A Comprehensive Study of Machine Learning and Deep Learning Technique Based Personalized Treatment Analysis Using Electronic Health Records

Electronic Health Records (EHR) serves as a digital platform for the storage and maintenance of medical patient history for future analysis. The EHR allows for easy and quick access to patient details, facilitating a better diagnosis by healthcare professionals. The EHR platform improves communication within healthcare, which leads to reduction in medical errors. The EHR data includes details such as medical history, diagnosis, lab and test results, treatment plans, and radiology images that require large datasets. Reducing the dimensionality of data without losing important information is very complex. Hence, Machine Learning (ML) and Deep Learning (DL) methods are used to regulate personalized treatment analysis based on the EHRs. The ML and DL methods employ classification techniques such as Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), Multilayer Perceptron (MLP), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Reinforcement Learning, and Linear Regression (LR) to ensure accurate predictions and formulate personalized treatment plans. The performance metrices such as recall, precision, specificity, and FI-Score are used to evaluate the performance of the proposed model against that of the existing models.