Does the HistGradientBoosting classifier accurately predict cardiovascular disease in a dataset of 1000 subjects?
A machine learning approach using the HistGradientBoosting classifier achieved 99% accuracy in predicting cardiovascular disease, highlighting its potential for automated diagnostic systems.
Cardiovascular disease has been more common throughout the past several decades. Cardiovascular disease detection methods use machine learning algorithms to assess data and provide accurate cardiac diagnosis. An accurate and comprehensive assessment of cardiovascular risk is essential to improve cardiovascular protection and reduce the frequency and severity of heart attacks and strokes. This paper proposes a machine learning-based autonomous strategy for the diagnosis of cardiovascular disease. Some preprocessing methods were applied to improve the results and accuracy. Finally, lazy prediction was used to find the best model by applying a neural network and two ensemble models. The best accuracy of 99% was obtained with the HistGradientBoosting (ensemble) classifier, which obtained respectable results with a higher accuracy rate. This model can enhance the ability to predict cardiovascular disease with better accuracy.
Tasnim et al. (Sat,) studied this question.