Non-Traditional Lipid Ratios Predict Cardiovascular-Kidney-Metabolic Syndrome: Insights from Machine Learning Model Using NHANES Data

Non-Traditional Lipid Ratios Predict Cardiovascular-Kidney-Metabolic Syndrome: Insights from Machine Learning Model Using NHANES Data | medRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-P4HH5NV'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search Non-Traditional Lipid Ratios Predict Cardiovascular-Kidney-Metabolic Syndrome: Insights from Machine Learning Model Using NHANES Data Nan Wang , Jie Zhang , YuYing Wang , ZhaoXia Zhang , Ya Shi , Lu Zhang , Ying Xing , QianQian Lv doi: https://doi.org/10.1101/2025.09.26.25336774 Nan Wang 1 Department of Endocrinology, Xi’an Daxing Hospital affiliated to Yan’an University. Xi’an , China . 710082 MM Find this author on Google Scholar Find this author on PubMed Search for this author on this site Jie Zhang 1 Department of Endocrinology, Xi’an Daxing Hospital affiliated to Yan’an University. Xi’an , China . 710082 MM Find this author on Google Scholar Find this author on PubMed Search for this author on this site YuYing Wang 1 Department of Endocrinology, Xi’an Daxing Hospital affiliated to Yan’an University. Xi’an , China . 710082 MM Find this author on Google Scholar Find this author on PubMed Search for this author on this site ZhaoXia Zhang 1 Department of Endocrinology, Xi’an Daxing Hospital affiliated to Yan’an University. Xi’an , China . 710082 MM Find this author on Google Scholar Find this author on PubMed Search for this author on this site Ya Shi 1 Department of Endocrinology, Xi’an Daxing Hospital affiliated to Yan’an University. Xi’an , China . 710082 MM Find this author on Google Scholar Find this author on PubMed Search for this author on this site Lu Zhang 1 Department of Endocrinology, Xi’an Daxing Hospital affiliated to Yan’an University. Xi’an , China . 710082 MM Find this author on Google Scholar Find this author on PubMed Search for this author on this site Ying Xing 1 Department of Endocrinology, Xi’an Daxing Hospital affiliated to Yan’an University. Xi’an , China . 710082 MD Find this author on Google Scholar Find this author on PubMed Search for this author on this site QianQian Lv 1 Department of Endocrinology, Xi’an Daxing Hospital affiliated to Yan’an University. Xi’an , China . 710082 BM Find this author on Google Scholar Find this author on PubMed Search for this author on this site For correspondence: 18329418877{at}163.com Abstract Full Text Info/History Metrics Data/Code Preview PDF Abstract Background Cardiovascular-kidney-metabolic (CKM) syndrome is a newly defined multisystem disease continuum characterized by the coexistence of metabolic dysfunction, cardiovascular disease, and chronic kidney disease (CKD). This study aimed to explore the relationship between the non-traditional lipid ratios and CKM syndrome. Methods A cross-sectional analysis was performed using data from the 2007-2018 National Health and Nutrition Examination Survey (NHANES). CKM stages (0-4) were classified according to the 2023 American Heart Association (AHA) criteria. Non-traditional lipid ratios, including triglyceride to high-density lipoprotein cholesterol (TG/HDL-C), total cholesterol to HDL-C (TC/HDL-C), low-density lipoprotein cholesterol to HDL-C (LDL-C/HDL-C), and non-HDL-C, were assessed. Nonlinear associations were explored using restricted cubic spline models. Variable selection was conducted using the least absolute shrinkage and selection operator (LASSO) regression, and four machine learning models were developed. SHapley Additive exPlanations (SHAP) and partial dependence plots (PDPs) were applied for interpretability. Results The significant associations were observed between non-traditional lipid ratios and CKM risk. Nonlinear relationships were observed for LDL, TG, TC, and HDL. The random forest (RF) algorithm demonstrated superior performance. SHAP analysis identified body mass index (BMI) as the most influential predictor, followed by TG, TG/HDL-C, and glucose. Elevated TG/HDL-C, TC/HDL-C, and non-HDL-C levels were positively associated with increased CKM risk, while LDL-C/HDL-C showed inverse associations. PDPs indicated synergistic interactions among TG/HDL-C, TC/HDL-C, and non-HDL-C. Multivariate logistic regression confirmed TG/HDL-C as an independent predictor (OR = 3.11; 95% CI: 2.49-3.88; p < 0.001). Conclusion TG/HDL-C and non-HDL-C are strong predictors of CKM syndrome. Integration of these markers into risk models may facilitate earlier detection and guide individualized prevention strategies. Introduction Cardiovascular-kidney-metabolic (CKM) syndrome has recently been recognized as a systemic clinical entity that reflects complex interactions among obesity, diabetes, chronic kidney disease (CKD), and cardiovascular disease (CVD) 1 . Unlike traditional single-organ frameworks, CKM highlights multi-organ crosstalk, where metabolic disturbances accelerate cardiovascular and renal dysfunction, while organ impairments further intensify metabolic derangements. CKM has been linked to renal failure 2 , metabolic dysfunction-associated steatotic liver disease (MASLD) 3 , 4 , and increased risks of certain cancers 5 , 6 . Epidemiological evidence suggests that about 5% of U.S. adults already exhibit coexisting cardiovascular, renal, and metabolic conditions, with prevalence rising steadily, underscoring its growing public health burden 7 . Global Burden of Disease (GBD) analyses have further emphasized the significance of CKM syndrome. Disability-adjusted life years (DALYs) attributable to seven core components of CKM syndrome have increased steadily between 1990 and 2021, driven largely by population growth and aging. Projected trends indicate that stroke of DALYs will increase by 55.9%, and the burden of atrial fibrillation and flutter by 105.7% from 2022 to 2046 8 . These projections underscore the need for early detection, risk stratification, and preventive strategies, as CKM syndrome is poised to remain a major contributor to global morbidity. Dysregulated lipid metabolism has emerged as a pivotal mechanism in CKM syndrome. Conventional lipid metrics, including total cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), and high-density lipoprotein cholesterol (HDL-C), are routinely employed for cardiovascular risk assessment but often lack sufficient predictive accuracy in the context of multi-morbidity. In contrast, non-traditional lipid parameters, derived from conventional lipid measures, have demonstrated enhanced predictive value for complex cardiometabolic disorders. Parameters such as the Atherogenic Index of Plasma (AIP) 9 , non-HDL cholesterol (non-HDL-C) 10 , and the Cholesterol Retention Index (CRI-I and CRI-II) 11 integrate multiple lipid fractions, reflecting both atherogenic potential and systemic metabolic disturbances. Epidemiological evidence confirms that non-traditional lipid indices are strongly associated with predicting cardiometabolic multimorbidity (CMM) and its components 12 – 14 . Elevated AIP correlates with increased cardiovascular and type 2 diabetes risk, suggesting utility as an early metabolic marker. Non-HDL-C and CRI indices demonstrate stronger associations with metabolic syndrome than LDL-C. Mechanistic studies indicate that these parameters are linked to inflammation, oxidative stress, and insulin resistance (IR) 15 – 17 . Adipose tissue contributes further to pathogenesis: as an endocrine organ, it secretes adipokines, cytokines, and free fatty acids that impair insulin signaling, promote chronic inflammation, and accelerate metabolic deterioration 18 , 19 . These processes affect cardiovascular, renal, and hepatic function, reflecting the multi-organ progression of CKM syndrome. Despite these insights, research remains limited by a focus on individual disease components rather than CKM syndrome as an integrated entity. The combined predictive value and potential synergistic effects of non-traditional lipid indices are underexplored, constraining their clinical translation for early identification and risk stratification. Given their ability to detect metabolic abnormalities earlier than conventional measures, systematic investigation is warranted. This study aims to evaluate the associations between non-traditional lipid parameters and CKM syndrome and to assess their predictive utility using machine learning. Integrating multiple lipid indices permits consideration of cross-organ interactions and the identification of high-risk individuals at early stages of disease progression. Findings are expected to elucidate shared mechanisms of organ damage, inform novel intervention targets, and provide evidence for the simultaneous prevention of cardiovascular, renal, and metabolic disorders, addressing a growing global health burden. Methods All data are publicly available and can be accessed at the NHANES website ( https://wwwn.cdc.gov/nchs/nhanes/Default.aspx ). Relevant R code is available upon reasonable request to the corresponding author. Data sources and study population A cross-sectional analysis was conducted using data from the NHANES from 2007 to 2018. NHANES employed a multistage, stratified probability sampling design to generate a nationally representative sample of the non-institutionalized U.S. population. Health-related data were collected through standardized interviews, physical examinations, and laboratory testing 20 . The inclusion criteria were as follows: 1) adults aged ≥ 18 years were included; 2) Exclusion criteria consisted of pregnancy, lactation; 3) missing critical variables, or inability to undergo cardiovascular risk evaluation. A total of 4,689 participants were eligible and randomly assigned to training (n = 3,282) and validation (n = 1,407) sets at a 7:3 ratio ( Figure 1 ). Download figure Open in new tab Figure 1. Study participant selection process from NHANES 2007-2018. Definition of exposure Exposure variables included four lipid-related biomarkers, including triglyceride to high-density lipoprotein cholesterol ratio (TG/HDL-C), total cholesterol to HDL-C ratio (TC/HDL-C), low-density lipoprotein cholesterol to HDL-C ratio (LDL-C/HDL-C), and non-HDL-C. The HDL-C was measured using direct immunoassay or precipitation methods. The TC and HDL-C were measured enzymatically using the Hitachi 704 Analyzer (Boehringer Mannheim Diagnostics, Indianapolis, IN, USA). LDL-C was calculated using the Friedewald equation 21 . Non-HDL-C was derived by subtracting HDL-C from TC (Supplementary Table S1). All laboratory measurements were obtained from the NHANES laboratory database and standardized by the U.S. Centers for Disease Control and Prevention. Definition of cardiovascular-kidney-metabolic syndrome The primary outcome was CKM syndrome, defined by the 2023 American Heart Association staging criteria. CKM stages were determined based on three dimensions, including metabolic dysfunction, CVD, and CKD 22 . Stage 0 indicated no CKM risk, stage 1 included individuals with obesity or impaired glucose metabolism, stage 2 involved additional metabolic disorders or moderate-to-high CKD risk, stage 3 reflected subclinical CVD, and stage 4 indicated established clinical CVD (Supplementary Table S2). Ten-year CVD risk was estimated using the AHA PREVENT equations, applicable to adults aged 30–79 years. High CVD risk was defined as a predicted 10-year risk ≥20%. CKD staging was determined based on estimated glomerular filtration rate (eGFR), calculated using the race-neutral CKD-EPI 2021 creatinine equation, and urinary albumin-to-creatinine ratio (ACR). Covariates Covariates included demographic variables (age, sex, race, education level, marital status, and poverty income ratio (PIR)), lifestyle behaviors (smoking, alcohol use), chronic conditions (hypertension, diabetes, heart disease, angina, myocardial infarction, stroke), and laboratory biomarkers (body mass index (BMI), albumin, and creatinine) (Supplementary Table S3). Statistical analysis Baseline characteristics were summarized for the total sample, training, and validation sets. Continuous variables were reported as weighted means with standard errors (SE), and categorical variables as weighted percentages. Between-group differences were evaluated using weighted t-tests 23 . Restricted cubic spline (RCS) models were applied to assess nonlinear associations between lipid ratios and CKM risk, with p -overall and p -nonlinear used to test significance 24 . To address high-dimensional input variables, the least absolute shrinkage and selection operator (LASSO) regression was used for feature selection 25 . The optimal penalty parameter was determined using 10-fold cross-validation to minimize mean squared error. Generalized variance inflation factors were calculated to evaluate multicollinearity, values below 10 were considered acceptable. Four supervised machine learning methods were developed using the training set, including random forest (RF), support vector machine (SVM), decision tree (DT), and multilayer perceptron (MLP) 26 . Data preprocessing included one-hot encoding for categorical variables and standardization for continuous variables. Hyperparameters were optimized using grid search and cross-validation. Model performance was assessed using area under the curve (AUC), accuracy, sensitivity, specificity, and F 1 score. Confusion matrices were generated to visually compare classification results, and the model with the highest overall performance was selected. To interpret model output, SHapley Additive exPlanations (SHAP) were used to quantify each variable’s contribution 27 . Variable importance rankings and SHAP dependency plots were created to assess directional influence. Partial dependence plots (PDPs) were applied to examine synergistic effects and variable interactions 28 . To quantify the independent association between the key lipid biomarker and CKM syndrome, multivariable logistic regression models were employed, where participants were dichotomized into two groups: Stage 0 (no CKM risk) versus Stages 1-4 (presence of CKM risk) 29 . Specifically, Model 1 (unadjusted) used univariate logistic regression to assess the crude association of key lipid biomarkers with CKM syndrome, while Model 2 (adjusted) used multivariable logistic regression, adjusting for sex, age, education level, and hypertension status. Results for both models were expressed as odds ratios (ORs) with corresponding 95% confidence intervals (95% CI). This logistic regression analysis was performed separately on both the training set and the validation set. All analyses were conducted in R (version 4.4.1) and Python (version 3.12.3), with visualizations produced using “ggplot2” and “matplotlib”. A two-sided p -value <0.05 was considered statistically significant. Results Baseline characteristics of participants A total of 4,689 participants were included and stratified by CKM syndrome stage. Among the overall population, 50.8% were female, and 59.8% were aged ≥45 years ( Table 1 ). Non-Hispanic White individuals comprised 51.1%. Statistically significant differences ( p < 0.05) were observed across CKM stages in sociodemographic factors (age, sex, race, marital status, education, PIR), lifestyle behaviors (smoking, alcohol use), comorbidities (hypertension, diabetes, heart disease, angina, stroke), and biochemical indicators (serum creatinine, HDL-C, TC). Although the proportion of females was balanced across most stages, it declined to 41.3% in Stage 4. The proportion of individuals aged ≥45 years increased to 94.8% in Stage 4. Non-Hispanic White participants were most prevalent in Stage 4 (64.5%), and this stage also had the highest proportion of married individuals (55.5%). Higher education levels (College graduate or above) decreased with CKM progression, dropping from 36% in Stage 0 to 18.2% in Stage 4. The proportion of non-drinkers increased from 20.2% to 28.9% in Stage 4. Serum albumin declined from 4.38 g/dL to 4.14 g/dL, creatinine increased from 70.89 to 95.08 mg/dL, BMI from 22.03 to 30.14 kg/m², and glucose from 93.02 to 119.50 mg/dL ( Table 1 ). In the training set, all variables differed significantly by CKM stage; in the validation set, all but depression showed significance (Supplementary Table S4-S5). View this table: View inline View popup Table 1 Baseline characteristics of the total study population according to different stages of CKM syndrome. Nonlinear associations between lipid markers and CKM risk The RCS identified significant nonlinear relationships between CKM risk and lipid markers, including low-density lipoprotein (LDL) ( p -overall < 0.01; p -nonlinear < 0.01), TG ( p -overall < 0.01; p -nonlinear < 0.01), and TC ( p -overall < 0.01; p -nonlinear = 0.0208). Increased levels of glucose, TG/HDL-C, TC/HDL-C, LDL-C/HDL-C, and non-HDL-C were positively associated with CKM risk ( p -overall < 0.05), whereas higher high-density lipoprotein cholesterol (HDL) was inversely associated ( p -overall < 0.01; p -nonlinear < 0.01) ( Figure 2 ). Download figure Open in new tab Figure 2. RCS curves of significant exposure variables associated with CKM syndrome. (A) Glucose. (B) HDL. (C) LDL. (D) TG. (E) TC. (F) TG/HDL-C. (G) TC/HDL-C. (H) LDL-C/HDL-C. (I) non-HDL-C. Feature selection and machine learning model performance The association between cross-validation error and the log-transformed penalty parameter (λ) in LASSO regression analyses was used to identify exposures that are more relevant to CKM syndrome, and the 24 exposures included in the LASSO regressions had the smallest error in the model at λ = 3×10 - 5 , with all variables retained, suggesting that all variables are potentially relevant ( Figure 3 ). Download figure Open in new tab Figure 3. LASSO screening of characterization variables. (A) LASSO coefficient paths. Horizontal axis: log(lambda); vertical axis: variable coefficients. As lambda increases, coefficients shrink toward zero. Variables with zero coefficients are excluded at the optimal lambda. (B) LASSO cross-validation. Horizontal axis: log(lambda); vertical axis: model error. Optimal lambda minimizes model error. The RF model demonstrated superior performance, with an AUC of 0.97, accuracy of 93.106%, sensitivity of 0.953, and specificity of 0.784. In comparison, the DT (AUC = 0.84), SVM (AUC = 0.94), and MLP (AUC = 0.93) models in the training set