Key result
A one-dimensional deep learning convolutional neural network incorporated with a support vector machine classifier successfully detected chronic kidney disease from salivary urea with 98.04% accuracy.
A novel deep-learning-based sensing technique using salivary urea concentration can detect chronic kidney disease with 98.04% accuracy.
May enable noninvasive CKD screening; leaves open need for prospective clinical validation.
In this article, we propose a new sensing technique for the automated detection of kidney disease. The salivary urea concentration is monitored to detect the disease. A new sensing approach is introduced to monitor the urea levels in the saliva sample. Furthermore, for analyzing the raw signals obtained from the sensor, we have implemented a one-dimensional deep learning convolutional neural network (CNN) algorithm, which is incorporated with a support vector machine (SVM) classifier. The use of CNN-SVM integrated network enhanced the classification accuracy of the model. The proposed model successfully classified the samples with an accuracy of 98.04%.
No takes yet. Share an insight, caveat, or question.
Bhaskar et al. (2019) studied Chronic Kidney Disease. Deep-learning-based sensing technique (CNN-SVM) for salivary urea concentration was evaluated on Classification accuracy. A one-dimensional deep learning convolutional neural network incorporated with a support vector machine classifier successfully detected chronic kidney disease from salivary urea with 98.04% accuracy.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: