Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Challenges and Opportunities of Big Data in Health Care: A Systematic Review

Challenges and Opportunities of Big Data in Health Care: A Systematic Review Background: Big data analytics offers promise in many business sectors, and health care is looking at big data to provide answers to many age-related issues, particularly dementia and chronic disease management. Objective: The purpose of this review was to summarize the challenges faced by big data analytics and the opportunities that big data opens in health care. Methods: A total of 3 searches were performed for publications between January 1, 2010 and January 1, 2016 (PubMed/MEDLINE, CINAHL, and Google Scholar), and an assessment was made on content germane to big data in health care. From the results of the searches in research databases and Google Scholar (N=28), the authors summarized content and identified 9 and 14 themes under the categories Challenges and Opportunities, respectively. We rank-ordered and analyzed the themes based on the frequency of occurrence. Results: The top challenges were issues of data structure, security, data standardization, storage and transfers, and managerial skills such as data governance. The top opportunities revealed were quality improvement, population management and health, early detection of disease, data quality, structure, and accessibility, improved decision making, and cost reduction. Conclusions: Big data analytics has the potential for positive impact and global implications; however, it must overcome some legitimate obstacles. (JMIR Med Inform 2016;4(4):e38) doi: 10.2196/medinform.5359 KEYWORDS big data; analytics; health care; human genome; electronic medical record Big data is commonly defined through the 4 Vs: volume (scale Introduction or quantity of data), velocity (speed and analysis of real-time or near-real-time data), variety (different forms of data, often Rationale from disparate data sources), and veracity (quality assurance of Big data analytics offers promise in many business sectors, and the data). The first 3 Vs are found in most literature [2,3], and health care is looking at big data to provide answers to many the fourth V is a goal [4]. age-related issues, particularly dementia and chronic disease As of 2012, about 2.5 exabytes of data are created each day; management. This systematic review explores the depth of big Walmart can collect up to 2.5 petabytes of customer-related data analytics since 2010 and identifies both challenges and data per hour [2]. The industry of health care produces and opportunities associated with big data in health care. The review collects data at a staggering speed, but different electronic health follows the standard set by Preferred Reporting Items for records (EHRs) collect data in different structures: structured, Systematic Reviews and Meta-analysis (2009) [1]. http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 1 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al unstructured, and semistructured. This variety can pose difficulty convert data into knowledge. Health care needs to follow their when seeking veracity or quality assurance of the data. The lead so that decisions regarding organizational objectives and EHRs can provide a rich source of data, ripe for analysis to goals can be met [4,11,12]. This evolutionary process of data increase our understanding of disease mechanisms, as well as management is collectively known as big data, and it is essential better and personalized health care, but the data structures pose to the future of adoption and management of health information a problem to standard means of analysis [5]. technology [13]. There are several large sources for big data in health care: Objectives genomics, EHR, medical monitoring devices, wearable video The purpose of this systematic review is to objectively review devices, and health-related mobile phone apps. Approximately articles and studies published in academic journals in order to 483 studies on genomics are registered with the US Department compile a list of challenges and opportunities faced by big data of Health and Human Services; these studies are being analytics in health care in the United States. Particular emphasis conducted in 9 countries, and they all use portions of the data was paid to age-related applications of big data. from the Human Genome Project [6]. The EHR, being adopted in many countries, offers a source of data the depth of which is Methods almost inconceivable. About 500 petabytes of data was generated by the EHR in 2012, and by 2020, the data will reach Eligibility Criteria 25,000 petabytes [7]. The EHR can collect data from other Articles and studies were eligible for analysis if they were monitoring devices, but the continuous data streams are not published between 2010 and 2015, published in academic consistently saved in the longitudinal record. journals, and published in English. The researchers chose a The decrease in the cost of storage has enabled an exponential range from 2010 to 2015 for two reasons: HITECH was passed distribution of data collection, but the ability to analyze this in 2009, and it appeared that a blossom of research and other quantity of data is the center of gravity for “big data” in health articles seemed to occur in 2010. We focused on academic care. In the United States, financial incentives offered for the journals for their peer-review quality and to decrease the chance “meaningful use” of health information technology has spurred of selecting something about big data published from a growth in the adoption of the EHR and other enabling noncredible source. health-related technology since 2009. Information Sources Health information systems show great potential in improving A combination of key terms from Medical Subject Headings the efficiency in the delivery of care, a reduction in overall costs (MeSH) and Boolean operators were combined and used in 2 to the health care system, as well as a marked increase in patient common research databases, CINAHL and PubMed, and outcomes [8]. The US government has allocated billions of combined with a general search from Google Scholar (see Figure dollars to help the country’s health care market realize some of 1) in January 2016. these efficiencies and savings. Specific provisions of the Health These terms were chosen not only because they are the focus Information Technology for Economic and Clinical Health of the review, but also because they were identified in the initial (HITECH), part of the American Recovery and Reinvestment research into the definition of big data. Act, acknowledge the importance of IT in the delivery of health care within the United States [9]. The Act allocates Search approximately US $17.2 billion in incentives for the adoption The following search string was used in all 3 searches: ((“big and meaningful use of health information technology, part of data” AND healthcare) OR (“big data” AND “health care”)). which involves the participation in the electronic exchange of This search string was used in CINAHL, PubMed (MEDLINE), clinical information. In 2010, the Congress passed the Health and Google Scholar. In the 2 research databases, our team was Information Exchange (HIE) Challenge Grant