International Research Journal of Engineering and Technology (IRJET) Volume: 04 Issue: 02 | Feb -2017
www.irjet.net
e-ISSN: 2395 -0056 p-ISSN: 2395-0072
Review paper on Big Data in healthcare informatics Harshit Kumar1, Nishant Singh2 1Student 2Student
B.E(3rd year),Dept.of Computer Engg., SKNCOE , Pune University B.E(3rd year),Dept.of Computer Engg., SKNCOE, , Pune University
---------------------------------------------------------------------***--------------------------------------------------------------------decision support systems (physician’s written notes Abstract - The rapid increase in computational power, the and prescriptions, medical imaging, laboratory, number of internet enabled data generating devices and the falling costs of data storage itself which make data available pharmacy, insurance, and other administrative data); to everybody for virtually no cost have primarily lead to the patient data in electronic patient records (EPRs); emergence of big data. Health Care is one of the major areas machine generated/sensor data, such as from where the use of big data analytics has become monumental in monitoring vital signs; social media posts, including rendering productive performance as compared to the Twitter feeds (so-called tweets) [3], blogs [4], status conventional means. Big data mainly deals with the storage updates on Facebook and other platforms, and web and processing of large scale and complex data sets for which pages; and less patient-specific information, including the traditional methods prove to be inept. In this paper a emergency care data, news feeds, and articles in survey on use of big data analytics in health care has been medical journals. made to provide an insight overview of the technology, methodology and algorithms in big data used for data management and decision making in healthcare .the outcomes of this survey paper will prove to be beneficial to academician, researchers, industries who have interest in big data and healthcare specifically. Key Words: big data, healthcare informatics,volume,velocity.variety,varacity,stakehold ers,genomic analytics ,opportunities
1.INTRODUCTION The healthcare industry historically has generated huge amount of data, driven by record keeping, compliance & regulatory requirements, and patient care[1]. Historically, the point of care generated mostly unstructured data: office medical records, handwritten nurse and doctor notes, hospital admission and discharge records, paper prescriptions, MRI, CT and other images. The increase in digitization of data in healthcare industry has started producing data that fits in the definition of big data by all the attributes and definitions. The analytics of these digital data will provide multidimensional benefits in clinical practices, disease surveillance, population health administration and management in healthcare industry. By definition, big data in healthcare refers to electronic health data sets so large and complex that they are difficult (or impossible) to manage with traditional software and/or hardware; nor can they be easily managed with traditional or common data management tools and methods [2]. It includes clinical data from CPOE(Computerized physician order entry) and clinical Š 2017, IRJET
|
Impact Factor value: 5.181
|
2) V's OF THE HEALTH CARE BIG DATA 2.1)Volume According to Health Catalyst [5], healthcare firms with over 1,000 employees store over 400 terabytes of data per firm (reported in the year of 2009), which qualifies healthcare as a high-data volume industry, despite the real-time streams of web and social media data. Contributing to the huge volume of healthcare data are various sources of data, from traditional personal medical records and clinical trial data to new types of data such as various sensor readings and 3D imaging [6].Recently the proliferation of wearable medical devices has significantly added fuel to the healthcare data. Those devices are able to continuously monitor a series of physiological information, such as bio potential, heart rate, blood pressure, and so forth [7]. 2.2) Variety Healthcare data could be characterized by the variety of sources and the complexity of different forms of data. Generally, healthcare data could be classified into unstructured, structured, and semi structured. Historically, most unstructured data usually come from office medical records, handwritten notes, paper prescriptions, MRI, CT, and so on.[30] The structured and semi structured data refers to electronic accounting and billings, actuarial data, laboratory instrument readings, and EMR data converted from paper records [8].Nowadays, more and more data streams add variety to healthcare information, both structured and unstructured, including intelligent wearable devices, fitness devices, social media, and so on.
ISO 9001:2008 Certified Journal
|
Page 197