Cardiotech Next AI Healthcare: Enhanced Arrhythmia Cardio Vascular Disease Prediction using Hyper Capsule LSTM Gated Recurrent Neural Network with Optimal Swarm Intelligence Technique

The rising incidence of cardiovascular diseases,
especially arrhythmias, demands advanced predictive models
for early diagnosis and treatment. This study introduces the
Cardiotech Next AI model, integrating Hyper Capsule Long
Short-Term Memory (LSTM) and Gated Recurrent Neural
Networks (GRNN) with an Optimal Swarm Intelligence
Technique (OSIT) to enhance prediction accuracy. The process
begins with C-score normalization to standardize cardiac data,
followed by the Cardiac Disease Impact Behavioural Scaling
Rate, which evaluates behavioral risk factors. OSIT-based
feature selection optimizes predictor identification, improving
model robustness and generalization. The final classification
employs a Hyper Capsule LSTM-GRNN architecture to assign
multiclass cardiovascular risk levels, leveraging temporal
dependencies in cardiac data. The proposed system not only
improves prediction performance but also enhances
understanding of arrhythmia dynamics. Results demonstrate
superior metrics precision (0.98), accuracy (0.81), recall (0.83),
and F1-score (0.90), outperforming conventional models. This
highlights the model's potential in advancing cardiovascular
risk classification and supporting proactive healthcare
management.