Program, which able to restrict the search to academic journals (including other contributed about US $547.7 million to state HIE programs systematic reviews). MEDLINE was excluded in CINAHL [10]. because it was already captured in PubMed. Google Scholar With the implementation of this legislation as well as the creates difficulty for searches because of its severe limit of technologies associated with it, it is imperative to effectively filters typically associated with academic research. The initial organize and process the ever-increasing quantity of data that 13,935 results were limited by restricting dates to the last 5 is digitally collected and stored within health care organizations. years, limiting results to academic journals and MEDLINE, and Other industries such as astronomy, retail, search engines, and in Google Scholar by restricting the keyword search to titles. politics have developed advanced data-handling capabilities to The result from the filters ended with 121 articles to review. http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 2 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al Figure 1. Literature review process with inclusion and exclusion criteria. observations. These themes were tabulated and counted for Study Selection additional analysis. Through group research and a series of consensus meetings, researchers were trained to identify articles germane to this Results review and to recommend elimination of all others. A shared spreadsheet was used by the research team to parse through the Study Selection list of articles. Researchers read all articles in their entirety. A As depicted in Figure 1, 935 articles resulted from the initial total of 97 articles were eliminated due to various exclusion search. Filters such as data published (2010-2015), academic criteria (not germane to big data or health care, editorial only, journals, and English language were implemented to reduce the not an academic journal, or duplicate from another search), and range to what was being studied. Reviewers agreed to eliminate 4 additional articles were identified from the references of the editorials and focus on those articles that studied big data, as 24 that remained. The group of reviewers made these rejections described in the Introduction section of this manuscript. At the or additional recommendations through a series of consensus end of the search process, only 28 remained. The articles meetings where we met to discuss their recommendations and reviewed for this study ranged from 2012 to 2015. The majority consensus was reached through discussion. A total of 28 articles of the literature chosen for this paper was published in 2014 remained in the final review. (15/28, 54%), and a minority was published in 2015 (2/28, 7%); the latter was most likely due to the early part of the year when Data Collection Process and Identification of Summary the search was conducted. Measures Each article was reviewed by at least two authors to identify Synthesis of Results the relevant points. All reviewers used a spreadsheet template Multiple reviewers read each article in its entirety. Articles were to summarize their key observations from each article. One team included or excluded based on the criteria illustrated in Figure member combined the spreadsheets into one and shared it once 1. All articles included in the analysis were sorted by date and again. Reviewers held one more consensus meeting to discuss are listed in Multimedia Appendix 1. their findings. From this meeting, trends were identified, and A study catalog number was assigned to each article to simplify from those trends, inferences were made. the analysis. Researchers summarized the main points of each Additional Analysis article for further analysis. From the list of observations, reviewers were able to identify Additional Analysis some common threads that emerged as challenges and Through the combination of observations, reviewers identified opportunities in health care that permeated multiple articles. common threads (challenges and opportunities) and themes Separate tables were created to group the threads, and from each from each thread. Themes were organized into affinity diagrams of these tables, common themes were identified. These common (Tables 1 and 2), compared, and discussed among researchers. themes only emerged when reviewers combined their http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 3 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al lack of skill of data analysts, inaccuracies in data, regulatory Challenges for Big Data in Health Care compliance, and real-time analytics. Examples for each theme Nine themes emerged under the category of challenges: data are provided in Table 1. A total of 60 observations were made structure, security, data standardization, data storage and for challenges. transfers, managerial issues such as governance and ownership, Table 1. Themes associated with challenges for big data in health care. Themes Examples Number of articles Articles themes appeared in % of total articles (n) (N=28) Data structure Fragmented data 17 1, 2, 7-9, 12, 14-19, 22, 25-28 61% Incompatible formats Heterogeneous data   Raw and unstructured datasets   Large volumes   High variety and velocity   Lack of transparency   Security Privacy 14 2, 4, 7-9, 12, 13, 17, 21, 22, 25- 50% Confidentiality Data duplication Integrity Data standardization Limited Interoperability 11 4, 5, 7-9, 11, 12, 15, 16, 22, 25 39% Data acquisition and cleansing Global sharing Terminology Language barriers Storage and transfers Expensive to store 8 1, 4, 7, 12, 22, 26, 28 28% Transfer from one place to other Store electronic data Securely extract, transmit, and process Managerial issues Governance issues 4 2, 8, 14, 22 14% Ownership issues Lack of skill Untrained workers 3 5, 9, 14 11% Inaccuracies Inconsistences 1 9 4% Lack of precision Data timeliness Regulatory compliance Legal concerns 1 13 4% Real-time analytics Real-time analytics 1 9 4% The 4 Vs appear in multiple places under the Challenges Data Structure Issues category. Volume and variety are seen by name under the theme Issues related to data structure were addressed in the majority of Data structure. Variety is also implied in the same theme, of the papers reviewed for this study. It is essential that the key but listed as Incompatible formats, as well as Raw and functions of data processing are supported by the applications unstructured datasets. Variety can also be inferred from the of big data [13]. Big data applications should be user-friendly, theme of Data standardization, listed as Limited interoperability. transparent, and menu-driven [13,14]. The majority of data in Velocity is seen in the theme Real-time analytics. Veracity is health care is unstructured, such as from natural language seen under the theme of Data Standardization, but listed as Data processing [12]. It is often fragmented, dispersed, and rarely acquisition and cleansing, Terminology, and Language barriers. standardized [12,13,15-21]. It is no secret that the EHRs do not It is also inferred in the theme Inaccuracies listed as share well across organizational lines, but with unstructured Inconsistencies and Lack of precision. data, even within the same organization, unstructured data is