Predicting hyperkalemia by a two-staged artificial neural network

Wu, Ming‐Feng; Chiang, Jung-Hsien; Yang, Yan-Bin; Chao, I-Pin; Shieh, Sean; Tzeng, Wen-Yan; Hsieh, J.C.

doi:10.1109/cic.2003.1291185

Cited by 5 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dimension of classification was decreased from the previous 17 to 5 in this study [6]. The benefits of the reduced dimension model were not only to reduce the complexity of classification but also to speed up the iteration in the algorithm of k-means.…”

Section: Discussionmentioning

confidence: 99%

“…Nevertheless, the choice of the exact features in response to hyperkalemia is difficult to make because of the variability of the features. In our previous study [6], we developed a two-stage artificial neural network to predict patients' hyperkalemia (5.4 -7.4 mmole/L). The results showed that the sensitivity of prediction reached 60% and the specificity was approximately 60%.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Predicting hyperkalemia by the use of a 12-lead temporal-spatial electrocardiograph: clinical evaluations and model simulations

Tzeng

Chan

Hsieh

2005

Computers in Cardiology, 2005

Self Cite

View full text Add to dashboard Cite

Predicting hyperkalemia by the use of IntroductionThe rapidity and accuracy of predicting hyperkalemia was crucial in clinical practice. Hyperkalemia can be degenerated and endanger one's life if it is not diagnosed in time. Traditionally, the procedure for diagnosis of hyperkalemia is conducted through the laboratory blood test, which will take 20 minutes or more. Recently, the diagnosis of hyperkalemia can be conducted by the use of ECG because of its convenience and the possible correlations between potassium levels in serum and ECG features. The verification of the correlations between hyperkalemia and ECG may increase the diagnostic and treatment efficiency. However, the sensitivity of hyperkalemia prediction by ECG is very low (about 38% to 58%) even by experienced cardiologists [1,2], because the ECG features in response to hyperkalemia are still unclear. Based on recent clinical reports [3,4], hyperkalemia is related to the changes of some ECG features. The peaked T waves could be observed in some chest leads or limb lead II in early hyperkalemia, and flatten P waves in some limb and chest leads. Other variables such as the increased PR interval, the QRS interval, and the RR interval could be seen in mild to severe hyperkalemia [5]. Nevertheless, the choice of the exact features in response to hyperkalemia is difficult to make because of the variability of the features. In our previous study [6], we developed a two-stage artificial neural network to predict patients' hyperkalemia (5.4 -7.4 mmole/L). The results showed that the sensitivity of prediction reached 60% and the specificity was approximately 60%. In this study, a serial two-staged classifier based on k-means method was developed to screen hyperkalemia using feature parameters extracted from 12-lead ECG. Furthermore, to search for better correlations between ECG features and hyperkalemia, a computer program ECGSIM was used to simulate the ECG waveforms under mild to severe hyperkalemic conditions. Methods Extracting ECG feature parametersThe SCP-ECG records of 56 normal individuals and 41 hyperkalemia patients (serum potassium level > 5.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Predicting hyperkalemia by the use of a 12-lead temporal-spatial electrocardiograph: clinical evaluations and model simulations

Tzeng

Chan

Hsieh

2005

Computers in Cardiology, 2005

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent studies have utilized deep learning models [2] [3] [4] [5] to classify between normal and hyperkalaemia classes. Deep learning models require vast amounts of data to train effectively without over-fitting.…”

Section: Introductionmentioning

confidence: 99%

Integrating Morphological Characteristics with Empirical Mode Decomposition for Robust ECG Signal Classification

Achamma T Varghese

2024

cana

View full text Add to dashboard Cite

Hyperkalemia, a critical concern, is the primary cause of sudden cardiac deaths in patients with chronic kidney disease (CKD). Traditionally, blood tests serve as the gold standard for hyperkalemia detection. Electrocardiogram (ECG) signals offer a non-invasive means to assess cardiac activity and identify hyperkalemia in CKD patients. Hyperkalemia often presents ECG changes such as elevated T-waves, changes in P-wave morphology, prolonged PR intervals, widened QRS complexes, and, in severe instances, the onset of ventricular arrhythmias and sinusoidal waves. This study proposes a method for the classification of ECG signals for hyperkalaemia using a feature set extracted from electrocardiogram (ECG) signals. Our approach integrates morphological attributes, including P-wave amplitude, T-wave amplitude, QRS interval, PR interval, and ST depression, with spectral attributes such as total power, spectral entropy, variance, skewness, and singular values extracted from Intrinsic Mode Functions obtained through empirical mode decomposition., aiming to capture both structural and frequency domain information inherent in ECG signals. Morphological features provide insights into cardiac abnormalities associated with hyperkalemia and spectral features extracted from IMF, offer valuable information regarding the frequency distribution and complexity of ECG signals. The performance of three classifiers—Kernel Naïve Bayes (KNB), AdaBoost Ensemble Classifier, and Artificial Neural Networks (ANN) is assessed using the extracted features. Among these classifiers, AdaBoost Ensemble Classifier demonstrated the most favorable classification results with sensitivity of 97.7, specificity of 98.84 and accuracy of 98.3%. These findings align with existing state-of-the-art approaches for hyperkalemia classification.

show abstract

“…However, in the diagnosis field of potassium disturbances, very little references were published. Wu et al (2003) proposed a two-staged artificial neural network for predicting of hyperkalemia. Although the proposed approach represents a good step toward the application of artificial intelligence techniques for diagnosis of K + disturbances, it has many shortcomings.…”

Section: Introductionmentioning

confidence: 99%

A Novel Neural Fuzzy Approach for Diagnosis of Potassium Disturbances

Amer

Amawi²,

El-Khatib

2011

International Journal of Healthcare Information Systems and Informatics

View full text Add to dashboard Cite

In this paper, a neural fuzzy system for the diagnosis of potassium disturbances is presented. This paper develops an adaptive neuro-fuzzy expert system that can provide accurate diagnosis of potassium disturbances. The proposed diagnostic approach has many attractive features. First, it provides an efficient tool for diagnosis of K+ disturbances and aids clinicians, especially the non-expert ones, in providing fast and accurate diagnosis of K+ disturbances in critical time. Second, it significantly reduces the time needed to accomplish precise diagnosis of K+ disturbances and thus enhances the healthcare standards. Third, it is capable of diagnosing the different types of potassium disturbances using a hybrid neural fuzzy approach. Finally, it has good accuracy (higher than 87%), specificity (100%), and average sensitivity (83%). The performance of the proposed diagnostic system was experimentally evaluated and the achieved results confirmed that the proposed system is efficient and accurate in diagnosing K+ disturbances.

show abstract

Predicting hyperkalemia by a two-staged artificial neural network

Abstract: Abstract

Cited by 5 publications

References 5 publications

Predicting hyperkalemia by the use of a 12-lead temporal-spatial electrocardiograph: clinical evaluations and model simulations

Predicting hyperkalemia by the use of a 12-lead temporal-spatial electrocardiograph: clinical evaluations and model simulations

Integrating Morphological Characteristics with Empirical Mode Decomposition for Robust ECG Signal Classification

A Novel Neural Fuzzy Approach for Diagnosis of Potassium Disturbances

Contact Info

Product

Resources

About