January 1, 2022Open Access

Risk prediction of cardiovascular disease using machine learning classifiers

Q: What is the clinical evidence from this study?

Study design: Other. Population: Cardiovascular disease. Intervention: Multi-layer perceptron (MLP) machine learning model vs. K-nearest neighbour (K-NN) model. Primary outcome: CVD detection accuracy.

Q: What does this research mean for the field?

A multi-layer perceptron machine learning model achieves 82.47% accuracy and an AUC of 86.41% for cardiovascular disease detection, outperforming a K-nearest neighbour model. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Key Result

A multi-layer perceptron machine learning model achieved 82.47% accuracy and an AUC of 86.41% for cardiovascular disease detection, outperforming a K-nearest neighbour model.

Structured PICO

Does a multi-layer perceptron (MLP) model improve cardiovascular disease detection accuracy compared to K-nearest neighbour (K-NN)?

Population

Data from publicly available University of California Irvine (UCI) repository for cardiovascular disease detection

Intervention

Multi-layer perceptron (MLP) machine learning model

Comparator

K-nearest neighbour (K-NN) machine learning model

Outcome

Accuracy and area-under-the-curve (AUC) for cardiovascular disease detection

A multi-layer perceptron machine learning model demonstrated good accuracy (82.47%) for automatic detection of cardiovascular disease using a standard public dataset.

Limitations

Performance of the proposed model needs to be assessed via other standard data sets

Abstract

Abstract Cardiovascular disease (CVD) makes our heart and blood vessels dysfunctional and often leads to death or physical paralysis. Therefore, early and automatic detection of CVD can save many human lives. Multiple investigations have been carried out to achieve this objective, but there is still room for improvement in performance and reliability. This study is yet another step in this direction. In this study, two reliable machine learning techniques, multi-layer perceptron (MLP), and K -nearest neighbour (K-NN) have been employed for CVD detection using publicly available University of California Irvine repository data. The performances of the models are optimally increased by removing outliers and attributes having null values. Experimental-based results demonstrate that a higher accuracy in detection of 82.47% and an area-under-the-curve value of 86.41% are obtained using the MLP model, unlike the K-NN model. Therefore, the proposed MLP model was recommended for automatic CVD detection. The proposed methodology can also be employed in detecting other diseases. In addition, the performance of the proposed model can be assessed via other standard data sets.

Demander à l'IA

Bookmark

View Full Paper