http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 4 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al difficult to aggregate and analyze. It is no wonder that 61% of Managerial Issues the articles analyzed listed this as a concern; big data analytics Data governance will need to move up on the priority list of will need to address this large challenge. organizations, and it should be treated as a primary asset instead of a by-product of the business [15]. Data ownership and data Research data within the health care sector is more stewardship should create new roles in business that consider heterogeneous than the research data produced within other big data analytics [15], and new partnerships will need to be research fields [3,5,12]. Data from both research and public brokered when sharing data [23,24,27]. About 14% of the health is often produced in large volumes [15,22,23]. Another literature mentioned this point. structure-related issue results from the changing health care fee-for-service care model [4]. Finally, big data will need to Lack of Appropriate Skills address issues with the transparency of metadata [16,24]. It is important that health care workers are also kept up to date Security Issues with the use of constantly changing technology, techniques, and a constantly moving standard of care [5,24]. Due to the constant There are considerable privacy concerns regarding the use of evolution of technology, there exist populations of individuals big data analytics, specifically in health care given the enactment lacking specific skills; as such this is also a significant of Health Insurance Portability and Accountability Act(HIP   AA) continuing barrier to the implementation of big data [12]. About legislation [15]. Data that is made available on open source is 11% of the literature expressed this challenge. freely available and, hence, highly vulnerable [12,13,18,20]. Further, due to the sensitivity of health care data, there are Inaccuracies (Veracity) significant concerns related to confidentiality [25,26]. Moreover, Self-reported data is extensively used in health care, and so it this information is centralized, and as such, it is highly is crucial that the data collected in this manner be consistent vulnerable to attacks [25]. For these reasons, enabling privacy [12]. Keeping information current as well as accurate is another and security is very important, as illustrated by a frequency of challenge of data collection. Precision of data is also needed to mention in 50% of the literature reviewed. provide accurate information [12]. Only 4% of the literature Data Standardization Issues mentioned this challenge. Although the EHRs share data within the same organization, Regulatory Compliance Issues intra-organizational, EHR platforms are fragmented, at best. Health care organizations should be aware of the various legal Data is stored in formats that are not compatible with all issues that can surface in the process of managing high volume applications and technologies [13,22]. This lack of data of sensitive information. Organizations implementing big data standardization also causes problems in transfer of that data analytics as a part of their information systems will have to [5,25]. It complicates data acquisition and cleansing [5,25,26]. comply with a significant amount of standards and regulatory About 39% of the literature mentioned this challenge. compliance issues specific to health care [28]. Only 4% of the Limited interoperability poses a large challenge for big data, as literature mentioned this challenge. data is rarely standardized [12,13,16,22]. This leaves big data Real-Time Analytics (Velocity) to face issues related to the acquisition and cleansing of data One of the key requirements in health care is to be able to utilize into a standardized format to enable analysis and global sharing big data in real time. Real time is defined by enabling the use [13,17,23,25,27]. With globalization of data, big data will have of applications such as cloud computing to view said data in to deal with a variety of standards, barriers of language, and real time. The use of these technologies leads to issues of different terminologies. security and privacy within patient information [12]. Only 4% Storage and Transfers of the literature mentioned this challenge. Challenges most often Data generation is inexpensive compared with the storage and mentioned or discussed were data structure (17/28, 61%), transfer of the same. Once data is generated, the costs associated security (14/28, 50%), data standardization (11/28, 39%), and with securing and storing them remain high [25]. Costs are also data storage and transfers (8/28, 29%). The other five challenges incurred with transferring data from one place to another as well comprised less than 15% of the observations. as analyzing it [14,21,22]. Some researchers have been able to Opportunities for Big Data in Health Care combine the themes of Data structure and Storage and transfers Fourteen themes emerged under the category of opportunities: when they illustrate how structured data can be easily stored, improve quality of care, managing population health, early queried, analyzed, and so forth, but unstructured data is not as detection of diseases, data quality, structure, and accessibility, easily manipulated [13]. Cloud-based health information improve decision making, cost reduction, patient-centric care, technology has the additional layer of security associated with enhances personalized medicine, globalization, fraud detection, the extraction, transformation, and loading of patient-related and health-threat detection. Examples of each theme are listed data [27]. The use of big data should address issues related to in Table 2. A total of 113 observations were made for increased expenditures as well as the transmittance of secure opportunities. or insecure information. About 28% of the literature mentioned this challenge. http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 5 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al Table 2. Themes that emerged from the opportunities for big data in health care. Themes Examples Number of articles Articles themes appeared in % of total articles (n) (N=28) Improve quality of care Improve efficiency 18 2, 4, 5, 6, 8-13, 18-20, 22-25, 64% Improve outcomes Reduce waste Reduce readmissions Increased productivity and performance Risk reduction Process optimization Managing population Managing population health 17 2, 5, 8-10, 12-14, 16, 18-20, 23, 61% health 25, 26, 28 Early detection of diseases Predicting epidemics 17 2, 4, 5, 7-13, 15, 18-20, 23, 24, 61% Disease monitoring Health tracking Adopt and track healthier behaviors Predicting patient vulnerability Improved treatments Data quality, structure, and Large volumes 16 2, 4, 6, 9, 11, 12, 16, 18, 20- 23, 57% accessibility 25-28 Wide variety Creating transparency High-velocity capture Access to primary data Reusable data Weed out unwanted data Open source—free access Improve decision making Evidence-based medicine 11 2,-4, 7, 9, 12, 16, 20, 22, 23, 24 39% New treatment guidelines Accuracy in information Cost reduction Inexpensive 10 1, 3, 4, 7, 9, 11, 12, 14, 16, 18 36% Reducing health care spending Patient-centric health care Empowering patients 8 2, 3, 5, 12, 14, 20, 22, 24 29% Patients making informed decisions Increased communication Enhancing personalized Targeted approach 6 4-6, 24, 25, 28 24% medicine Globalization Widely accessible 6 2, 6-8, 10, 20 24% Global sharing Leveraging knowledge and practices Knowledge dissemination Fraud detection Fraud detection 3 8, 12, 28 11% Health-threat detection Health-threat detection 1 7 4% Despite the challenges that big data needs to overcome, the care industry (patient, provider, and payer). More than 64% of advanced analytics that are promised through big data offer the articles analyzed focused on quality improvement and more tremendous opportunities for most stakeholders in the health than 60% on managing population health and early detection http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 6 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al of diseases through big data analytics. If even some of the Data Quality, Structure, and Accessibility opportunities of big data are realized, they can radically change Literature suggests that big data enables rapid capture of data patient outcomes and the way decisions are made by providers, and the conversion of primary, raw and unstructured data into and help solve some macro-level issues related to health care meaningful information [15,17,31,34]. New knowledge can within countries such as the United States (cost, quality, and then be generated from high volumes of effective data, enabling access). reuse of the data [15,20,21,32,33]. Open-source technology increases accessibility to and transparency of the data Improve Quality of Care [12,25,26,30,35]. Finally, data quality can be maintained using Big data has the potential and ability to improve the quality and analytics to get rid of unnecessary information [27]. About 57% efficiency of care [5,15,23,29-31]. Big data offers an ability to of the literature mentioned this opportunity. predict outcomes using the available primary or historical data and provide proof of benefit that could change established, Improve Decision Making industry-wide standards of care [25,28]. Leveraging technology Big data enables appropriate use of evidence-based medicine at the patient end can also help with medication adherence and helps health care providers make more informed decisions [23,25]. This will most certainly play an important role in [12,13,15,22]. This, in turn, improves the quality of care improving outcomes [2,13] and improve the health-related provided to the patients [16,31,36]. Remote monitoring, patient quality of life [20,26,32]. profile analytics, and genomic analytics are examples of other applications that influence the decision-making process [13,25]. Quality of care will also be improved by reducing waste of information, which will reduce inefficiencies [13,26]. This will Decision-making process can be highly optimized by the also assist in analyzing real-time resource utilization productivity availability of accurate and up-to-date information, as decision [13]. Quality can also be improved by reducing the rates of making is influenced by the generation of new practices and readmissions, increasing operational efficiencies, and improving treatment guidelines within clinical research. Allowing big data performance [5,12,13]. About 64% of the literature mentioned to influence decision making will allow for a faster and simpler this opportunity. process. This is done by either supporting or replacing human decision making. About 39% of the literature mentioned this Managing Population Health opportunity. The management of population health and the early detection of diseases were topics that the authors thought would have Cost Reduction highly similar results after the analysis. Although there was a The literature suggests that the decrease in cost of the elements large overlap between the 2 themes, there was also specific of computing, such as storage and processing, leads to a decrease variation between them. So, the researchers chose to keep them in the cost of data-intensive tasks [2,13]. This pass-through of separate. The theme of managing population health focused on savings will be seen across the spectrum of medicine [24,36] special populations rather than public health. and the health care workforce [25]. Savings will be realized through more cost-effective treatments and monitoring to Big data analytics define populations at a finer level of improve medication adherence [25,31] and through the reduction granularity than has ever been previously achieved [5,14,15,33]. of costly transportation costs, as is experienced in cardiology It can help in managing the overall health of a population as [12,17,22,34]. About 36% of the literature mentioned this well as specific individual health [13,26,29]. Big data can enable opportunity. population health management from a local or global perspective [31,34]. This capability becomes more salient from the global Patient-Centric Care perspective when considering the aging of the population and Increasing the use of technology is slowly changing the direction age-related health issues shared by many populations and of the health care sector from disease-centric care toward subpopulations, many of which are underserved patient-centric care [5]. Big data will play a significant role in [17,19,21,24,28,32]. About 61% of the literature mentioned this this transformation [37]. It will allow the information to be opportunity. delivered to patients directly and empower them to play an Early Detection of Diseases active part in their care [5,15,27]. When patients are provided with the appropriate information, it will influence their decision Big data allows for the early detection of diseases, which aids making and allow them to make informed decisions [13,24]. in clinical objectives related to achieving improved treatments Informed decisions will also be influenced by increased and higher patient outcomes [12,13,15,22,25]. It is in this area communication between patients, providers, as well as their that the authors found great promise in age-related illness and communities [5,24,32,36]. About 29% of the literature disease. Along with early detection, big data analytics can also mentioned this opportunity. help in the prevention of a wide range of deadly illnesses and personalized disease management and monitoring Enhancing Personalized Medicine [5,19,21,22,29,34]. It enables providers to track healthy With the use of big data, the objectives of personalized medicine behaviors and helps patients in monitoring their respective can be translated into clinical practice [5,25,30]. Access to and conditions [25,32,33]. This capability holds great potential when processing of large volumes of data should enable a personalized faced with either age-related diseases, or worldwide health patient-specific record of risks of disease [25,29,32]. Big data issues such as cardiology [16,22,28,31,34]. About 61% of the literature mentioned this opportunity. http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 7 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al applications aim to make this process more efficient [12]. About previously unpublished. These tables identify challenges and 24% of the literature mentioned this opportunity. opportunities and illustrate