showed lower specificity. The confusion matrix for the RF model showed 1,165 true positives, 57 false positives, 145 true negatives, and 40 false negatives, confirming its suitability as the final predictive model ( Figure 4 , Supplementary Table S6). Download figure Open in new tab Figure 4. ROC curves of the test and train sets and mixing matrices. (A) RF. (B) DT. (C) SVM. (D) MLP. Variable importance in the RF model Variable importance analysis revealed that BMI had the highest predictive contribution (importance = 0.454), followed by TG (0.100), TG/HDL-C (0.097), and glucose (0.095). In contrast, TC (0.036) and LDL (0.035) demonstrated lower contributions ( Figure 5A ). Download figure Open in new tab Figure 5. RF model. (A) Characteristic importance of RF models. (B) The effect of each feature in the predictive model on the CKM syndrome was explained by the SHAP value in the RF models. Relationships between the lipid markers and CKM syndrome PDPs showed that TG/HDL-C and non-HDL-C levels were associated with increased CKM risk. A nonlinear pattern was observed for TC/HDL-C, which initially increased with risk and then declined. An inverse association was noted for LDL-C/HDL-C (Supplementary Figure S1). Synergistic effects of lipid markers and CKM syndrome The synergistic effects revealed that TG/HDL-C and TC/HDL-C synergistically elevated predicted CKM risk, with TG/HDL-C playing a dominant role. Further synergistic effects between TC/HDL-C and LDL-C/HDL-C, as well as between LDL-C/HDL-C and non-HDL-C, which significantly affect CKM syndrome risk estimation. Lower LDL-C/HDL-C and higher non-HDL-C levels were consistently linked to elevated CKM syndrome risk (Supplementary Figure S2). Model decision of SHAP The SHAP analysis indicated that elevated TG/HDL-C, TC/HDL-C, and non-HDL-C levels were associated with higher SHAP values, suggesting a greater CKM risk. The SHAP value for TG/HDL-C plateaued at higher values. TC/HDL-C showed stable contributions at mid-range levels but fluctuated at extremes. Non-HDL-C exhibited a rising trend that eventually stabilized, while LDL-C/HDL-C showed decreasing SHAP values with increasing levels (Supplementary Figure S3). SHAP importance rankings further confirmed BMI as the strongest predictor. The TG and TG/HDL-C were positively associated with risk, while glucose and TC/HDL-C demonstrated a negative association ( Figure 5B ). Association between TG/HDL-C and CKM syndrome Logistic regression analysis conducted in both the training set and validation set (n = 645 for Stage 0; n = 4,044 for Stages 1-4) confirmed TG/HDL-C as a robust independent predictor of CKM syndrome. In unadjusted models (model 1), significant associations were observed in the training (OR = 3.11; 95% CI: 2.49-3.88; p < 0.01) and validation sets (OR = 3.10; 95% CI: 2.39-4.01; p < 0.01). After adjustment for sex, age, education level, and hypertension (model 2), the association remained statistically significant in the testing (OR = 3.39; 95% CI: 2.52-4.54; p < 0.01), confirming its independent predictive value ( Figure 6 ). Download figure Open in new tab Figure 6. Forest plots comparing model 1 and model 2 between TG/HDL-C and CKM syndrome. Note: contains only the TGH univariate model; Model 2: based on model 1, 4 indicators of sex, age, education, and Hypertension were added to the training set. Discussion A comprehensive evaluation of non-traditional lipid parameters revealed their strong association with CKM syndrome, offering critical insights into both pathophysiology and potential early identification of this multi-organ disorder. Elevated TG/HDL-C and non-HDL-C were identified as key contributors to CKM risk, with TG/HDL-C emerged as a strong predictor of CKM risk when combined with TC/HDL-C. Predictive models incorporating these indices achieved superior performance, highlighting the non-linear interactions among lipid fractions that traditional linear analyses fail to capture. SHAP analysis further confirmed TG/HDL-C as a robust independent predictor, exhibiting stabilized influence at higher values and aligning with its pathophysiological relevance in cardiometabolic dysregulation. Logistic regression analysis reinforced its independent predictive capacity across both training and validation cohorts, with adjusted ORs remaining significant, emphasizing its potential utility for early risk stratification. Dyslipidemia remains a principal driver of CKM syndrome, with triglycerides and LDL-C recognized as key determinants of CVD risk and prognosis, whereas HDL-C exerts protective effects through cholesterol efflux, endothelial stabilization, and antioxidant activity 30 – 32 . Conventional lipid metrics, though routinely employed in clinical practice, insufficiently capture the complex metabolic interactions underpinning multi-organ pathophysiology in CKM. Non-traditional lipid parameters integrate multiple lipid fractions, providing a more comprehensive reflection of systemic metabolic disturbance and atherogenic potential 33 – 36 . These observations align with prior cohort studies demonstrating that elevated TG/HDL-C, non-HDL-C, and cholesterol retention indices are associated with increased incidence of CVD, type 2 diabetes (T2D), and CKD. Longitudinal data from the NAGALA cohort and the Korean National Health Examination Survey further demonstrated that non-traditional lipid indices independently predict incident diabetes and, when combined with abdominal obesity, substantially increase the cumulative risk of CMM 33 . Mechanistic evidence supports the role of “pan-lipotoxicity” in CKM pathogenesis, extending beyond traditional triglyceride-centered lipotoxicity. Dysregulated adipose tissue function, ectopic lipid deposition, and abnormal secretion of adipokines and bioactive metabolites collectively contribute to multi-organ injury 37 , 38 . Elevated TG levels activate cholesteryl ester transfer protein (CETP), reducing HDL-C while increasing LDL-C, thereby generating small dense LDL particles with enhanced endothelial permeability and pro-inflammatory potential 39 , 40 . Dyslipidemia contributes to both atherosclerosis and thrombogenesis, exacerbates insulin resistance, and promotes metabolic syndrome progression, amplifying cardiovascular and renal injury 41 , 42 . Renal pathophysiology in CKM is tightly linked to lipid-mediated damage, excessive cholesterol and phospholipid reabsorption in proximal tubules triggers tubulointerstitial inflammation, foam cell formation, and fibrotic remodeling, while intracellular cholesterol accumulation impairs podocyte and tubular cell function, perpetuating CKD progression 43 – 46 . Reciprocal interactions between declining renal function and lipid dysregulation create a feed-forward loop that exacerbates multi-organ deterioration 47 . These findings provide a mechanistic rationale for the observed superior predictive value of TG/HDL-C in identifying individuals at risk for CKM syndrome. Recent studies emphasize the interplay between lipid abnormalities and subclinical cardiovascular dysfunction. Elevated TG/HDL-C correlates with endothelial impairment, reduced vascular compliance, and chronic low-grade inflammation, contributing to early atherogenesis and left ventricular remodeling 35 , 36 . Concurrent derangements in non-HDL-C and TC/HDL-C reflect cumulative atherogenic burden and residual risk not captured by LDL-C 10 , 11 . Multi-parametric lipid evaluation thus enables earlier identification of cardiometabolic derangements and high-risk individuals prior to overt CKM manifestation. The additive and synergistic effects of lipid indices further underscore the importance of integrated metrics rather than reliance on single measures for risk assessment. From a clinical perspective, incorporating non-traditional lipid parameters into risk assessment frameworks represents a paradigm shift. Tree-based machine learning algorithms leveraged the complex interactions among lipid indices to enhance predictive accuracy. SHAP and partial dependence analyses elucidated individual contributions as well as synergistic interactions, providing mechanistic insight into their predictive utility 12 . Such approaches highlight the limitations of linear modeling in capturing the multi-dimensional and non-linear nature of CKM, supporting the adoption of advanced computational methods for comprehensive risk stratification. Moreover, machine learning outputs offer interpretable metrics that could facilitate personalized intervention strategies, such as identifying individuals most likely to benefit from targeted lipid-lowering therapies or lifestyle modification. Policy and public health implications are substantial. With the global prevalence of metabolic syndrome, CKD, and CVD continuing to rise, early identification of high-risk populations using integrative lipid metrics could inform preventative strategies, including structured lifestyle interventions, pharmacotherapy addressing dyslipidemia and insulin resistance, and individualized monitoring programs. Population-level screening programs incorporating non-traditional lipid indices may facilitate the detection of subclinical CKM, enabling timely intervention to prevent progression to end-organ damage 34 , 48 . Such strategies align with contemporary guidelines emphasizing multi-dimensional risk assessment and personalized management in metabolic and cardiovascular disorders. This study provides several novel contributions. First, it represents one of the largest analyses examining non-traditional lipid parameters in relation to CKM syndrome, establishing TG/HDL-C as a particularly robust predictor. Second, it employs machine learning methodologies to model complex non-linear relationships among lipid fractions and disease outcomes, providing a framework for future integrative risk prediction tools. Third, by combining clinical, laboratory, and demographic variables, the study offers a holistic perspective on early cardiometabolic and renal risk that could be leveraged in both clinical and public health contexts. Furthermore, mechanistic interpretations grounded in pan-lipotoxicity and lipid-mediated endothelial and renal injury support the biological plausibility of the observed associations, bridging epidemiologic findings with underlying pathophysiology. Several limitations warrant consideration. First, CVD risk was estimated using the Framingham 10-year risk score, which may not fully capture all subclinical pathologies or account for emerging risk factors. Second, cardiovascular outcomes were self-reported, potentially introducing measurement bias and underreporting. Third, the study population was limited to U.S. adults, which may reduce the generalizability of findings to other ethnicities or geographic regions. Fourth, as an observational analysis, causality cannot be inferred, and residual confounding by unmeasured factors, including dietary patterns, genetic predisposition, and inflammatory biomarkers, cannot be entirely excluded. Fifth, molecular biomarkers, advanced imaging, and metabolomic data were unavailable, limiting mechanistic exploration. Future research should leverage prospective multi-ethnic cohorts, integrate multi-omics, inflammatory and endothelial biomarkers, and utilize imaging to validate non-traditional lipid parameters in CKM risk prediction and to elucidate pathways linking dyslipidemia, insulin resistance, and multi-organ injury. Emerging areas for further investigation include the interaction of non-traditional lipid parameters with gut microbiota, systemic inflammation, and oxidative stress pathways, which may modulate cardiometabolic risk in CKM populations. In addition, evaluating the longitudinal trajectories of lipid indices in relation to CKM progression could inform dynamic risk prediction models. The potential benefits of interventions targeting TG/HDL-C and non-HDL-C for multi-organ protection remain largely unexplored, warranting randomized clinical trials and mechanistic studies. Integrating lifestyle, pharmacologic, and precision medicine approaches based on these predictive indices may optimize early prevention strategies, mitigate end-organ damage, and reduce long-term healthcare burden. Conclusion In summary, BMI emerges as the key predictive factor for CKM, accounting for 0.454 of the predictive power. Additionally, the TG/HDL-C (0.097) and glucose (0.095) further refine risk stratification. Analysis indicates a positive correlation between TG/HDL-C and non-HDL-C with the occurrence of CKM, while the LDL-C/HDL-C shows a significant negative association. SHAP values and PDPs reveal that high TG/HDL-C and high TC/HDL-C synergistically promote CKM. Therefore, future CKM screening systems could consider incorporating the TG/HDL-C ratio, particularly for individuals with a BMI greater than 25 kg/m 2 . However, prospective studies are needed to validate causality and explore precise intervention strategies. Data Availability All data are publicly available and can be accessed at the NHANES website (https://wwwn.cdc.gov/nchs/nhanes/Default.aspx). https://wwwn.cdc.gov/nchs/nhanes/Default.aspx Sources of Funding This study was supported by the Basic Research Program of Natural Science in Shaanxi Province (Project No.: 2024JC-YBMS-609). Disclosures None. Acknowledgments The authors thank the National Center for Health Statistics of the Centers for Disease Control and Prevention for sharing the NHANES data. Footnotes Authorship Responsibilities: ZhaoXia Zhang: conception and desig; Ya Shi and Lu Zhang: acquisition of data; YuYing Wang: analysis and interpretation of data; Nan Wang and Jie Zhang: drafting the manuscript; Ying Xing: revising the manuscript; QianQian Lv: final approval of the version to be published Reference 1. ↵ Ndumele CE , Rangaswami J , Chow SL , Neeland IJ , Tuttle KR , Khan SS , Coresh J , Mathew RO , Baker-Smith CM , Carnethon MR , et al. Cardiovascular-Kidney-Metabolic Health: A Presidential Advisory From the American Heart Association . Circulation . 2023 ; 148 : 1606 – 1635 . doi: 10.1161/cir.0000000000001184 OpenUrl CrossRef PubMed 2. ↵ Zhu D , Judge PK , Wanner C , Haynes R , Herrington WG . The prevention and management of chronic kidney disease among patients with metabolic syndrome . Kidney international . 2025 ; 107 : 816 – 824 . doi: 10.1016/j.kint.2024.12.021 OpenUrl CrossRef PubMed 3. ↵ Israelsen M , Francque S , Tsochatzis EA , Krag A . Steatotic liver disease . Lancet (London, England) . 2024 ; 404 : 1761 – 1778 . doi: 10.1016/s0140-6736(24)01811-7 OpenUrl CrossRef PubMed 4. ↵ Rinella ME , Lazarus JV , Ratziu V , Francque SM , Sanyal AJ , Kanwal F , Romero D , Abdelmalek MF , Anstee QM , Arab JP , et al. A multisociety Delphi consensus statement on new fatty liver disease nomenclature . Annals of hepatology . 2024 ; 29 : 101133 . doi: 10.1016/j.aohep.2023.101133 OpenUrl CrossRef PubMed 5. ↵ Giovannucci E , Harlan DM , Archer MC , Bergenstal RM , Gapstur SM , Habel LA , Pollak M , Regensteiner JG , Yee D . Diabetes and Cancer: A Consensus Report . CA: a cancer journal for clinicians . 2010 ; 60 : 207 – 221 . doi: 10.3322/caac.20078 OpenUrl CrossRef PubMed Web of Science 6. ↵ Esposito K , Chiodini P , Colao A , Lenzi A , Giugliano D . Metabolic syndrome and risk of cancer: a systematic review and meta-analysis . Diabetes care . 2012 ; 35 : 2402 – 2411 . doi: 10.2337/dc12-0336 OpenUrl Abstract / FREE Full Text 7. ↵ Ostrominski JW , Arnold SV , Butler J , Fonarow GC , Hirsch JS , Palli SR , Donato BMK , Parrinello CM , O’Connell T , Collins EB , et al. Prevalence and Overlap of Cardiac, Renal, and Metabolic Conditions in US Adults, 1999-2020 . JAMA cardiology . 2023 ; 8 : 1050 – 1060 . doi: 10.1001/jamacardio.2023.3241 OpenUrl CrossRef PubMed 8. ↵ Xie Z , Yu C , Cui Q , Zhao X , Zhuang J , Chen S , Guan H , Li J . Global Burden of the Key Components of Cardiovascular-Kidney-Metabolic Syndrome . Journal of the American Society of Nephrology : JASN . 2025 ; 36 : 1572 – 1584 . doi: 10.1681/asn.0000000658 OpenUrl CrossRef PubMed 9. ↵ Zheng X , Zhang X , Han Y , Hu H , Cao C . Nonlinear relationship between atherogenic index of plasma and the risk of prediabetes: a retrospective study based on Chinese adults . Cardiovascular diabetology . 2023 ; 22 : 205 . doi: 10.1186/s12933-023-01934-0 OpenUrl CrossRef 10. ↵ Brandts J , Tittel SR , Bramlage P , Danne T , Brix JM , Zimny S , Heyer CHJ , Holl RW , Müller-Wieland D . Low-density lipoprotein cholesterol and non-high-density lipoprotein cholesterol in type 1 diabetes and type 2 diabetes: Lipid goal attainment in a large German-Austrian diabetes registry . Diabetes, obesity & metabolism . 2023 ; 25 : 3700 – 3708 . doi: 10.1111/dom.15264 OpenUrl CrossRef PubMed 11. ↵ Yu S , Yan L , Yan J , Sun X , Fan M , Liu H , Li Y , Guo M . The predictive value of nontraditional lipid parameters for intracranial and extracranial atherosclerotic stenosis: a hospital-based observational study in China . Lipids in health and disease . 2023 ; 22 : 16 . doi: 10.1186/s12944-022-01761-4 OpenUrl CrossRef 12. ↵ Zhao Y , Zhuang Z , Li Y , Xiao W , Song Z , Huang N , Wang W , Dong X , Jia J , Clarke R , et al. Elevated blood remnant cholesterol and triglycerides are causally related to the risks of cardiometabolic multimorbidity . Nature communications . 2024 ; 15 : 2451 . doi: 10.1038/s41467-024-46686-x OpenUrl CrossRef PubMed 13. Zeljkovic A , Vekic J , Stefanovic A . Obesity and dyslipidemia in early life: Impact on cardiometabolic risk . Metabolism: clinical and experimental . 2024 ; 156 : 155919 . doi: 10.1016/j.metabol.2024.155919 OpenUrl CrossRef 14. ↵ Li M , Zhang W , Zhang M , Li L , Wang D , Yan G , Qiao Y , Tang C . Nonlinear relationship between untraditional lipid parameters and the risk of prediabetes: a large retrospective study based on Chinese adults . Cardiovascular diabetology . 2024 ; 23 : 12 . doi: 10.1186/s12933-023-02103-z OpenUrl CrossRef 15. ↵ Li S , Yin C , Zhao W , Zhu H , Xu D , Xu Q , Jiao Y , Wang X , Qiao H . Homeostasis model assessment of insulin resistance in relation to the poor functional outcomes in nondiabetic patients with ischemic stroke . Bioscience reports . 2018 ; 38 . doi: 10.1042/bsr20180330 OpenUrl CrossRef 16. Khadka T , Giri GK , Sherpa P , Ghimire U , Parajuli S , Pudasaini A , Shrestha S . Dyslipidemia among Patients with Ischemic Stroke Admitted to the Department of Medicine of a Tertiary Care Centre . JNMA; journal of the Nepal Medical Association . 2023 ; 61 : 718 – 722 . doi: 10.31729/jnma.8261 OpenUrl CrossRef PubMed 17. ↵ Zhang F , Liu L , Zhang C , Ji S , Mei Z , Li T . Association of Metabolic Syndrome and Its Components With Risk of Stroke Recurrence and Mortality: A Meta-analysis . Neurology . 2021 ; 97 : e695 – e705 . doi: 10.1212/wnl.0000000000012415 OpenUrl CrossRef PubMed 18. ↵ James DE , Stöckli J , Birnbaum MJ . The aetiology and molecular landscape of insulin resistance . Nature reviews Molecular cell biology . 2021 ; 22 : 751 – 771 . doi: 10.1038/s41580-021-00390-6 OpenUrl CrossRef PubMed 19. ↵ Tilg H , Ianiro G , Gasbarrini A , Adolph TE . Adipokines: masterminds of metabolic inflammation . Nature reviews Immunology . 2025 ; 25 : 250 – 265 . doi: 10.1038/s41577-024-01103-8 OpenUrl CrossRef PubMed 20. ↵ Gao C , Gao S , Zhao R , Shen P , Zhu X , Yang Y , Duan C , Wang Y , Ni H , Zhou L , et al. Association between systemic immune-inflammation index and cardiovascular-kidney-metabolic syndrome . Sci Rep . 2024 ; 14 : 19151 . doi: 10.1038/s41598-024-69819-0 OpenUrl CrossRef 21. ↵ Sampson M , Ling C , Sun Q , Harb R , Ashmaig M , Warnick R , Sethi A , Fleming JK , Otvos JD , Meeusen JW , et al. A New Equation for Calculation of Low-Density Lipoprotein Cholesterol in Patients With Normolipidemia and/or Hypertriglyceridemia . JAMA cardiology . 2020 ; 5 : 540 – 548 . doi: 10.1001/jamacardio.2020.0013 OpenUrl CrossRef PubMed 22. ↵ Tan MY , Zhang YJ , Zhu SX , Wu S , Zhang P , Gao M . The prognostic significance of stress hyperglycemia ratio in evaluating all-cause and cardiovascular mortality risk among individuals across stages 0-3 of cardiovascular-kidney-metabolic syndrome: evidence from two cohort studies . Cardiovascular diabetology . 2025 ; 24 : 137 . doi: 10.1186/s12933-025-02689-6 OpenUrl CrossRef 23. ↵ Reedy J , Lerman JL , Krebs-Smith SM , Kirkpatrick SI , Pannucci TE , Wilson MM , Subar AF , Kahle LL , Tooze JA . Evaluation of the Healthy Eating Index-2015 . Journal of the Academy of Nutrition and Dietetics . 2018 ; 118 : 1622 – 1633 . doi: 10.1016/j.jand.2018.05.019 OpenUrl CrossRef 24. ↵ Wu M , Si J , Liu Y , Kang L , Xu B . Association between composite dietary antioxidant index and hypertension: insights from NHANES . Clinical and experimental hypertension (New York, NY : 1993) . 2023 ; 45 : 2233712 . doi: 10.1080/10641963.2023.2233712 OpenUrl CrossRef PubMed 25. ↵ Wei H , Sun J , Shan W , Xiao W , Wang B , Ma X , Hu W , Wang X , Xia Y . Environmental chemical exposure dynamics and machine learning-based prediction of diabetes mellitus . The Science of the total environment . 2022 ; 806 : 150674 . doi: 10.1016/j.scitotenv.2021.150674 OpenUrl CrossRef 26. ↵ Li W , Huang G , Tang N , Lu P , Jiang L , Lv J , Qin Y , Lin Y , Xu F , Lei D . Effects of heavy metal exposure on hypertension: A machine learning modeling approach . Chemosphere . 2023 ; 337 : 139435 . doi: 10.1016/j.chemosphere.2023.139435 OpenUrl CrossRef 27. ↵ Cao S , Hu Y . Creating machine learning models that interpretably link systemic inflammatory index, sex steroid hormones, and dietary antioxidants to identify gout using the SHAP (SHapley Additive exPlanations) method . Front Immunol . 2024 ; 15 : 1367340 . doi: 10.3389/fimmu.2024.1367340 OpenUrl CrossRef 28. ↵ Gui Y , Gui S , Wang X , Li Y , Xu Y , Zhang J . Exploring the relationship between heavy metals and diabetic retinopathy: a machine learning modeling approach . Sci Rep . 2024 ; 14 : 13049 . doi: 10.1038/s41598-024-63916-w OpenUrl CrossRef 29. ↵ Zhu R , Wang R , He J , Wang L , Chen H , Niu X , Sun Y , Guan Y , Gong Y , Zhang L , et al. Prevalence of Cardiovascular-Kidney-Metabolic Syndrome Stages by Social Determinants of Health . JAMA network open . 2024 ; 7 : e2445309 . doi: 10.1001/jamanetworkopen.2024.45309 OpenUrl CrossRef 30. ↵ Pikkemaat M , Woodward M , Af Geijerstam P , Harrap S , Hamet P , Mancia G , Marre M , Poulter N , Chalmers J , Harris K . Lipids and apolipoproteins and the risk of vascular disease and mortality outcomes in women and men with type 2 diabetes in the ADVANCE study . Diabetes, obesity & metabolism . 2024 ; 26 : 5669 – 5680 . doi: 10.1111/dom.15935 OpenUrl CrossRef PubMed 31. Di Angelantonio E , Sarwar N , Perry P , Kaptoge S , Ray KK , Thompson A , Wood AM , Lewington S , Sattar N , Packard CJ , et al. Major lipids, apolipoproteins, and risk of vascular disease . Jama . 2009 ; 302 : 1993 – 2000 . doi: 10.1001/jama.2009.1619 OpenUrl CrossRef PubMed Web of Science 32. ↵ Kou T , Luo H , Yin L . Relationship between neutrophils to HDL-C ratio and severity of coronary stenosis . BMC cardiovascular disorders . 2021 ; 21 : 127 . doi: 10.1186/s12872-020-01771-z OpenUrl CrossRef 33. ↵ Kim J , Shin SJ , Kim Y-s , Kang H-TJCD . Positive association between the ratio of triglycerides to high-density lipoprotein cholesterol and diabetes incidence in Korean adults . 2021 ; 20 . 34. ↵ Lai H , Tu Y , Liao C , Zhang S , He L , Li J . Joint assessment of abdominal obesity and non-traditional lipid parameters for primary prevention of cardiometabolic multimorbidity: insights from the China health and retirement longitudinal study 2011-2018 . Cardiovascular diabetology . 2025 ; 24 : 109 . doi: 10.1186/s12933-025-02667-y OpenUrl CrossRef 35. ↵ Hu Y , Liang Y , Li J , Li X , Yu M , Cui W . Correlation between atherogenic index of plasma and cardiovascular disease risk across Cardiovascular-kidney-metabolic syndrome stages 0-3: a nationwide prospective cohort study . Cardiovascular diabetology . 2025 ; 24 : 40 . doi: 10.1186/s12933-025-02593-z OpenUrl CrossRef 36. ↵ Yin B , Wu Z , Xia Y , Xiao S , Chen L , Li Y . Non-linear association of atherogenic index of plasma with insulin resistance and type 2 diabetes: a cross-sectional study . Cardiovascular diabetology . 2023 ; 22 : 157 . doi: 10.1186/s12933-023-01886-5 OpenUrl CrossRef 37. ↵ Lee Y , Hirose H , Ohneda M , Johnson JH , McGarry JD , Unger RH . Beta-cell lipotoxicity in the pathogenesis of non-insulin-dependent diabetes mellitus of obese rats: impairment in adipocyte-beta-cell relationships . Proceedings of the National Academy of Sciences of the United States of America . 1994 ; 91 : 10878 – 10882 . doi: 10.1073/pnas.91.23.10878 OpenUrl Abstract / FREE Full Text 38. ↵ Cheng Y , Shao S , Wang Z , Guan Q , Li H , Liu G , Zhang H , Fan X , Zhao J . From lipotoxicity to pan-lipotoxicity . Cell discovery . 2025 ; 11 : 27 . doi: 10.1038/s41421-025-00787-z OpenUrl CrossRef 39. ↵ Rabiee Rad M , Ghasempour Dabaghi G , Darouei B , Amani-Beni R . The association of atherogenic index of plasma with cardiovascular outcomes in patients with coronary artery disease: A systematic review and meta-analysis . Cardiovascular diabetology . 2024 ; 23 : 119 . doi: 10.1186/s12933-024-02198-y OpenUrl CrossRef PubMed 40. ↵ Kutkiene S , Petrulioniene Z , Laucevicius A , Matuzeviciene G , Kasiulevicius V , Petrulionyte E , Staigyte J , Saulyte A , Gargalskaite U , Skiauteryte E , et al. Cardiovascular risk profile of patients with atherogenic dyslipidemia in middle age Lithuanian population . Lipids in health and disease . 2018 ; 17 : 208 . doi: 10.1186/s12944-018-0851-0 OpenUrl CrossRef 41. ↵ Boizel R , Benhamou PY , Lardy B , Laporte F , Foulon T , Halimi S . Ratio of triglycerides to HDL cholesterol is an indicator of LDL particle size in patients with type 2 diabetes and normal HDL cholesterol levels . Diabetes care . 2000 ; 23 : 1679 – 1685 . doi: 10.2337/diacare.23.11.1679 OpenUrl Abstract / FREE Full Text 42. ↵ Tagoe EA , Dwamena-Akoto E , Nsaful J , Aikins AR , Clegg-Lamptey JN , Quaye O . High atherogenic index of plasma and cardiovascular risk factors among Ghanaian breast cancer patients. Experimental biology and medicine (Maywood , NJ ) . 2020 ; 245 : 1648 – 1655 . doi: 10.1177/1535370220940992 OpenUrl CrossRef 43. ↵ Chabowski DS , Cohen KE , Abu-Hatoum O , Gutterman DD , Freed JK . Crossing signals: bioactive lipids in the microvasculature . American journal of physiology Heart and circulatory physiology . 2020 ; 318 : H1185 – h1197 . doi: 10.1152/ajpheart.00706.2019 OpenUrl CrossRef PubMed 44. Magil AB . Interstitial foam cells and oxidized lipoprotein in human glomerular disease. Modern pathology : an official journal of the United States and Canadian Academy of Pathology , Inc . 1999 ; 12 : 33 – 40 . OpenUrl 45. Gai Z , Wang T , Visentin M , Kullak-Ublick GA , Fu X , Wang Z. Lipid Accumulation and Chronic Kidney Disease . Nutrients . 2019 ; 11 . doi: 10.3390/nu11040722 OpenUrl CrossRef 46. ↵ Vaziri ND . Lipotoxicity and impaired high density lipoprotein-mediated reverse cholesterol transport in chronic kidney disease . Journal of renal nutrition : the official journal of the Council on Renal Nutrition of the National Kidney Foundation . 2010 ; 20 : S35 – 43 . doi: 10.1053/j.jrn.2010.05.010 OpenUrl CrossRef PubMed 47. ↵ Tonelli M , Wiebe N , Culleton B , House A , Rabbat C , Fok M , McAlister F , Garg AX . Chronic kidney disease and mortality risk: a systematic review . Journal of the American Society of Nephrology : JASN . 2006 ; 17 : 2034 – 2047 . doi: 10.1681/asn.2005101085 OpenUrl CrossRef PubMed 48. ↵ Zhang YB , Sheng LT , Wei W , Guo H , Yang H , Min X , Guo K , Yang K , Zhang X , He M , et al. Association of blood lipid profile with incident chronic kidney disease: A Mendelian randomization study . Atherosclerosis . 2020 ; 300 : 19 – 25 . doi: 10.1016/j.atherosclerosis.2020.03.020 OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted September 29, 2025. Download PDF Data/Code Email Thank you for your interest in spreading the word about medRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following Non-Traditional Lipid Ratios Predict Cardiovascular-Kidney-Metabolic Syndrome: Insights from Machine Learning Model Using NHANES Data Message Subject (Your Name) has forwarded a page to you from medRxiv Message Body (Your Name) thought you would like to see this page from the medRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share Non-Traditional Lipid Ratios Predict Cardiovascular-Kidney-Metabolic Syndrome: Insights from Machine Learning Model Using NHANES Data Nan Wang , Jie Zhang , YuYing Wang , ZhaoXia Zhang , Ya Shi , Lu Zhang , Ying Xing , QianQian Lv medRxiv 2025.09.26.25336774; doi: https://doi.org/10.1101/2025.09.26.25336774 Share This Article: Copy Citation Tools Non-Traditional Lipid Ratios Predict Cardiovascular-Kidney-Metabolic Syndrome: Insights from Machine Learning Model Using NHANES Data Nan Wang , Jie Zhang , YuYing Wang , ZhaoXia Zhang , Ya Shi , Lu Zhang , Ying Xing , QianQian Lv medRxiv 2025.09.26.25336774; doi: https://doi.org/10.1101/2025.09.26.25336774 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Epidemiology Subject Areas All Articles Addiction Medicine (568) Allergy and Immunology (863) Anesthesia (299) Cardiovascular Medicine (4425) Dentistry and Oral Medicine (443) Dermatology (382) Emergency Medicine (607) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1507) Epidemiology (15221) Forensic Medicine (30) Gastroenterology (1123) Genetic and Genomic Medicine (6588) Geriatric Medicine (667) Health Economics (997) Health Informatics (4524) Health Policy (1368) Health Systems and Quality Improvement (1612) Hematology (540) HIV/AIDS (1264) Infectious Diseases (except HIV/AIDS) (15910) Intensive Care and Critical Care Medicine (1103) Medical Education (623) Medical Ethics (145) Nephrology (667) Neurology (6588) Nursing (346) Nutrition (998) Obstetrics and Gynecology (1143) Occupational and Environmental Health (956) Oncology (3331) Ophthalmology (970) Orthopedics (369) Otolaryngology (420) Pain Medicine (435) Palliative Medicine (129) Pathology (663) Pediatrics (1690) Pharmacology and Therapeutics (691) Primary Care Research (710) Psychiatry and Clinical Psychology (5440) Public and Global Health (9219) Radiology and Imaging (2195) Rehabilitation Medicine and Physical Therapy (1369) Respiratory Medicine (1196) Rheumatology (593) Sexual and Reproductive Health (710) Sports Medicine (529) Surgery (710) Toxicology (99) Transplantation (289) Urology (265) (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9ffc8ef7e969593a',t:'MTc3OTQ2MDY0Mg=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();