What is the clinical evidence from this study?

Study design: Cohort. Population: Cardiovascular disease (n=12692). Intervention: L1 regularized logistic regression (FLR-L1-LR) prediction model vs. Other machine learning models (SVM, RF, AdaBoost). Primary outcome: Prediction of incident cardiovascular disease (AUC) (AUC 0.817, 95% CI 0.801-0.832).

June 17, 2022Open Access

A Cardiovascular Disease Prediction Model Based on Routine Physical Examination Indicators Using Machine Learning Methods: A Cohort Study

XQXin QianShihezi University YLYu LiZhejiang Chinese Medical University XZXianghui ZhangLanzhou University

Key Result

A prediction model based on L1 regularized logistic regression demonstrated the best performance for predicting incident cardiovascular disease in the Xinjiang rural population, achieving an AUC of 0.817.

Study Design

Type

Cohort (n=12,692)

Multicenter

Yes

Structured PICO

Does a machine learning prediction model based on routine physical examination indicators accurately predict the incidence of cardiovascular disease in the Xinjiang rural population?

Population

12,692 adults aged 18 and older from the Uyghur and Kazak populations in rural Xinjiang, free of baseline cardiovascular disease, followed for a median of 4.94 years.

Exposure

Cardiovascular disease prediction model based on L1 regularized logistic regression with forward partial likelihood estimation (FLR-L1-LR) using routine physical examination indicators.

Comparator

Other machine learning prediction models (Lasso-AdaBoost, FLR-RF, FLR-SVM).

Outcome

Incidence of cardiovascular disease (CVD) at median 4.94 years follow-up.hard clinical

A machine learning model based on L1 regularized logistic regression using routine physical examination indicators effectively predicts cardiovascular disease risk in the rural Xinjiang population.

Main Result

Effect estimate: AUC 0.817 (95% CI 0.801-0.832)

Limitations

Limited number of variables included, which may restrict the prediction performance of machine learning algorithms
Lacked an independent external verification population to confirm prediction accuracy and robustness
Only baseline measurement data were used for modeling, without considering time effect and censored data
Low positive predictive value of the models in this population, which may lead to unnecessary interventions

Abstract

Background: Cardiovascular diseases (CVD) are currently the leading cause of premature death worldwide. Model-based early detection of high-risk populations for CVD is the key to CVD prevention. Thus, this research aimed to use machine learning (ML) algorithms to establish a CVD prediction model based on routine physical examination indicators suitable for the Xinjiang rural population. Method: The research cohort data collection was divided into two stages. The first stage involved a baseline survey from 2010 to 2012, with follow-up ending in December 2017. The second-phase baseline survey was conducted from September to December 2016, and follow-up ended in August 2021. A total of 12,692 participants (10,407 Uyghur and 2,285 Kazak) were included in the study. Screening predictors and establishing variable subsets were based on least absolute shrinkage and selection operator (Lasso) regression, logistic regression forward partial likelihood estimation (FLR), random forest (RF) feature importance, and RF variable importance. The selected subset of variables was compared with L1 regularized logistic regression (L1-LR), RF, support vector machine (SVM), and AdaBoost algorithm to establish a CVD prediction model suitable for this population. The incidence of CVD in this population was then analyzed. Result: After 4.94 years of follow-up, a total of 1,176 people were diagnosed with CVD (cumulative incidence: 9.27%). In the comparison of discrimination and calibration, the prediction performance of the subset of variables selected based on FLR was better than that of other models. Combining the results of discrimination, calibration, and clinical validity, the prediction model based on L1-LR had the best prediction performance. Age, systolic blood pressure, low-density lipoprotein-L/high-density lipoproteins-C, triglyceride blood glucose index, body mass index, and body adiposity index were all important predictors of the onset of CVD in the Xinjiang rural population. Conclusion: In the Xinjiang rural population, the prediction model based on L1-LR had the best prediction performance.

Ask AI

Helpful

Bookmark

View Full Paper