EARLY PREDICTION OF HEART DISEASE: IN-DEPTH STUDY

A comparison between Support Vector Machine (SVM) and Artificial Neural Networks (ANN) in heart disease prediction reveals that each method has distinct advantages and is suited to different scenarios. SVM is consistently recognized as a dependable and effective model, often surpassing traditional approaches like Logistic Regression and Decision Trees in numerous studies, with some identifying it as the most reliable for heart disease prediction. On the other hand, ANN models excel in accuracy-related metrics such as AUC and recall, with recorded values around 0.808 and 0.81, respectively. Despite these strengths, ANN faces challenges related to data complexity and overfitting. In summary, SVM is noted for its robustness and reliability, whereas ANN shows considerable promise in improving predictive accuracy, particularly in dealing with data complexity and imbalance. The selection between these models may hinge on the specific characteristics of the dataset and the clinical context in which they are applied.  

[1]  M. Heron, “Deaths: leading causes for 2008,” National VitalStatistics Reports: From the Centers for Disease Control and Prevention, National Center for Health Statistics, National Vital Statistics System, vol. 60, no. 6, pp. 1–94, 2012. [2]    M. Durairaj and N. Ramasamy, “A comparison of the perceptive approaches for preprocessing the data set for predicting fertility success rate,” International Journal of Control Theory and Applications, vol. 9, no. 27, pp. 255–260, 2016. [3]   P. A. Heidenreich, J. G. Trogdon, O. A. Khavjou et al., “Fore casting the future of cardiovascular disease in the UnitedStates,” Circulation, vol. 123, no. 8, pp. 933–944, 2011. [4]  G. Savarese and L. H. Lund, “Global public health burden ofheart failure,” Cardiac Failure Review, vol. 3, no. 1, pp. 7–11,2017. [ 5 ] March 2022, https : / / www . who . int / health - topics /cardiovascular-diseases =tab_1. [6] C. Beyene and P. Kamat, “Survey on prediction and analysis the occurrence of heart disease using data mining techniques,” International Journal of Pure and Applied Mathematics, vol. 118, no. 8, pp. 165–174, 2018. [7] T. Bala Krishna,Vimala Nunavath,P.S.N.M. Vinay,Nagudu Siddhardha,P Manohar “Early Heart Disease Prediction Using Support Vector Machine “ 01 Jan 2023(Springer International Publishing) [8]    Pooja Dehankar,Susanta Das “Detection of Heart Disease Using ANN”      21 Jun 2024 1 - Advances in medical diagnosis, treatment. [9] Windeatt,T (2008). Ensemble MLP Classifier Design.In: Jain, L.C., Sato-Ilic, M, Virvou,M. Tsihrintzis, G.A., Balas, V.E., Abeynayake, C. (eds) Computational Intelligence Paradigms. Studies in Computational Intelligence, vol 137. Springer, Berlin, Heidelberg. [10]Rehan Ahmed', Maria Bibi 3, Sibtain Syed "Improving Heart Disease Prediction Accuracy Using a Hybrid Machine Learning Approach: A Comparative study of SVM and KNN Algorithm" IJCIM June 2023