their frequency of mention in the literature. This information is helpful to other researchers and Globalization innovators because it provides direction and proper emphasis Big data will actively help in disseminating the knowledge of research effort. The listed challenges and opportunities are acquired from the data collected [15,22,30]. Big data plays an ordered by their frequency found in the literature. active role in leveraging the practices and knowledge not only Limitations regionally but globally [12,15,29]. By globalizing data, it is made more widely accessible and providers may access new A big limitation in this review is the low number of articles information from all regions [22,23,32]. About 24% of the used in the analysis. If we were to do this over again, we would literature mentioned this opportunity. query another database to see whether additional articles were available for analysis. Fraud Detection Selection bias seems to exist in any study. Our control for One of the most significant benefits offered by big data is that selection bias was the initial research up front to agree on a it is instrumental in detecting fraud in an efficient and effective definitive definition of the concept of big data, and our manner [13,23]. For example, the unauthorized use of specific consensus meetings to discuss findings. The consensus meetings user accounts by third parties can be minimized [21]. Only about offered great value to the process because they enabled the 11% of the literature mentioned this opportunity. group to hear the focus of an individual and either provide Health-Threat Detection feedback to confirm the focus or agree that the unique focus Big data offers opportunity for improving capabilities of threat was warranted for all the articles in the review. detection quickly and more accurately. This can be especially Another bias that we discuss regularly is publication bias. beneficial for government use [22]. Big data augments the Journals tend to publish results that are statistically significant, current acquisition of protection against the increasing threats which inherently limits the publication of research that may not of foreign countries, criminals, terrorists, and others. Only 3.6% reach that level. Our control for publication bias was to include of the literature mentioned this opportunity. Google Scholar in our search. Our intent was to identify material Opportunities most often mentioned or discussed were improve in lesser-known journals that might not be indexed in PubMed quality of care (18/28, 64%), managing population health (17/28, (MEDLINE) or CINAHL. 61%), early detection of diseases (17/28, 60.7%), data quality Conclusions structure and accessibility (16/28, 57%), improve decision Big data and the use of advanced analytics have the potential making (11/28, 39.3%), cost reductions (10/28, 36%), to advance the way in which providers leverage technology to patient-centric health care (8/28, 29%), enhancing personalized make informed clinical decisions. However, the vast amounts medicine (6/28, 24%), and globalization (6/28, 24%). The other of information generated annually within health care must be two opportunities each comprised less than 15% of the organized and compartmentalized to enable universal observations. accessibility and transparency between health care organizations. Discussion Our systematic literature review revealed both challenges and opportunities that big data offers to the health care industry. Summary of Evidence The literature mentioned the challenges of data structure and Although the integration of big data is well underway in security in at least 50% of the articles reviewed. The literature industries such as finance and advertising, it has not yet fully also mentioned the opportunities of increased quality, better assimilated into health care. Challenges and opportunities were management of population health, early detection of disease, made quite clear in the articles analyzed in this review. Three and data quality structure and accessibility in at least 50% of of the 4 Vs (volume, velocity, and variety) were consistently the articles reviewed. These findings identify foci for future adhered to. The fourth V, veracity, was found, but rarely listed research. by name. Tables 1 and 2 provide insightful information that is Conflicts of Interest None declared. Multimedia Appendix 1 Summary or relevance of cited work. [PDF File (Adobe PDF File), 33KB-Multimedia Appendix 1] References 1. PRISMA. Welcome to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) website! 2009. URL: http://www.prisma-statement.org/ [accessed 2015-07-30] [WebCite Cache ID 6aPmhFUMM] http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 8 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al 2. McAfee A, Brynjolfsson E. Big data: the management revolution. Harv Bus Rev 2012 Oct;90(10):60-6, 68, 128. [Medline: 23074865] 3. Heudecker N. Hype Cycle for Big Data. Gartner. 2013 Jul 31. URL: https://www.gartner.com/doc/2574616/ hype-cycle-big-data- [accessed 2016-11-08] [WebCite Cache ID 6lsI6Sxxr] 4. Kayyali B, Knott D, Van Kuiken S. The big-data revolution in US health care: accelerating value and innovation. McKinsey & Company. 2013 Apr. URL: https://digitalstrategy.nl/wp-content/uploads/E2-2013. 04-The-big-data-revolution-in-US-health-care-Accelerating-value-and-innovation.pdf [accessed 2016-11-11] [WebCite Cache ID 6lvquouez] 5. Chawla NV, Davis DA. Bringing big data to personalized healthcare: a patient-centered framework. J Gen Intern Med 2013 Sep;28(Suppl 3):S660-S665 [FREE Full text] [doi: 10.1007/s11606-013-2455-8] [Medline: 23797912] 6. US Department of Health and Human Services. Genomics Data Sharing. 2014. URL: https://gds.nih.gov/ 17summary_dbGaP_statistics.html[WebCite Cache ID 6m62Idais] 7. Feldman B, Martin E, Skotnes T. Big data in healthcare hype and hope. GHDonline. 2012 Oct. URL: https://www. ghdonline.org/uploads/big-data-in-healthcare_B_Kaplan_2012.pdf [accessed 2016-11-09] [WebCite Cache ID 6lt9sqaYc] 8. Hillestad R, Bigelow J, Bower A, Girosi F, Meili R, Scoville R, et al. Can electronic medical record systems transform health care? Potential health benefits, savings, and costs. Health Aff (Millwood) 2005;24(5):1103-1117 [FREE Full text] [doi: 10.1377/hlthaff.24.5.1103] [Medline: 16162551] 9. US Department of Health and Human Services. 28. Medicare and Medicaid Programs; Electronic Health Record Incentive Program. US Government Printing Office. Federal Register. 2010 Jul 28. URL: https://www.federalregister.gov/documents/ 2010/07/28/2010-17207/medicare-and-medicaid-programs-electronic-health-record-incentive-program [accessed 2016-11-09] [WebCite Cache ID 6ltJ4cdh3] 10. US Department of Health and Human Services. State Health Information Exchange Cooperative Agreement Program. US Printing Office. HealthIT. 2011. URL: https://www.healthit.gov/policy-researchers-implementers/ state-health-information-exchange [accessed 2016-11-09] [WebCite Cache ID 6ltJbJxRk] 11. Murdoch TB, Detsky AS. The inevitable application of big data to health care. JAMA 2013 Apr 3;309(13):1351-1352. [doi: 10.1001/jama.2013.393] [Medline: 23549579] 12. Jee K, Kim GH. Potentiality of big data in the medical sector: focus on how to reshape the healthcare system. Healthc Inform Res 2013 Jun;19(2):79-85 [FREE Full text] [doi: 10.4258/hir.2013.19.2.79] [Medline: 23882412] 13. Raghupathi W, Raghupathi V. Big data analytics in healthcare: promise and potential. Health Inf Sci Syst 2014;2:3 [FREE Full text] [doi: 10.1186/2047-2501-2-3] [Medline: 25825667] 14. Song TM, Song J, An JY, Hayman LL, Woo JM. Psychological and social factors affecting Internet searches on suicide in Korea: a big data analysis of Google search trends. Yonsei Med J 2014 Jan;55(1):254-263 [FREE Full text] [doi: 10.3349/ymj.2014.55.1.254] [Medline: 24339315] 15. Fernandes L, O'Connor M, Weaver V. Big data, bigger outcomes: healthcare is embracing the big data movement, hoping to revolutionize HIM by distilling vast collection of data for specific analysis. J AHIMA 2012 Oct;83(10):38-43; quiz 44. [Medline: 23061351] 16. Kim T, Park K, Yi S. A Big Data Framework for u-Healthcare Systems Utilizing Vital Signs. Presented at: Computer, Consumer and Control (IS3C), 2014 International Symposium; 10-12 June, 2014; Taichung, Taiwan. IEEE; 2014 Jun 30. [doi: 10.1109/IS3C.2014.135] 17. Augustine D. Leveraging big data analytics and Hadoop in developing India's healthcare service. Int J Comput Applications 2014 Mar;89(16):44-50 [FREE Full text] 18. Jiang P, Winkley J, Zhao C, Munnoch R, Min G, Yang LT. An intelligent information forwarder for healthcare big data systems with distributed wearable sensors. IEEE Systems Journal 2016 Sep;10(3):1147-1159. [doi: 10.1109/JSYST.2014.2308324] 19. Hrovat G, Stiglic G, Kokol P, Ojsteršek M. Contrasting temporal trend discovery for large healthcare databases. Comput Methods Programs Biomed 2014;113(1):251-257. [doi: 10.1016/j.cmpb.2013.09.005] [Medline: 24120407] 20. Baro E, Degoul S, Beuscart R, Chazard E. Toward a literature-driven definition of big data in healthcare. Biomed Res Int 2015;2015:639021 [FREE Full text] [doi: 10.1155/2015/639021] [Medline: 26137488] 21. Naqishbandi T, Imthyaz Sheriff C, Qazi S. Big data, CEP and IoT: redefining holistic healthcare information systems and analytics. Int J Eng Res and Technol 2015;4(1):1-6 [FREE Full text] 22. Hsieh JC, Li AH, Yang CC. Mobile, cloud, and big data computing: contributions, challenges, and new directions in telecardiology. Int J Environ Res Public Health 2013 Nov 13;10(11):6131-6153 [FREE Full text] [doi: 10.3390/ijerph10116131] [Medline: 24232290] 23. Sepulveda MJ. From worker health to citizen health: moving upstream. J Occup Environ Med 2013 Dec;55(12 Suppl):S52-S57 [FREE Full text] [doi: 10.1097/JOM.0000000000000033] [Medline: 24284749] 24. Baker TB, Gustafson DH, Shah D. How can research keep up with eHealth? Ten strategies for increasing the timeliness and usefulness of eHealth research. J Med Internet Res 2014;16(2):e36 [FREE Full text] [doi: 10.2196/jmir.2925] [Medline: 24554442] http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 9 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al 25. Mohr DC, Burns MN, Schueller SM, Clarke G, Klinkman M. Behavioral intervention technologies: evidence review and recommendations for future research in mental health. Gen Hosp Psychiatry 2013;35(4):332-338 [FREE Full text] [doi: 10.1016/j.genhosppsych.2013.03.008] [Medline: 23664503] 26. Mancini M. Exploiting big data for improving healthcare services. J e-Learning Knowledge Soc 2014;10(2):1-11 [FREE Full text] 27. Youssef AE. A framework for secure healthcare systems based on big data analytics in mobile cloud computing environments. Int J Ambient Syst Appl 2014;2(2):1-11. [doi: 10.5121/ijasa.2014.2201] 28. Schilsky RL, Michels DL, Kearbey AH, Yu PP, Hudis CA. Building a rapid learning health care system for oncology: the regulatory framework of CancerLinQ. J Clin Oncol 2014 Aug 1;32(22):2373-2379 [FREE Full text] [doi: 10.1200/JCO.2014.56.2124] [Medline: 24912897] 29. Moore P, Thomas A, Tadros G, Xhafa F, Barolli L. Detection of the onset of agitation in patients with dementia: real-time monitoring and the application of big-data solutions. IJSSC 2013;3(3):136-154. [doi: 10.1504/IJSSC.2013.056405] 30. Wang P, Chen Z. Traditional Chinese medicine ZHENG and OMICS convergence: a systems approach to post-genomics medicine in a global world. OMICS 2013 Sep;17(9):451-459. [doi: 10.1089/omi.2012.0057] [Medline: 23837436] 31. Lamarche-Vadel A, Pavillon G, Aouba A, Johansson LA, Meyer L, Jougla E, et al. Automated comparison of last hospital main diagnosis and underlying cause of death ICD10 codes, France, 2008-2009. BMC Med Inform Decis Mak 2014;14:44 [FREE Full text] [doi: 10.1186/1472-6947-14-44] [Medline: 24898538] 32. Howren MB, Vander Weg MW, Wolinsky FD. Computerized cognitive training interventions to improve neuropsychological outcomes: evidence and future directions. J Comp Eff Res 2014 Mar;3(2):145-154. [doi: 10.2217/cer.14.6] [Medline: 24645688] 33. Wlodarczyk TW, Hacker TJ. Current trends in predictive analytics of big data. Int J Big Data Intel 2014;1(3):172-122. [doi: 10.1504/IJBDI.2014.066326] 34. Sengupta PP. Intelligent platforms for disease assessment: novel approaches in functional echocardiography. JACC Cardiovasc Imaging 2013 Nov;6(11):1206-1211 [FREE Full text] [doi: 10.1016/j.jcmg.2013.09.003] [Medline: 24229773] 35. Issa NT, Byers SW, Dakshanamurthy S. Big data: the next frontier for innovation in therapeutics and healthcare. Expert Rev Clin Pharmacol 2014 May;7(3):293-298 [FREE Full text] [doi: 10.1586/17512433.2014.905201] [Medline: 24702684] 36. Beveridge R, Fox J, Higgins SA, Kohn M, Mahoney JJ, Newcomer LN, et al. Roundtable—the changing oncology landscape: evolution or revolution? J Natl Compr Canc Netw 2013 May;11(5 Suppl):636-638. [Medline: 23704232] 37. Kaushik K, Kapoor D, Varadharajan V, Nallusamy R. Disease management: clustering-based disease prediction. Int J Collaborative Enterprise 2014;4(1-2):69-82. [doi: 10.1504/IJCENT.2014.065047] Abbreviations ARRA: American Recover and Reinvestment Act EHR: electronic health record HIE: Health Information Exchange HIPAA: Health Insurance Portability and Accountability Act HITECH: Health Information Technology for Economic and Clinical Health MeSH: Medical Subject Headings PRISMA: Preferred Reporting Items for Systematic Reviews and Meta-analysis Edited by G Eysenbach; submitted 19.11.15; peer-reviewed by J Bian, D Maslove, MA Mayer, S Seevanayanagam, L Toldo; comments to author 03.01.16; revised version received 27.07.16; accepted 28.09.16; published 21.11.16 Please cite as: Kruse CS, Goswamy R, Raval Y, Marawi S JMIR Med Inform 2016;4(4):e38 URL: http://medinform.jmir.org/2016/4/e38/ doi: 10.2196/medinform.5359 PMID: 27872036 ©Clemens Scott Kruse, Rishi Goswamy, Yesha Raval, Sarah Marawi. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 21.11.2016. This is an open-access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 10 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al bibliographic information, a link to the original publication on http://medinform.jmir.org/, as well as this copyright and license information must be included. http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 11 (page number not for citation purposes) XSL FO RenderX http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png JMIR Medical Informatics JMIR Publications

Challenges and Opportunities of Big Data in Health Care: A Systematic Review

Loading next page...
