What is the clinical evidence from this study?

Study design: Cohort. Population: Atherosclerotic cardiovascular disease (ASCVD) (n=9609). Intervention: Artificial Neural Network (ANN) model vs. Pooled Cohort Equations (PCE) and China-PAR. Primary outcome: Prediction of ASCVD (AUC) (AUC 0.800, 95% CI 0.759-0.838, p=0.12).

What does this research mean for the field?

An artificial neural network (ANN) machine learning model outperforms conventional regression-based calculators, such as the Pooled Cohort Equations and China-PAR, in predicting atherosclerotic cardiovascular disease risk. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

July 24, 2023Open Access

Comparing the performance of machine learning and conventional models for predicting atherosclerotic cardiovascular disease in a general Chinese population

Key Result

The machine learning-based Artificial Neural Network model outperformed conventional calculators like PCE and China-PAR in predicting 5-year ASCVD risk, achieving an AUC of 0.800.

Study Design

Type

Cohort (n=9,609)

Structured PICO

Does a machine learning-based Artificial Neural Network model improve the prediction of incident ASCVD compared to conventional risk calculators (PCE and China-PAR) in a general Chinese population?

Population

9,609 adults (aged 35-85 years) with no history of cardiovascular disease from a prospective rural Chinese cohort (Northeast China Rural Cardiovascular Health Study), mean age 53.4, 53.7% female.

Intervention

Machine learning-based Artificial Neural Network (ANN) prediction model incorporating 30 selected features (including demographics, behavioral, psychological, ECG, and echocardiography parameters).

Comparator

Conventional regression ASCVD risk calculators: Pooled Cohort Equations (PCE) and Prediction for ASCVD Risk in China (China-PAR), including their recalibrated versions.

Outcome

Incident atherosclerotic cardiovascular disease (ASCVD), defined as stroke and coronary heart disease (including myocardial infarction, resuscitated cardiac arrest, definite angina, probable angina followed by revascularization, and CHD death) during follow-up.hard clinical

An artificial neural network model incorporating ECG and echocardiography features significantly improved ASCVD risk prediction and reclassification compared to traditional risk scores in a Chinese population.

Main Result

Effect estimate: AUC 0.800 (95% CI 0.759-0.838)

Absolute Event Rate: 0.8% vs 0.78%

p-value: p=0.12

Limitations

The ML algorithm cannot assess the independent effects of each variable on events and may be difficult to identify specific treatments to reduce individual risk.
Longer follow-up is needed considering the chronic, progressive course of ASCVD.
Excluded 84 variables with >10% missing data, and the imputation of missing data might bias the analysis.
External validation studies are required to demonstrate the accuracy of the model's predictions in diverse populations.
The models were established using the initial follow-up blood pressure and glucose, which may have changed during the follow-up period.

Abstract

BACKGROUND: Accurately predicting the risk of atherosclerotic cardiovascular disease (ASCVD) is crucial for implementing individualized prevention strategies and improving patient outcomes. Our objective is to develop machine learning (ML)-based models for predicting ASCVD risk in a prospective Chinese population and compare their performance with conventional regression models. METHODS: A hybrid dataset consisting of 551 features was used, including 98 demographic, behavioral, and psychological features, 444 Electrocardiograph (ECG) features, and 9 Echocardiography (Echo) features. Seven machine learning (ML)-based models were trained, validated, and tested after selecting the 30 most informative features. We compared the discrimination, calibration, net benefit, and net reclassification improvement (NRI) of the ML models with those of conventional ASCVD risk calculators, such as the Pooled Cohort Equations (PCE) and Prediction for ASCVD Risk in China (China-PAR). RESULTS: The study included 9,609 participants (mean age 53.4 ± 10.4 years, 53.7% female), and during a median follow-up of 4.7 years, 431 (4.5%) participants developed ASCVD. In the testing set, the final ML-based ANN model outperformed PCE, China-PAR, recalibrated PCE, and recalibrated China-PAR in predicting ASCVD. This was demonstrated by the model's higher area under the curve (AUC) of 0.800, compared to 0.777, 0.780, 0.779, and 0.779 for the other models, respectively. Additionally, the model had a lower Hosmer-Lemeshow χ2 of 9.1, compared to 37.3, 67.6, 126.6, and 18.6 for the other models. The net benefit at a threshold of 5% was also higher for the ML-based ANN model at 0.017, compared to 0.016, 0.013, 0.017, and 0.016 for the other models, respectively. Furthermore, the NRI was 0.089 for the ML-based ANN model, while it was 0.355, 0.098, and 0.088 for PCE, China-PAR, and recalibrated PCE, respectively. CONCLUSIONS: Compared to conventional regression ASCVD risk calculators, such as PCE and China-PAR, the ANN prediction model may help optimize identification of individuals at heightened cardiovascular risk by flexibly incorporating a wider range of potential predictors. The findings may help guide clinical decision-making and ultimately contribute to ASCVD prevention and management.

AI से पूछें

Bookmark

View Full Paper