Heart Risk Predictor

Heart disease is one of the leading causes of death globally. Predicting cardiovascular risk in the early stages can significantly reduce mortality rates and improve patient out-comes. This paper presents a machine learning-based solution for predicting heart disease risk using features such as age, cholesterol, blood pressure, smoking status, and diabetes. The system employs Linear Regression and Multivariable Polynomial Regression models trained on a dataset of 6,644 instances. A web interface built using Flask allows users to input health parameters and receive a risk score. The multivariable polynomial regression model achieved an accuracy of 75.8%. The paper also presents a comparative literature review of seven studies in heart disease prediction and discusses the implementation, sample circuit diagrams, code. and results.

In this project we successfully deployed a website which can be used to predict heart disease risk level by taking patient detail as input. We used some libraries provided by Python and html, CSS and bootstrap to implement this project. After the experiments. the algorithm of Multivariable Polynomial Regression gives us the best test accuracy, which is 75.8%. The reason why it outperforns others is that it is not limited to the property of the dataset. Regression techniques mostly differ based on the number of independent variables and the type of relationship between the independent and dependent Yarables.Though we get a good result of 75.8% accuracy, that is not enough because it cannot guarantee that no wrong dagnosis happens. To improve accuracy, we hope to require more dataset because 300 instances of dataset are not sufficient lo do an excellent job. In the future, to predict diseuse we want to try different diseases such as lung cancer by uung image detection. In this way, the dataser becomes complicated, and we can apply other algonthan to make accurate predictions

111 W. H. Organsation, “Cardovascular diseases (evds)” World Health Organication. 2021, avastable: hilps://www.who.iw/news-toom/fact- sheets/detail/cardiovascular-diseases-(evds), 21 M. Giudadbe, S. Wankhade, and S. Dongre, for heart disease based as support vers eced wie net nerwork.” International Journal ef Computer Applicarions, vol. 7, mx 3, pp. 1-5. 2010. (3) J. Patel, U. Tejal, and S. Patel, “Heart disease prediction using machine learning and data musing technique,” International Journal of Computer Applications, vol. 7, no. 1, pp. 1-3, 2015 14) L. Ah, C; Zhu. 2. Zhang el al. “An elicient deep leaning apprech to presmanta classlication in healbcare.” Junal of Healeare Engi. neerng. vol. 2020, 2020. |S J. Som, U. Ansari, D. Sharma, and S. Sont. “Predictive data rang lor medical diagnoss: An overview of hear deeme prediction.” later national Joarnal of Computer Applications, vol, 17, no. K, PD. 43-4%. 2011 [6) R. Detrano, A. Janoss, W. Steinbruna et al, “Interational sophication of « new probability algorthm for the diagnoss of coronary artery disease.” The Anserian Joarnal of Cardeleo, vol 66, no 5, pp: 304-310, 1949 17) K. Dry. 3. Obo, and A Mswax, “Podctve analyse of bear dis case tsung randors forest and kan classter? Daterethal Joveral af Anabeenag Rescarce and Technology, vol 7/mo. 3, pp.1-6. 201% IN A Hotanga. C. Bensan, C. S. Pallklus, are D. 8. Kell. What do we need to tuald explanable at Mysten for the medical domain” Never 19) J. Son. U. Ansari, D. Sharma, and S. Soni. “Predictive data mining for medical diagnosis: An overview of heart disease prediction.” Inter national Journal of Computer Applications, vol. 17, no. N. pp. 43-4%. 2011 (10) C. S. Dangure and S. S. Apte, “Improved mudy of heart disease predic-bon system using data mining classification techniques.” International Journal of Computer Applications, vol. 47, no. 10, pp. 44-48, 2012. |11) S. Oyar and A. Uhan, “Diagnoss of bear disease asing penetie algonths based trained rocurent luesy neural networks, neural networks, Procedur Computer Scarace. vol. 120 pp. 36X 593, 2017 C. Kumar, “Heart risk prediction uniae polynomual repaessica,” 2025. unpublished research. Kazale dataset used 1131 M. M. Rahman, M. A. Rahman, and M. I. Jony. “An interrated appeoach for prechetng beart disease asong data maning lechagues,” 1-15. 2021-

Call for Paper (Hub) Fast Paper Publication IJCT Indexing & Databases Submit Manuscript Call for Paper: Sep–Oct 2025 Call for Paper: Publish Research