 
/lp/jmir-publications/challenges-and-opportunities-of-big-data-in-health-care-a-systematic-fFwE0TlCLN

References (40)

Publisher
JMIR Publications
Copyright
Copyright © The Author(s). Licensed under Creative Commons Attribution cc-by 4.0
ISSN
2291-9694
DOI
10.2196/medinform.5359
Publisher site
See Article on Publisher Site

Abstract

Background: Big data analytics offers promise in many business sectors, and health care is looking at big data to provide answers to many age-related issues, particularly dementia and chronic disease management. Objective: The purpose of this review was to summarize the challenges faced by big data analytics and the opportunities that big data opens in health care. Methods: A total of 3 searches were performed for publications between January 1, 2010 and January 1, 2016 (PubMed/MEDLINE, CINAHL, and Google Scholar), and an assessment was made on content germane to big data in health care. From the results of the searches in research databases and Google Scholar (N=28), the authors summarized content and identified 9 and 14 themes under the categories Challenges and Opportunities, respectively. We rank-ordered and analyzed the themes based on the frequency of occurrence. Results: The top challenges were issues of data structure, security, data standardization, storage and transfers, and managerial skills such as data governance. The top opportunities revealed were quality improvement, population management and health, early detection of disease, data quality, structure, and accessibility, improved decision making, and cost reduction. Conclusions: Big data analytics has the potential for positive impact and global implications; however, it must overcome some legitimate obstacles. (JMIR Med Inform 2016;4(4):e38) doi: 10.2196/medinform.5359 KEYWORDS big data; analytics; health care; human genome; electronic medical record Big data is commonly defined through the 4 Vs: volume (scale Introduction or quantity of data), velocity (speed and analysis of real-time or near-real-time data), variety (different forms of data, often Rationale from disparate data sources), and veracity (quality assurance of Big data analytics offers promise in many business sectors, and the data). The first 3 Vs are found in most literature [2,3], and health care is looking at big data to provide answers to many the fourth V is a goal [4]. age-related issues, particularly dementia and chronic disease As of 2012, about 2.5 exabytes of data are created each day; management. This systematic review explores the depth of big Walmart can collect up to 2.5 petabytes of customer-related data analytics since 2010 and identifies both challenges and data per hour [2]. The industry of health care produces and opportunities associated with big data in health care. The review collects data at a staggering speed, but different electronic health follows the standard set by Preferred Reporting Items for records (EHRs) collect data in different structures: structured, Systematic Reviews and Meta-analysis (2009) [1]. http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 1 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al unstructured, and semistructured. This variety can pose difficulty convert data into knowledge. Health care needs to follow their when seeking veracity or quality assurance of the data. The lead so that decisions regarding organizational objectives and EHRs can provide a rich source of data, ripe for analysis to goals can be met [4,11,12]. This evolutionary process of data increase our understanding of disease mechanisms, as well as management is collectively known as big data, and it is essential better and personalized health care, but the data structures pose to the future of adoption and management of health information a problem to standard means of analysis [5]. technology [13]. There are several large sources for big data in health care: Objectives genomics, EHR, medical monitoring devices, wearable video The purpose of this systematic review is to objectively review devices, and health-related mobile phone apps. Approximately articles and studies published in academic journals in order to 483 studies on genomics are registered with the US Department compile a list of challenges and opportunities faced by big data of Health and Human Services; these studies are being analytics in health care in the United States. Particular emphasis conducted in 9 countries, and they all use portions of the data was paid to age-related applications of big data. from the Human Genome Project [6]. The EHR, being adopted in many countries, offers a source of data the depth of which is Methods almost inconceivable. About 500 petabytes of data was generated by the EHR in 2012, and by 2020, the data will reach Eligibility Criteria 25,000 petabytes [7]. The EHR can collect data from other Articles and studies were eligible for analysis if they were monitoring devices, but the continuous data streams are not published between 2010 and 2015, published in academic consistently saved in the longitudinal record. journals, and published in English. The researchers chose a The decrease in the cost of storage has enabled an exponential range from 2010 to 2015 for two reasons: HITECH was passed distribution of data collection, but the ability to analyze this in 2009, and it appeared that a blossom of research and other quantity of data is the center of gravity for “big data” in health articles seemed to occur in 2010. We focused on academic care. In the United States, financial incentives offered for the journals for their peer-review quality and to decrease the chance “meaningful use” of health information technology has spurred of selecting something about big data published from a growth in the adoption of the EHR and other enabling noncredible source. health-related technology since 2009. Information Sources Health information systems show great potential in improving A combination of key terms from Medical Subject Headings the efficiency in the delivery of care, a reduction in overall costs (MeSH) and Boolean operators were combined and used in 2 to the health care system, as well as a marked increase in patient common research databases, CINAHL and PubMed, and outcomes [8]. The US government has allocated billions of combined with a general search from Google Scholar (see Figure dollars to help the country’s health care market realize some of 1) in January 2016. these efficiencies and savings. Specific provisions of the Health These terms were chosen not only because they are the focus Information Technology for Economic and Clinical Health of the review, but also because they were identified in the initial (HITECH), part of the American Recovery and Reinvestment