Key result
Random Forest outperforms other machine learning models with 99% accuracy for stroke prediction.
Why the study?
Deaths due to heart strokes are increasing and detecting such conditions in humans is complex, requiring automated prediction methods.
Machine learning, specifically the Random Forest algorithm, can achieve very high accuracy (99%) in predicting heart conditions using ECG datasets.
May support ML development for ECG monitoring; leaves open prospective validation before clinical stroke prediction use.
Present day, Deaths due to heart strokes are increasing greatly day by day. Unfortunately, detecting such conditions in humans is a complex task. Handling such complex tasks can be done by using data sets. Heart strokes occurrence prediction can be done only by automation because we need to keep monitoring the heart rate. MITBIH arrhythmia is one of the datasets which help us, so it is used in this paper. Automation for the mentioned task can be obtained by using various data mining techniques. Some of the techniques used in this paper are decision trees, naïve bayes, ANN algorithm & Random Forest algorithm. Therefore, the motto of this paper is to compare the above-mentioned algorithms & find out which is more accurate in accomplishing the task. At the end, after all the assessments we can say that the algorithm Random Forest has got 99% of accuracy which is recorded as highest among all the algorihms. But in the case of ECG images ANN algorithm has achieved an accuracy of 94%.
No takes yet. Share an insight, caveat, or question.
Shareefunnisa et al. (2022) studied Heart stroke / Arrhythmia. Random Forest algorithm vs. Decision trees, Naïve Bayes, and ANN algorithms was evaluated on Prediction accuracy. The Random Forest algorithm achieved the highest accuracy of 99% for heart stroke prediction compared to other evaluated machine learning models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: