Related Experiment Video
Updated: Jul 26, 2026
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Early prediction of CKD from time series data using adaptive PSO optimized echo state networks
Thangadurai Anbazhagan1, Balamurugan Rangaswamy2
1Department of Electrical and Electronics Engineering, K.S.Rangasamy College of Technology, Tiruchengode, 637215, Tamil Nadu, India. thangaduraieie@gmail.com.
Insights
Early detection of Chronic Kidney Disease (CKD) is crucial. A new Adaptive Particle Swarm Optimization (APSO)-optimized Echo State Network (ESN) model achieves 99.6% classification accuracy for early CKD detection.
Area of Science:
- Medical Informatics
- Computational Biology
- Machine Learning
Background:
- Chronic Kidney Disease (CKD) presents a significant healthcare challenge due to late detection, leading to increased medical costs and reduced treatment efficacy.
- Current methods for CKD detection often fail to identify symptoms in the early stages, necessitating advanced predictive models.
Purpose of the Study:
- To develop a novel predictive model for early detection of Chronic Kidney Disease (CKD) symptoms.
- To enhance the performance and stability of Echo State Networks (ESNs) for analyzing complex temporal medical data.
Main Methods:
- An Adaptive Particle Swarm Optimization (APSO) algorithm was employed to dynamically optimize ESN hyperparameters, including spectral radius, input scaling, and sparsity.
- Random Matrix Theory (RMT) was integrated into APSO to regulate the spectral radius, improving the ESN's ability to handle long-term dependencies and maintain training stability.
- The developed APSO-optimized ESN (APSO+ESN) was trained and validated using the Medical Information Mart for Intensive Care-III (MIMIC-III) dataset.
Main Results:
- The APSO+ESN model demonstrated superior performance compared to conventional ESN and other recognized models in CKD detection.
- The proposed model achieved a classification accuracy (CA) of 99.6%.
- APSO+ESN improved recall by 2% and precision by 3% over the next best-performing model.
Conclusions:
- The novel APSO+ESN model effectively detects early-stage Chronic Kidney Disease (CKD) with high accuracy.
- Dynamic hyperparameter optimization using APSO and RMT significantly enhances ESN performance for complex temporal sequence analysis in healthcare.
- This approach offers a promising solution for early CKD detection, potentially improving patient outcomes and reducing healthcare burdens.
Abstract:
Chronic Kidney Disease (CKD) is a significant problem in today's healthcare since it is challenging to detect until it has improved significantly, which increases medical expenses. If CKD was detected early, the patient might qualify for more effective treatment and prevent the disease from spreading further. Presently, existing methods that effectively detect CKD cannot detect symptoms early on. This problem motivates researchers to work on a predictive model that successfully detects disease symptoms in the early stages. This study introduces a novel Adaptive Particle Swarm Optimization (APSO)-optimized Echo State Network (ESN) model designed to overcome key limitations of existing methods. ESNs, while effective in processing temporal sequences, are highly sensitive to hyperparameter settings such as spectral radius, input scaling, and sparsity, which directly impact stability, memory retention, and predictive Classification Accuracy (CA). To address this, APSO optimizes these hyperparameters dynamically, ensuring a balanced trade-off between stability and computational efficiency. Moreover, Random Matrix Theory (RMT) is integrated into APSO to regulate the spectral radius, enhancing the ESN's capability to handle long-term dependencies while maintaining stability in training. This investigation exploited the Medical Information Mart for Intensive Care-III (MIMIC-III) dataset to train the model they developed. The proposed method employs this data collection to analyze the highly complex temporal sequences signifying CKD is present. The hyperparameters of the ESN, such as the range of the spectral region and the input data sizing, can be optimized in real-time with APSO by applying Random Matrix Theory (RMT). Compared with different recognized models, such as conventional ESN and standard M, the recommended APSO + ESN proved to have higher CA in medical investigations. The APSO + ESN improved the subsequent highest-performing model by 2% in recall and 3% in precision and attained a CA of 99.6%.
