What is the clinical evidence from this study?

Study design: Cross-Sectional. Population: early arterial stiffness in community population (n=2948). Intervention: machine learning model using routine blood-derived indices vs. none. Primary outcome: Early increased arterial stiffness defined as brachial-ankle pulse wave velocity (baPWV) ≥ 1400 cm/s (AUC 0.877, 95% CI 0.865–0.889).

What does this research mean for the field?

A machine learning model based on seven routine clinical indicators, notably including the TyG-waist-to-height ratio, can accurately predict early arterial stiffness in a community population. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The study aims to develop a machine learning model for early prediction of arterial stiffness using blood-derived indices.

February 25, 2026Lipids in Health and Disease1 citationsOpen Access

A machine learning model based on routine blood-derived indices for early arterial stiffness prediction in the community

LZLiuting Zheng FXFeng Xiao KWKeyun Wang

Key Result

The machine learning model based on seven routine clinical indicators predicted early arterial stiffness with an AUC of 0.877 (95% CI: 0.865–0.889) in a community population of 2948 participants.

Key Points

The study aims to develop a machine learning model for early prediction of arterial stiffness using blood-derived indices.
Employed machine learning algorithms to identify predictors of arterial stiffness in a healthy population.
Conducted a cross-sectional analysis with 2948 community participants.
Used LASSO regression for variable selection and logistic regression for analysis of risk factors.
Developed a random forest model and SHAP analysis to rank predictors and visualize risk using a nomogram.
Identified early increased arterial stiffness in 55.5% of participants.
Nine independent risk factors were established, including MHR, CRI-I, CRI-II, and TyG-WHtR.
The model showed excellent discrimination (AUC = 0.877) and good calibration.

Study Design

Type

Cross-Sectional (n=2,948)

Multicenter

Yes

Structured PICO

Population

2,948 apparently healthy community-dwelling adults (1,753 females) recruited from 10 community centers in Beijing, China. Key exclusion criteria: history of clinically diagnosed CVD, prior diagnosis or current medication use for hypertension, diabetes mellitus, chronic kidney disease, autoimmune diseases, active malignancy, liver dysfunction, or thyroid dysfunction.

Outcome

Early increased arterial stiffness, defined as a brachial-ankle pulse wave velocity (baPWV) ≥ 1400 cm/ssurrogate

A machine learning model incorporating routine clinical and blood-derived indices, particularly TyG-WHtR, can accurately identify early arterial stiffness in community-dwelling adults.

Main Result

Effect estimate: AUC 0.877 (95% CI 0.865–0.889)

Limitations

Study design was cross-sectional and observational, limiting causal inference.
Single country (China) study limits generalizability.
Lack of external validation cohort for the prediction model.

Abstract

Increased arterial stiffness is a high-risk factor for cardiovascular diseases, making its early identification crucial. Based on data from an apparently healthy community-based population, this study employed machine learning algorithms to screen for factors influencing early arterial stiffness and constructed a risk prediction model for its development. In this cross-sectional study, 2948 community participants were enrolled between June and December 2024. Twenty-four blood-derived indices spanning metabolic, lipid, and inflammatory domains were calculated. Least absolute shrinkage and selection operator (LASSO) regression was used to select and adjust for significant confounders among baseline clinical variables. Univariate and multivariate logistic regression analyses were then performed to identify indicators independently associated with early increased arterial stiffness, defined as a brachial-ankle pulse wave velocity (baPWV) ≥ 1400 cm/s. A random forest model, combined with SHapley Additive exPlanations (SHAP) analysis, was employed to evaluate and rank the predictive importance of all candidate variables. Key predictors identified through these analyses were integrated to build a multivariate logistic regression model, visualized as a nomogram. Model performance was evaluated by discrimination, calibration, and decision curve analysis (DCA). Early increased arterial stiffness was identified in 1636 participants (55.5%). Multivariate analysis identified nine independent risk factors, including the monocyte-to-high-density lipoprotein cholesterol ratio (MHR), Castelli’s Risk Index I and II (CRI- I, CRI-II), atherogenic index (AI), TyG-waist circumference (TyG-WC), TyG-waist-to-height ratio (TyG-WHtR), neutrophil-to-HDL ratio (NHR), platelet-to-HDL ratio (PHR), and uric acid-to-HDL ratio (UHR). The random forest model highlighted age, systolic and diastolic blood pressure, TyG-WHtR, heart rate, fasting blood glucose, and glycated hemoglobin as top predictors. SHAP analysis confirmed the substantial contribution of TyG-WHtR. The resulting nomogram demonstrated excellent discrimination in the test set (AUC = 0.877, 95% CI: 0.865–0.889) and good calibration. A web-based calculator was developed for individualized risk estimation. This study developed and internally validated a prediction model incorporating seven routine clinical indicators for assessing arterial stiffness risk in a community population. TyG-WHtR emerged as a key independent predictor. The model and its visual tools offer a practical means for early community-based screening of arterial stiffness. Clinical cohort registration number：ChiCTR2300068117 Registration date: 2023-02-07

KI fragen

Bookmark

View Full Paper