Key result
Hybrid CNN-BiLSTM boosts heart disease classification accuracy to ~99%, outperforming CNN-LSTM.
Why the study?
Existing machine learning and deep learning models for heart disease detection struggle to simultaneously capture sequential dependencies and spatial feature interactions, and applying hybrid CNN-BiLSTM models to tabular heart disease datasets remained unexplored.
Does a hybrid CNN-BiLSTM deep learning model improve classification accuracy in tabular heart disease and heart failure datasets?
Does a hybrid CNN-BiLSTM deep learning model improve classification accuracy in tabular heart disease and heart failure datasets?
A novel hybrid CNN-BiLSTM deep learning architecture achieved high classification accuracy on benchmark tabular heart disease and heart failure datasets.
Heart disease remains a main cause of death worldwide, showing the necessity for accurate and timely automated diagnostic systems. Hence, precise and early detection is necessary and is done by some existing machine learning (ML) and deep learning (DL) algorithms. Existing ML and DL models, like convolutional neural network (CNN), long short-term memory (LSTM), CNN-LSTM, and some hybrid approaches, shows good performance. However, they struggle to capture sequential dependencies and spatial feature interactions simultaneously. Further more, hybrid CNN–BiLSTM models to tabular heart disease datasets remains unexplored. To address this gap, this paper, proposes a convolutional neural network–bidirectional long short-term memory (CNN-BiLSTM) hybrid model. This proposed model employs bidirectional processing to improve the temporal features extraction. The proposed hybrid model accurately stores sequential data of the past and the future to do predictions. The experimental validation is done with two different heart disease datasets. The implementation includes learning rate scheduling and hyperparameter adjustment for optimisation. Experimental results on two benchmark datasets demonstrate the proposed model effectiveness. The proposed model got 98.54% accuracy with heart disease dataset and 81.94% accuracy with heart failure clinical dataset, done using 5-fold cross-validation.
No takes yet. Share an insight, caveat, or question.
Azhar et al. (2026) studied Heart disease and heart failure (n=1,324). Hybrid CNN-BiLSTM deep learning model vs. CNN, LSTM, and CNN-LSTM baseline models was evaluated on 5-fold cross-validation classification accuracy on the Heart Disease Dataset (Dataset 2) (p=0.009950). The hybrid CNN-BiLSTM model achieved 98.54% classification accuracy on the heart disease dataset, outperforming CNN-LSTM (91.71%, p=0.00995) and achieving 81.94% accuracy on the heart failure dataset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: