A 3-tier information fusioned framework featuring explainable deep active optimized CRNet for accurate heart disease prediction

Sep 30, 2026

Uploaded by Fans

Heart disease prediction is addressed through a novel three-tier information fusioned deep learning framework designed for early, accurate risk assessment. The approach targets class imbalance, insufficient hyperparameter tuning, sparsely labeled data, and limited interpretability. Data are balanced using Oversampling Using the Propensity Score, model configuration is optimized via the grasshopper optimization algorithm, and active learning selects informative samples through uncertainty-based sampling. Performance is evaluated with 10-fold cross validation and one-way ANOVA, while explainable AI techniques provide local interpretability.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages39

Reading Time1 h 38 min

AccessFree to download

Abstract

Introduction

Methods

Model framework

Optimization and active learning

Evaluation and interpretability

Results

Conclusion

Highlights

Keywords

Javed et al. Journal of Translational Medicine (2026) 24:27 [https://doi.org/10.1186/s12967-025-07292-7](https://doi.org/10.1186/s12967-025-07292-7) Journal of Translational Medicine RESEARCH Open Access A 3-tier information fusioned framework featuring explainable deep active optimized CRNet for accurate heart disease prediction Aymin Javed 1†, Nadeem Javaid 1, Muhammad Shafiq2*†, Jin-Ghoo Choi2 and Nabil Alrajeh3* Abstract Background Heart disease remains a leading cause of global morbidity and mortality, emphasizing the need for early and accurate prediction. Traditional models, however, often struggle with high class imbalance, limited accuracy, inadequate hyperparameter tuning, reliance on sparsely labeled data, and poor interpretability. Methods To address these limitations, we introduce a novel 3-tier information fusioned framework integrating Oversampling Using the Propensity Score (OUPS), ConvRecurrentNet (CRNet), an optimized CRNet, and CRNet enhanced with Uncertainty-Based Sampling (UBS) . Initially, the highly imbalanced heart disease health indicator dataset is balanced using OUPS while preserving the underlying data distribution. In the first tier, we develop a new deep model; CRNet which combines gated units to capture temporal dependencies and convolutional layers for efficient spatial feature extraction. The second tier leverages the grasshopper optimization algorithm to optimize CRNet configuration and classification performance through hyperparameter tuning. At the third tier, we use an active learning based UBS to address the problem of sparse labeled data selecting the most informative samples for effective CRNet model learning. Model performance and generalizability are assessed through 10-fold cross validation and one-way analysis of variance. Interpretability is ensured using explainable artificial intelligence (AI) methods, local interpretable model-agnostic explanations and shapley additive explanations. Results Improvements are observed across all performance metrics: 3 .45%, 5 . 75%, and 8. 05% in accuracy, 3 .45%, 6. 90%, and 12. 64% in precision, 4 . 65%, 5 . 81%, and 4. 65% in recall, 4 . 65%, 6 . 98%, and 15. 12% in F1-score, 1. 04%, 2 . 08%, and 3. 13% in receiver operating characteristic-area under the curve, 8 . 00%, 9 . 33%, and 17. 33% in Matthews correlation coefficient, 12. 16%, 13. 51%, and 18. 92% in Cohen’s Kappa, and log loss reduction of 23 . 64%, 29 .45%, and 45. 82% across CRNet, optimized CRNet, and CRNet with UBS, respectively. †Aymin Javed and Muhammad Shafiq contributed equally to this work. *Correspondence: Muhammad Shafiq [shafiq@ynu.ac.kr](shafiq@ynu.ac.kr)[ ](shafiq@ynu.ac.kr)Nabil Alrajeh [nabil@ksu.edu.sa](nabil@ksu.edu.sa) Full list of author information is available at the end of the article © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creati](http://creati)[vecommons.org/l](vecommons.org/l)icenses/by-nc-nd/4.0/. Javed et al. Journal of Translational Medicine (2026) 24:27 Page 2 of 39 Conclusion The pr

FAQs

Why is early heart disease prediction challenging for traditional models?

Traditional models often struggle with class imbalance, limited accuracy, inadequate hyperparameter tuning, sparsely labeled data, and poor interpretability.

How does the proposed framework improve learning from imbalanced and sparse data?

It balances the dataset using OUPS in the first tier, optimizes CRNet configuration with the grasshopper optimization algorithm in the second tier, and uses uncertainty-based sampling with active learning in the third tier to select informative samples.

What evaluation and interpretability methods are used to validate the model?

Performance and generalizability are assessed using 10-fold cross validation and one-way analysis of variance, while interpretability is provided using local interpretable model-agnostic explanations and Shapley additive explanations (SHAP).

Sep 30, 2026

Uploaded by Fans