Related Experiment Videos
Medical diagnosis using adaptive perceptive particle swarm optimization and its hardware realization using field
Shubhajit Roy Chowdhury1, Dipankar Chakrabarti, Saha Hiranmay
1IC Design and Fabrication Centre, Department of Electronics and Telecommunication Engineering, Jadavpur University, Kolkata 700032, India. shubhajit@juiccentre.res.in
Journal of Medical Systems
|January 8, 2010
Summary
This study developed a low-cost, low-power Field Programmable Gate Array (FPGA) diagnostic system for early detection of critical health conditions. The system achieved 97.5% accuracy in diagnosing renal criticality, aiding rural healthcare access.
Area of Science:
- Biomedical Engineering
- Medical Diagnostics
- Health Informatics
Background:
- Healthcare access in rural areas of developing countries is limited by physician and power scarcity.
- Early detection of critical conditions, like renal criticality, is crucial for timely intervention and improved patient outcomes.
- Existing diagnostic methods may not be suitable for resource-limited settings due to cost, power, or complexity.
Purpose of the Study:
- To develop a novel, low-cost, low-power, high-speed Field Programmable Gate Array (FPGA) based diagnostic system.
- To enable early detection of approaching critical patient conditions, particularly in rural areas lacking physician availability.
- To optimize diagnostic accuracy using a novel adaptive perceptive particle swarm optimization algorithm for weighting pathophysiological parameters.
Main Methods:
- Development of an FPGA-based smart diagnostic system.
- Implementation of adaptive perceptive particle swarm optimization to determine optimal weights for multiple pathophysiological parameters.
- Application of the system for early detection of renal criticality using parameters like BMI, glucose, urea, creatinine, and blood pressure.
- Validation of diagnostic results using the standard Cockford Gault Equation.
- Utilizing Bayesian analysis for accuracy assessment.
Main Results:
- The FPGA-based system demonstrated high speed, low cost, and low power consumption.
- The adaptive perceptive particle swarm optimization effectively determined optimal weights for diagnostic parameters.
- The system achieved up to 97.5% accuracy in diagnosing renal criticality in a study population of 80 patients.
- Validation confirmed the system's ability to accurately detect approaching critical conditions.
Conclusions:
- The developed FPGA-based diagnostic system is a viable solution for early detection of critical health conditions in resource-limited rural settings.
- The novel optimization algorithm enhances diagnostic accuracy by appropriately weighting key pathophysiological parameters.
- This technology has the potential to significantly improve healthcare accessibility and patient outcomes in underserved regions.