TY - GEN
T1 - Machine Learning Models for Early Detection of Cardiac Arrest Risk Factors
AU - Bindewari, Shantanu
AU - Sharma, Kanhaiya
AU - Gaddam, Sesha Saisrikar
AU - Verma, Ananta
AU - Parashar, Deepak
AU - Arse, Mahesh
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - An interruption in the heart's electrical rhythm can result in cardiac arrest, which is potentially fatal. Effective management depends on accurately identifying high-risk patients, providing quick clinical care, and performing successful resuscitation. (ML) Researchers have used systems that are excellent at analyzing complex data to forecast the risk of cardiac arrest. Using real-time datasets from Kaggle, this study assessed four Machine Learning (ML) algorithms: Random Forest (RF), K-Nearest Neighbours (KNN), and Extreme Gradient Boost (XGBoost). The testing results showed that the RF-based ML technique displayed greater accuracy than existing algorithms. This demonstrates how can forecast the danger of cardiac arrest. ML algorithms can find patterns and risk factors that a human clinician might not be able to see. Healthcare professionals can build individualized preventive measures and interventions by utilizing these algorithms to acquire insightful information about a person's propensity for cardiac arrest.
AB - An interruption in the heart's electrical rhythm can result in cardiac arrest, which is potentially fatal. Effective management depends on accurately identifying high-risk patients, providing quick clinical care, and performing successful resuscitation. (ML) Researchers have used systems that are excellent at analyzing complex data to forecast the risk of cardiac arrest. Using real-time datasets from Kaggle, this study assessed four Machine Learning (ML) algorithms: Random Forest (RF), K-Nearest Neighbours (KNN), and Extreme Gradient Boost (XGBoost). The testing results showed that the RF-based ML technique displayed greater accuracy than existing algorithms. This demonstrates how can forecast the danger of cardiac arrest. ML algorithms can find patterns and risk factors that a human clinician might not be able to see. Healthcare professionals can build individualized preventive measures and interventions by utilizing these algorithms to acquire insightful information about a person's propensity for cardiac arrest.
UR - https://www.scopus.com/pages/publications/105008418200
UR - https://www.scopus.com/pages/publications/105008418200#tab=citedBy
U2 - 10.1109/IC3ECSBHI63591.2025.10990532
DO - 10.1109/IC3ECSBHI63591.2025.10990532
M3 - Conference contribution
AN - SCOPUS:105008418200
T3 - 2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics, IC3ECSBHI 2025
SP - 65
EP - 69
BT - 2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics, IC3ECSBHI 2025
A2 - Ansari, M. A.
A2 - Pal, Kirti
A2 - Kumar, Sushil
A2 - Baghel, Anurag Singh
A2 - Ashraf, Moh'd Tashfeen
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics, IC3ECSBHI 2025
Y2 - 16 January 2025 through 18 January 2025
ER -
