Sunil Bhutada, K Usharani, K Mahesh*, L Manish Reddy, N Sravan Kumar and D Vaishnavi

Sreenidhi Institute of Science and Technology, Yamnampet, Ghatkesar, Hyderabad, Telangana, India

*Corresponding Author: K Mahesh, Sreenidhi Institute of Science and Technology, Yamnampet, Ghatkesar, Hyderabad, Telangana, India..

Received: May 17, 2024; Published: June 04, 2024

Abstract

The importance of early diagnosis is highlighted by heart disease, a chronic illness that affects millions of people worldwide. To isolate and improve upon the most important characteristics, a novel feature engineering approach is presented that makes use of Principal Component analysis. The study’s goal is to develop a user interface and use machine learning (ML) to quickly anticipate the health condition of heart disease and start the necessary steps. A Stacking Classifier, an ensemble approach, is used in the work to integrate the predictions of three different models: Random Forest (RF), Multilayer Perceptron (MLP), and Light GBM. By combining the best features of many models in a complementary fashion, this method achieves a remarkable 100% accuracy rate in its final forecast, making it both resilient and precise. Model construction made use of the characteristics chosen according to Principal Component Heart Failure (PCHF), and front-end deployment of the Stacking Classifier was trained, have improved the accessibility and usefulness of our machine learning-based heart disease prediction system by integrating the Flask framework with user authentication. The patient will enter the details at a user interface and determine whether the user has heart disease or not. In this study comparative analysis of classification algorithms along with ROC curve of the different classification techniques. This offers a safe and effective platform for user testing.

Keywords: ML; Cardiac; Arrest; Cross-Validations; Feature; Engineering; Algorithms; Patient; Prevalence; Accuracy

References

1. M Gjoreski., et al. “Chronic heart failure detection from heart sounds using a stack of machine-learning classifiers”. in Proc. Int. Conf. Intell. Environments (IE), Aug. (2017): 14-19.
2. G Savarese and L H Lund. “Global public health burden of heart failure”. Cardiac Failure Review 1(2017): 7.
3. EJ Benjamin., et al. “Heart disease and stroke statistics—2019 update: A report from the American Heart Association”. Circulation 10 (2019): e56-e528.
4. A Qayyum., et al. “Secure and robust machine learning for healthcare: A survey”. IEEE Rev. Biomed. Eng. 14 (2021): 156-180.
5. C Trevisan., et al. “Gender differences in brain-heart connection”. Brain and Heart Dynamics (2020): 937-951.
6. DC Yadav and S Pal. “Prediction of heart disease using feature selection and random forest ensemble method”. International Journal for Pharmaceutical Research Scholars4 (2020): 56-66.
7. D Tomar and S Agarwal. “A survey on data mining approaches for healthcare”. International Journal of Bio-Science and Bio-Technology 5(2013): 241-266.
8. S Ekiz and P Erdogmus. “Comparative study of heart disease classification”. in Proc. Electr. Electron., Comput. Sci., Biomed. Eng. Meeting (EBBT) (2017): 1-4.
9. BA Tama., et al. “Improving an intelligent detection system for coronary heart disease using a two-tier classifier ensemble”. BioMed Research International (2020): 1-10.
10. FS Alotaibi. “Implementation of a machine learning model to predict heart failure disease”. International Journal of Advanced Computer Science and Applications 6 (2019): 1-8.
11. V Ramalingam., et al. “Heart disease prediction using machine learning techniques: A survey”. International Journal of Engineering and Technology 2 (2018): 684-687.
12. D K Plati., et al. “A machine learning approach for chronic heart failure diagnosis”. Diagnostics10 (2021): 1863.
13. A Saboor., et al. “A method for improving prediction of human heart disease using machine learning algorithms”. Mobile Information Systems (2022): 1-9.
14. R Katarya and S K Meena. “Machine learning techniques for heart disease prediction: A comparative study and analysis”. Health and Technology1 (2021): 87-97.
15. R Pahuja and A Kumar. “Sound-spectrogram based automatic bird species recognition using MLP classifier”. Applied Acoustics 180 (2021): Art. no. 108077.
16. B Olimov., et al. “Right initialization based-rectified linear unit activation function to improve the performance of a convolutional neural network model”. Concurrency and Computation: Practice and Experience 22 (2021): e6143.
17. K Shah., et al. “A comparative analysis of logistic regression, random forest and KNN models for the text classification”. Augmented Human Research1 (2020): 1-16.
18. V Kakulapati., et al. “Multimodal detection of COVID-19 Fake News and Public Behavior Analysis- Machine Learning Perspective" is in the book "Springer Innovation in Communication and Computing series "Intelligent Healthcare". (2021).
19. V Kakulapati., et al. “A Novel Multimodal Risk Disease Prediction of Covid-19 by Using Hierarchical LSTM Methods", "Taylor and Francis book" Data Science and Data Analytics: Opportunities and Challenges".
20. A Raza., et al. “Ensemble learning-based feature engineering to analyze maternal health during pregnancy and health risk prediction”. PLoS ONE11 (2022): Art. no. e0276525.

Citation

Citation: K Mahesh., et al. “Refined Approach for Predicting Heart Disease Through Machine Learning and Feature Engineering Techniques".Acta Scientific Computer Sciences 6.6 (2024): 11-16.

Copyright

Copyright: © 2024 K Mahesh., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.