HD-SMART: A Novel Machine Learning Framework for High-Accuracy Cardiovascular Risk Prediction Using Advanced Feature Engineering

Abstract

This work presents a novel concept known as Heart Disease Systematic Machine learning Analytical Risk prediction Technology (HD-SMART) that is considered a unique perspective in handling cardiac disease and the identification of sophisticated risk markers using superior computational technology. The work offers a rather peculiar approach to harnessing multiple machine learning algorithms in combination with feature selection methods that proved themselves highly accurate in cardiovascular risk estimation. The novelty is that these algorithms, namely, the Random Forest, Support Vector Machines (SVM), and Logistic Regression, are to be adopted in a systematic manner with supplementary feature engineering and with hyperparameter optimization, respectively. Based on the UCI Heart Disease dataset of 303 instances with 14 attributes, the new HD-SMART framework illustrated exceptional predictive capability, with the Random Forest at 97.57%, followed by SVM (95.23%) and Logistic Regression at 94.18%. The methodology achieved unique convergent optimization regarding feature selection with a minimum cost function of 0.0004 at iteration 50, while the Root Mean Square Error convergence was reached within the first four iterations with a value of 0.030. The innovative approach of data preprocessing and feature analysis in the framework pointed out critical patterns in cardiological parameters, such as in chest pain distribution (n ≈ 410 typical angina cases), bimodal blood pressure peaks (130–140 mmHg and 190–200 mmHg), as well as electrocardiogram variabilities (450 normal and 350 ST-T-wave abnormalities). The new proportion of 70–30 train-test split ratio was more optimal for model performance. This work introduces a completely new, computational diagnostic approach that not only outperforms but significantly surpasses conventional methods, and its robust statistical validity is maintained across a number of performance metrics. HD-SMART contributes to the advancement of cardiovascular diagnosis as a new, effective tool for early detection of heart disease for health practitioners based on big data analysis.

Received: 30 May 2025 | Revised: 11 November 2025 | Accepted: 8 January 2026

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

The Heart Disease data set that supports the findings of this study is openly available at https://doi.org/10.1007/s00521-021-06124-1 and at https://doi.org/10.1109/iciccs48265.2020.9121169, reference number [22, 24].

Author Contribution Statement

Gitanjali Gupta: Conceptualization, Methodology, Writing – original draft. Meena Malik: Conceptualization, Software, Validation, Visualization. Ramandeep Sandhu: Formal analysis, Investigation. Chander Prabha: Methodology, Resources, Data curation, Writing – review & editing, Supervision. Aimin Li: Investigation, Resources, Project administration. Saurav Mallik: Writing – review & editing, Visualization, Supervision.