• JAGADESH M
• DHARSHANA R
• DARUNYA S
• AHIESH SUJO I S
• DHILIP R M

Machine learning is frequently used to teach machines to learn and predict, When given with new data,. A person's risk of developing heart illness may be predicted in a number of ways thanks to advancements in machine learning. One of the illnesses that affects individuals the most in the entire globe is heart disease. Heart disease is a risk that can be increased by a number of causes. By merging logistic regression analysis with neural networks, a novel method of heart disease prediction is presented. In order to determine the key risk factors for disease prediction, logistic regression is first performed. It creates substantial risk factors that might be utilized to anticipate cardiac disease based on statistical p-value. Identifying and removing risk factors with little or no impact is done. The neural network receives the important emerging elements. Additionally, a neural network trained on the risk factors determined from logistic regression is employed to identify whether or not a person has heart disease. As a result, heart disease is predicted using a mix of logistic regression and neural networks.

Logistic regression model, neural networks, prediction, heart disease

"HEAT FAILURE PREDICTION WITH NEURAL NETWORK USING DESIGN THINKING FRAMEWORK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 1, page no.e593-e596, January-2023, Available :http://www.jetir.org/papers/JETIR2301480.pdf

"HEAT FAILURE PREDICTION WITH NEURAL NETWORK USING DESIGN THINKING FRAMEWORK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 1, page no. ppe593-e596, January-2023, Available at : http://www.jetir.org/papers/JETIR2301480.pdf