• Pedda Golla Ganesh
• A.Nithin
• S.Rohith
• Ms.G.Lohitha

People will face many problems in Hospitals while taking Admission. If it is in a popular hospital, they should wait hours together to take just admission. But it is not at all good at Emergency Department. Very serious cases will admit in Emergency Department. So, we need to use more innovation technique to ameliorate patient flow and prevent Overflowing. So, data mining techniques will show us a pleasant method to predict the ED Admissions. Here we Analyzed an algorithm for predicting models i.e. Naive Bayes, Random Forests, Support Vector Machine. For the prediction we should identify a handful of factors associated to Hospital admission including age, gender, systolic pressure, diastolic pressure, diabetes, previous records in the preceding month or year, admission. We also say about the algorithms which we used in detail. We use Random Forests algorithm for classifying the data into categories for improving the accuracy of prediction. Naive Bayes is used to identify the probabilities for each attribute and helps in predicting the outcome. Support Vector machine is used to classify the given input particular category which helps in predicting the outcome. Among all the algorithms SVM is giving better performance and we have extended paper with deep learning algorithms such as LSTM and CNN and among all algorithms CNN (Convolution Neural Networks) is giving best prediction result.

Machine learning,Admission required,Admission not required,Support vector Machine,Convolution Neural Networks,Naïve Bayes.

"Prediction of hospital admission using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.a667-a673, April-2024, Available :http://www.jetir.org/papers/JETIR2404083.pdf

"Prediction of hospital admission using machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppa667-a673, April-2024, Available at : http://www.jetir.org/papers/JETIR2404083.pdf