Key result
A novel approach using machine learning algorithms and ensemble techniques was proposed to classify patients into various conditions of arrhythmia to aid data-driven clinical decision-making.
Why the study?
Patients may receive differing clinical opinions for the same arrhythmia problem due to a lack of data-driven decision-making processes.
A novel machine learning ensemble approach using majority voting is proposed to assist in the classification of arrhythmia conditions.
May aid data-driven arrhythmia classification; leaves open prospective clinical validation.
Heart disease is the second leading cause of death in Singapore as reported by the Ministry of Health, Singapore. Research shows that stress and mental anxiety are the main causes of heart diseases. The risk of stroke is five times greater in people with atrial fibrillation, which makes the latter one of the leading cause of death in Singapore. This paper deals with classification of the patients into various conditions of arrhythmia. Each time a patient visits a hospital, the patient may get different opinions from different doctors about the same problem. There is no data-driven or evidential decision-making process in the sphere of health. Hence, a novel approach is proposed to help the doctors arrive at a proper conclusion about the patient's condition using various machine learning algorithms and ensemble techniques for classifying the patient condition.
No takes yet. Share an insight, caveat, or question.
Nguyen et al. (2019) studied Arrhythmia. Machine learning algorithms and ensemble techniques (Majority Voting) was evaluated on Classification of arrhythmia conditions. A novel approach using machine learning algorithms and ensemble techniques was proposed to classify patients into various conditions of arrhythmia to aid data-driven clinical decision-making.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: