Key result
Reservoir computing with fractional-order modeling outperforms LSTM in cardiovascular forecasting accuracy and speed.
Why the study?
Classical integer-order systems fail to represent the memory effects and long-term disease dependence in the coupled progression of diabetes and cardiovascular complications.
A novel discrete fractional-order mathematical model integrated with Reservoir Computing offers an efficient framework for forecasting the coupled progression of diabetes and cardiovascular complications.
May aid efficient forecasting of diabetes-CV comorbidity; leaves open prospective clinical validation before practice impact.
This study presents a novel discrete fractional-order mathematical framework for modeling and forecasting the coupled progression of diabetes and cardiovascular complications, with emphasis on population dynamics in Saudi Arabia. Using the discrete Caputo fractional operator, the model captures memory effects and long-term disease dependence not represented by classical integer-order systems. The population is divided into five interacting compartments: susceptible, exposed, diabetic without major complications, diabetic with severe complications, and cardiovascular-affected individuals. A rigorous qualitative analysis establishes equilibrium points and examines their local stability under fractional discrete dynamics. Stability regions are identified in parameter space, clarifying the mechanisms governing disease persistence and progression. A feedback-based control strategy is proposed to restore stability of the disease-free equilibrium when destabilization occurs. To enhance predictive performance, a Reservoir Computing framework is integrated and compared with Long Short-Term Memory networks, demonstrating improved accuracy and lower computational cost. Numerical simulations validate theoretical findings and highlight key epidemiological influences. Future work will extend the model by incorporating optimal control strategies aimed at minimizing infections through targeted interventions such as vaccination, improved hygiene, and environmental sanitation. The integration of fractional-order dynamics with control theory offers valuable insights for public health decision-making and epidemic mitigation.
No takes yet. Share an insight, caveat, or question.
Elsonbaty et al. (2026) studied Diabetes and cardiovascular complications. Discrete fractional-order model with Reservoir Computing vs. Long Short-Term Memory (LSTM) networks was evaluated. A discrete fractional-order model integrated with Reservoir Computing effectively captured diabetes and cardiovascular dynamics, demonstrating improved forecasting accuracy and lower computational cost compared to LSTM networks.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: