Prediction of Insufficient Accuracy for Patients Length of Stay using Deep Belief Network

The research study is to predict the patient's length of stay at healthcare centers and analyze their patient discharge by admission using machine learning algorithms to achieve higher accuracy and also to determine the patient's data to predict unplanned readmission in Intensive Care Unit (ICU). The framework to classify the Support Vector Machine (SVM) and Logistic Regression (LR) to perform all measures. This research study used the Novel Deep Belief Network and Convolutional Neural Network to perform the operations to give the best exactness of the patient's length of stay at healthcare centers. Their patients' health investigations were gathered from numerous web sources with current study results and threshold 0.05%, confidence interval 95% mean, and standard deviation for the research study, which used 47 samples with two groups of algorithms and a G-power of 80%. To predict the healthcare analysis, the Novel Deep Belief Network algorithm has found 90.25% of accuracy, therefore this study needs to find better accuracy for health prediction with the Convolutional Neural Network algorithm in machine learning. This research study found 87.11% of accuracy for healthcare analysis using the Convolutional Neural Network algorithm with a significant value of two tailed tests is 0.045 (p<0.05) with 95% confidence interval. This study concludes that the Novel Deep Belief Network algorithm for patient healthcare analysis is significantly better than the Convolutional Neural Network algorithm.