Enhanced Heart Disease Diagnosis and Management: A Multi-Phase Framework Leveraging Deep Learning and Personalized Nutrition

Strategic Insights -

A novel research study has made significant breakthroughs in heart disease diagnosis and management by proposing a multi-tiered data acquisition model that utilizes deep learning methods. The study, conducted by researchers at Maharshi Dayanand University, aimed to develop an accurate diagnosis system for heart disease using a data-driven forecasting framework. The researchers employed a multi-phase framework that includes data acquisition, preprocessing, feature extraction, and deep learning to identify the best features for heart disease diagnosis. The proposed model, called CILAD-Net, integrates various deep learning techniques, including CNN, Inception Net, LSTM, and Angle DetectNet, to achieve higher accuracy in detecting heart disease. The study's outcomes demonstrate the effectiveness of the proposed model in achieving higher accuracy compared to existing models.

Key Takeaways:

  • The study proposes a multi-tiered data acquisition model that utilizes deep learning methods to diagnose heart disease.
  • The model includes four phases: data acquisition, data preprocessing, feature extraction, and deep learning for heart disease diagnosis.
  • The proposed model, CILAD-Net, integrates various deep learning techniques to achieve higher accuracy in detecting heart disease.
  • The study's outcomes demonstrate the effectiveness of CILAD-Net in achieving higher accuracy compared to existing models, including DenseNet-201, ANN, KNN, and CL-Net.
  • The study also proposes a personalized nutrition recommendation system based on deep reinforcement learning for improving treatment individualization.
  • The developed model's experimental outcomes are validated with other prevailing models in terms of accuracy, recall, hamming loss, and so on.
  • The study's findings indicate that the proposed model can achieve higher accuracy of 0.998 for CILAD-Net, which is significantly better than DenseNet-201 (0.988), ANN (0.987), KNN (0.977), and CL-Net (0.98).
  • Rajender Singh Chhillar, the lead researcher, and his team at Maharshi Dayanand University developed the model and proposed the multi-phase framework for heart disease diagnosis and management.

Statistics:

  • The proposed model, CILAD-Net, achieved an accuracy of 0.998, which is significantly better than DenseNet-201 (0.988), ANN (0.987), KNN (0.977), and CL-Net (0.98).
  • The study's findings suggest that the proposed model can achieve higher accuracy compared to existing models.
  • The study's experimental outcomes are validated with other prevailing models in terms of accuracy, recall, hamming loss, and so on.
  • The developed model's outcomes are promising for real-world applications in heart disease diagnosis and management.

Sources:

  • NewsRx. Study Findings from Maharshi Dayanand University Broaden Understanding of Heart Disease (Enhanced heart disease diagnosis and management: A multi-phase framework leveraging deep learning and personalized nutrition). Health & Medicine Week. October 31, 2025; p 174.
  • Public Library Science. PLOS One. Enhanced heart disease diagnosis and management: A multi-phase framework leveraging deep learning and personalized nutrition. 2025;20(10).
  • Maharshi Dayanand University. Department of Computer Science & Applications. Contact: Rajender Singh Chhillar, Ritika Ritika, Sandeep Dalal, Surjeet Dalal, Iyyappan Moorthi, Mitiku Dubale, and Arshad Hashmi.