TY - JOUR
T1 - Prediction of Diabetic Neuropathy Severity in Diabetes Patients Based on Electromyography (EMG) Signals Using Hybrid Stacking Learning Model - Particle Swarm Optimization
AU - Purnawan, I. Ketut Adi
AU - Wibawa, Adhi Dharma
AU - Anggraeni, Wiwik
AU - Purnomo, Mauridhi Hery
N1 - Publisher Copyright:
© (2024), (Intelligent Network and Systems Society). All Rights Reserved.
PY - 2024
Y1 - 2024
N2 - Individuals with diabetes often experience nerve damage complications due to diabetic neuropathy, with up to 50% of cases being asymptomatic, increasing injury risk. Reducing the risk of long-term complications related to diabetes requires the ability to predict and track the severity of diabetic neuropathy in patients. Diabetes care strategies and management by predicting the severity of diabetic neuropathy can offer insight into disease progression and assist healthcare professionals in managing high-risk patients. The study introduces a novel approach by predicting diabetic neuropathy severity using electromyography signals, moving beyond traditional medical data. It also innovates by employing a hybrid method of Ensemble models with Particle Swarm Optimization for parameter optimization. The study predicts diabetic neuropathy severity by selecting the top 10, 20, and 30 features from 90 extracted electromyography signal features using a correlation matrix, principal component analysis, and recursive feature elimination. Various machine learning models, as well as two ensemble models, boosting and stacking, were employed for prediction. Optimal parameters for each learner were determined using Particle Swarm Optimizer to enhance prediction performance. Among 144 experiment scenarios, the hybrid stacking-particle swarm optimizer model outperformed others, showing 14.29% higher accuracy, 13.93% higher F-1 score, 4.17% higher recall, and 14.58% higher precision compared to other stacking models. The prediction results can be used for early identification of complications in diabetic patients.
AB - Individuals with diabetes often experience nerve damage complications due to diabetic neuropathy, with up to 50% of cases being asymptomatic, increasing injury risk. Reducing the risk of long-term complications related to diabetes requires the ability to predict and track the severity of diabetic neuropathy in patients. Diabetes care strategies and management by predicting the severity of diabetic neuropathy can offer insight into disease progression and assist healthcare professionals in managing high-risk patients. The study introduces a novel approach by predicting diabetic neuropathy severity using electromyography signals, moving beyond traditional medical data. It also innovates by employing a hybrid method of Ensemble models with Particle Swarm Optimization for parameter optimization. The study predicts diabetic neuropathy severity by selecting the top 10, 20, and 30 features from 90 extracted electromyography signal features using a correlation matrix, principal component analysis, and recursive feature elimination. Various machine learning models, as well as two ensemble models, boosting and stacking, were employed for prediction. Optimal parameters for each learner were determined using Particle Swarm Optimizer to enhance prediction performance. Among 144 experiment scenarios, the hybrid stacking-particle swarm optimizer model outperformed others, showing 14.29% higher accuracy, 13.93% higher F-1 score, 4.17% higher recall, and 14.58% higher precision compared to other stacking models. The prediction results can be used for early identification of complications in diabetic patients.
KW - Diabetes
KW - EMG signal
KW - Ensemble model
KW - Hybrid stacking
KW - Particle swarm optimizer
UR - http://www.scopus.com/inward/record.url?scp=85207880954&partnerID=8YFLogxK
U2 - 10.22266/ijies2024.1231.38
DO - 10.22266/ijies2024.1231.38
M3 - Article
AN - SCOPUS:85207880954
SN - 2185-310X
VL - 17
SP - 487
EP - 505
JO - International Journal of Intelligent Engineering and Systems
JF - International Journal of Intelligent Engineering and Systems
IS - 6
ER -