TY - GEN
T1 - Machine Learning Approach for Early Detection of Heart Disease
AU - Moolya, Santhosh
AU - Gopalakrishna Kini, N.
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - In recent years, Cardiovascular diseases (CVDs) have been a major health issue. Due to CVDs, around 17.9 million deaths are occurring annually. Therefore, early detection of the disease and treating it is very necessary. This paper addresses the need for efficient early diagnosis and intervention to reduce the burden of heart disease. The paper emphasizes the ability of machine learning in predicting heart disease development based on identifiable risk factors. The study shows the transformative impact of machine learning algorithms in heart disease prediction, which improves healthcare outcomes and reduces heart disease incidents. In this paper, the machine learning model is trained using several widely used and most popular classification algorithms. The models are evaluated using different evaluation metrics. Random Forest gave the best result with an accuracy of 91.80%, thus outperforming other models.
AB - In recent years, Cardiovascular diseases (CVDs) have been a major health issue. Due to CVDs, around 17.9 million deaths are occurring annually. Therefore, early detection of the disease and treating it is very necessary. This paper addresses the need for efficient early diagnosis and intervention to reduce the burden of heart disease. The paper emphasizes the ability of machine learning in predicting heart disease development based on identifiable risk factors. The study shows the transformative impact of machine learning algorithms in heart disease prediction, which improves healthcare outcomes and reduces heart disease incidents. In this paper, the machine learning model is trained using several widely used and most popular classification algorithms. The models are evaluated using different evaluation metrics. Random Forest gave the best result with an accuracy of 91.80%, thus outperforming other models.
UR - https://www.scopus.com/pages/publications/105012924444
UR - https://www.scopus.com/pages/publications/105012924444#tab=citedBy
U2 - 10.1007/978-981-96-3420-0_7
DO - 10.1007/978-981-96-3420-0_7
M3 - Conference contribution
AN - SCOPUS:105012924444
SN - 9789819634194
T3 - Smart Innovation, Systems and Technologies
SP - 75
EP - 85
BT - Human-Centric Smart Computing - Proceedings of ICHCSC 2024
A2 - Bhattacharyya, Siddhartha
A2 - Platos, Jan
A2 - Bhattacharyya, Siddhartha
A2 - Banerjee, Jyoti Sekhar
A2 - Köppen, Mario
A2 - Nayak, Somen
PB - Springer Science and Business Media Deutschland GmbH
T2 - 3rd International Conference on Human-Centric Smart Computing, ICHCSC 2024
Y2 - 25 July 2024 through 26 July 2024
ER -
