Content uploaded by Dr G Manjula
Author content
All content in this area was uploaded by Dr G Manjula on Apr 12, 2021
Content may be subject to copyright.
A preview of the PDF is not available
Application of BigData in Healthcare-Theory and Practices
Figures
Figures - uploaded by Dr G Manjula
Author content
All figure content in this area was uploaded by Dr G Manjula
Content may be subject to copyright.
ResearchGate has not been able to resolve any citations for this publication.
One of the most dreadful disease is breast cancer and it has a potential cause for death in women. Every year, death rate increases drastically due to breast cancer. An effective way to classify data is through classification or data mining. This becomes very handy, especially in the medical field where diagnosis and analysis are done through these techniques. Wisconsin Breast cancer dataset is used to perform a comparison between SVM, Logistic Regression, Naïve Bayes and Random Forest. Evaluating the correctness in classifying data based on accuracy and time consumption is used to determine the efficiency of the algorithms, which is the main objective. Based on the result of performed experiments, the Random Forest algorithm shows the highest accuracy (99.76%) with the least error rate. ANACONDA Data Science Platform is used to execute all the experiments in a simulated environment.
Breast Cancer is the most often identified cancer among women and major reason for increasing mortality rate among women. As the diagnosis of this disease manually takes long hours and the lesser availability of systems, there is a need to develop the automatic diagnosis system for early detection of cancer. Data mining techniques contribute a lot in the development of such system. For the classification of benign and malignant tumor we have used classification techniques of machine learning in which the machine is learned from the past data and can predict the category of new input. This paper is a relative study on the implementation of models using Logistic Regression, Support Vector Machine (SVM) and K Nearest Neighbor (KNN) is done on the dataset taken from the UCI repository. With respect to the results of accuracy, precision, sensitivity, specificity and False Positive Rate the efficiency of each algorithm is measured and compared. These techniques are coded in python and executed in Spyder, the Scientific Python Development Environment. Our experiments have shown that SVM is the best for predictive analysis with an accuracy of 92.7%.We infer from our study that SVM is the well suited algorithm for prediction and on the whole KNN presented well next to SVM.
Like other fields, the healthcare sector has also been greatly impacted by big data. A huge volume of healthcare data and other related data are being continually generated from diverse sources. Tapping and analysing these data, suitably, would open up new avenues and opportunities for healthcare services. In view of that, this paper aims to present a systematic overview of big data and big data analytics, applicable to modern-day healthcare. Acknowledging the massive upsurge in healthcare data generation, various ‘V's, specific to healthcare big data, are identified. Different types of data analytics, applicable to healthcare, are discussed. Along with presenting the technological backbone of healthcare big data and analytics, the advantages and challenges of healthcare big data are meticulously explained. A brief report on the present and future market of healthcare big data and analytics is also presented. Besides, several applications and use cases are discussed with sufficient details.
Recommender System (RS) has emerged as a major research interest that aims to help users to find items online by providing suggestions that closely match their interests. This paper provides a comprehensive study on the RS covering the different recommendation approaches, associated issues, and techniques used for information retrieval. Thanks to its widespread applications, it has induced research interest among a significant number of researchers around the globe. The main purpose of this paper is to spot the research trend in RS. More than 1000 research papers, published by ACM, IEEE, Springer, and Elsevier from 2011 to the first quarter of 2017, have been considered. Several interesting findings have come out of this study, which will help the current and future RS researchers to assess and set their research roadmap. Furthermore, this paper also envisions the future of RS which may open up new research directions in this domain.
Nowadays we are facing with data flood in many areas. Big data come from numerous sources such as human activities, measuring instruments and many appliances connected to computers or smart phones. One of the most challenging topics in the next decade will be how combination of genome and exposome data will contribute to reveal the risks for particular diseases. According to the medical scientists, the exposome includes all exposure environmental factors, from chemical and nonchemical agents to socio-behavioral and psychological factors as stress, diet, endogenous and exogenous factors from whole lifespan. The growing of mobile and ubiquitous computing technologies contributes in increasing the number of records regarding personal health and habits of patients. Internet of Things (IoT) includes the development of wearable measurement sensors connected with Bluetooth, which are capable to capture and store health-related data, intended to be stored in patient health records. The exposome is a healthcare and medicine concept that implies an interdisciplinary and integrated approach of many sciences domains including epidemiology, computing, environment sciences, toxicology and social science. We aim to integrate the data collected from various sensors and detectors in the patient health record to provide clinicians with more elements for better disease prognosis, diagnosis and treatment.
Data mining is the extraction of unseen predictive info from huge databases, is the process of arranging through enormous data sets to recognize patterns and create relationships to resolve the problems through data analysis. Cancer is one of the primary reasons of death wide-reaching. Timely detection and prevention of cancer plays a very vital role in decreasing deaths affected by cancer. Identification of genetic and environmental factors is very significant in emerging novel methods to identify and avert cancer. Many researchers’ use data mining techniques like clustering, classification and prediction find potential cancer patients. This paper focuses on a breast cancer prediction system built on data mining techniques. With the help of this system, people can guess the possibility of the breast cancer in the former stage itself.
Cardiovascular sickness is the largest cause of death in developing countries. The study of this coronary heart disease prediction model using a data mining technique and decision tree algorithm are applied in medical research, especially in heart disease prediction. The Coronary Heart Disease is also known as Coronary Artery Disease (CAD). Hence the decision system is analyses the heart disease for the patient. In this paper coronary illness studied a more number of input attributes and database records based on the patient's clinical data. This paper focuses on the around the prediction of heart disease accuracy value using the decision tree algorithm.
