than the conventional risk factors. Without including creatinine data, the XGBoost provided the best predictive performance. After adding creatinine, the performance of all the models was excellent, outperforming both conventional indicators and existing clinical algorithms for CKD. Using novel metabolic index in machine learning-based CKD risk prediction can accurately identify individuals at risk of diagnosis with CKD in the next year, with or without including creatinine.

Association between lipid accumulation product index and chronic kidney disease: A systematic review and meta-analysis

“…This approach could be particularly advantageous in primary care settings, where simple and cost-effective tools are essential for early disease detection. Age, blood pressure and body weight are other pertinent factors that, when combined with LAP index, could provide a more targeted screening tool for CKD ( 33 ). The incorporation of these parameters may potentially refine the specificity of CKD diagnosis, as they are known to be associated with disease progression and patient outcomes.…”

Urine metabolomics signature reveals novel determinants of adrenal suppression in children taking inhaled corticosteroids to control asthma symptoms

“…SMOTE is increasingly utilized in recent metabolomics investigations. [27][28][29] While seeing increasingly more applications in metabolomics, SMOTE still raises concerns in terms of the quality of data that it generates and consequently, its accuracy in identifying significant metabolites. Therefore, we conducted a simulation to evaluate the quality of metabolites detected by SMOTE compared with regular Logistics regression as well as Saddle point Approximation models.…”

“…Synthetic data is added until the number of instances in the minority group is as desired. SMOTE is increasingly utilized in recent metabolomics investigations 27–29 . While seeing increasingly more applications in metabolomics, SMOTE still raises concerns in terms of the quality of data that it generates and consequently, its accuracy in identifying significant metabolites.…”