Machine Learning Approaches For Nurses Decision Support System
Elizabeth Sony Thomas1, Anju Pratap2

1Elizabeth Sony Thomas, Department of Computer Science and Engineering, Saintgits College of Engineering, Kottayam (Kerala), India.
2Dr. Anju Pratap, Department of Compter Science and Engineering, Saintgits College of Engineering, Kottayam (Kerala), India.
Manuscript received on 27 March 2019 | Revised Manuscript received on 08 April 2019 | Manuscript Published on 18 April 2019 | PP: 928-931 | Volume-7 Issue-6S March 2019 | Retrieval Number: F03890376S19/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Cutting edge technologies lead to the early detection of diseases in the medical field. Now a day the main focus of health industry is to give high quality patient care. Some of the modern areas like clinical decision support system (CDSS) have been used by the clinicians to assist them for giving efficient patient care. This research work is focused on nurse practitioners for using such decision support systems. The initial stage of research carried out on two emergency situations that are handled by the nurses: Post Operative patient situation and Cardiac Arrhythmia. The identification of these conditions is very prevalent for the nurse practitioners in the absence of doctors. Cardiac arrhythmia can be diagnosed by taking ECG, usually identified by doctors. This paper introduces an approach for making suitable decision for nurses in the post operative ward and, also for interpreting the ECG signals for giving better care for the patients. The data set for the proposed work is taken from the UCI repository: postoperative data and cardiac arrhythmia. To build a decision support system, different machine learning techniques are used in this work. In order to take a better decision, the accuracy of desired model should be high so it is necessary to select the best feature from the existing attributes. This work compares the accuracy of the model for the postoperative datasets by using the classification machine learning algorithms like Random Forest, Linear Vector Quantization, Gradient Boosting Method algorithms, hence predict the best model.
Keywords: Cardiac Arrhythmia, Decision Support System, Electrocardiography (ECG), Nurses, Postoperative.
Scope of the Article: Machine Learning