research into the definition of big data. Act, acknowledge the importance of IT in the delivery of health care within the United States [9]. The Act allocates Search approximately US $17.2 billion in incentives for the adoption The following search string was used in all 3 searches: ((“big and meaningful use of health information technology, part of data” AND healthcare) OR (“big data” AND “health care”)). which involves the participation in the electronic exchange of This search string was used in CINAHL, PubMed (MEDLINE), clinical information. In 2010, the Congress passed the Health and Google Scholar. In the 2 research databases, our team was Information Exchange (HIE) Challenge Grant Program, which able to restrict the search to academic journals (including other contributed about US $547.7 million to state HIE programs systematic reviews). MEDLINE was excluded in CINAHL [10]. because it was already captured in PubMed. Google Scholar With the implementation of this legislation as well as the creates difficulty for searches because of its severe limit of technologies associated with it, it is imperative to effectively filters typically associated with academic research. The initial organize and process the ever-increasing quantity of data that 13,935 results were limited by restricting dates to the last 5 is digitally collected and stored within health care organizations. years, limiting results to academic journals and MEDLINE, and Other industries such as astronomy, retail, search engines, and in Google Scholar by restricting the keyword search to titles. politics have developed advanced data-handling capabilities to The result from the filters ended with 121 articles to review. http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 2 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al Figure 1. Literature review process with inclusion and exclusion criteria. observations. These themes were tabulated and counted for Study Selection additional analysis. Through group research and a series of consensus meetings, researchers were trained to identify articles germane to this Results review and to recommend elimination of all others. A shared spreadsheet was used by the research team to parse through the Study Selection list of articles. Researchers read all articles in their entirety. A As depicted in Figure 1, 935 articles resulted from the initial total of 97 articles were eliminated due to various exclusion search. Filters such as data published (2010-2015), academic criteria (not germane to big data or health care, editorial only, journals, and English language were implemented to reduce the not an academic journal, or duplicate from another search), and range to what was being studied. Reviewers agreed to eliminate 4 additional articles were identified from the references of the editorials and focus on those articles that studied big data, as 24 that remained. The group of reviewers made these rejections described in the Introduction section of this manuscript. At the or additional recommendations through a series of consensus end of the search process, only 28 remained. The articles meetings where we met to discuss their recommendations and reviewed for this study ranged from 2012 to 2015. The majority consensus was reached through discussion. A total of 28 articles of the literature chosen for this paper was published in 2014 remained in the final review. (15/28, 54%), and a minority was published in 2015 (2/28, 7%); the latter was most likely due to the early part of the year when Data Collection Process and Identification of Summary the search was conducted. Measures Each article was reviewed by at least two authors to identify Synthesis of Results the relevant points. All reviewers used a spreadsheet template Multiple reviewers read each article in its entirety. Articles were to summarize their key observations from each article. One team included or excluded based on the criteria illustrated in Figure member combined the spreadsheets into one and shared it once 1. All articles included in the analysis were sorted by date and again. Reviewers held one more consensus meeting to discuss are listed in Multimedia Appendix 1. their findings. From this meeting, trends were identified, and A study catalog number was assigned to each article to simplify from those trends, inferences were made. the analysis. Researchers summarized the main points of each Additional Analysis article for further analysis. From the list of observations, reviewers were able to identify Additional Analysis some common threads that emerged as challenges and Through the combination of observations, reviewers identified opportunities in health care that permeated multiple articles. common threads (challenges and opportunities) and themes Separate tables were created to group the threads, and from each from each thread. Themes were organized into affinity diagrams of these tables, common themes were identified. These common (Tables 1 and 2), compared, and discussed among researchers. themes only emerged when reviewers combined their http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 3 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al lack of skill of data analysts, inaccuracies in data, regulatory Challenges for Big Data in Health Care compliance, and real-time analytics. Examples for each theme Nine themes emerged under the category of challenges: data are provided in Table 1. A total of 60 observations were made structure, security, data standardization, data storage and for challenges. transfers, managerial issues such as governance and ownership, Table 1. Themes associated with challenges for big data in health care. Themes Examples Number of articles Articles themes appeared in % of total articles (n) (N=28) Data structure Fragmented data 17 1, 2, 7-9, 12, 14-19, 22, 25-28 61% Incompatible formats Heterogeneous data   Raw and unstructured datasets   Large volumes   High variety and velocity   Lack of transparency   Security Privacy 14 2, 4, 7-9, 12, 13, 17, 21, 22, 25- 50% Confidentiality Data duplication Integrity Data standardization Limited Interoperability 11 4, 5, 7-9, 11, 12, 15, 16, 22, 25 39% Data acquisition and cleansing Global sharing Terminology Language barriers Storage and transfers Expensive to store 8 1, 4, 7, 12, 22, 26, 28 28% Transfer from one place to other Store electronic data Securely extract, transmit, and process Managerial issues Governance issues 4 2, 8, 14, 22 14% Ownership issues Lack of skill Untrained workers 3 5, 9, 14 11% Inaccuracies Inconsistences 1 9 4% Lack of precision Data timeliness Regulatory compliance Legal concerns 1 13 4% Real-time analytics Real-time analytics 1 9 4% The 4 Vs appear in multiple places under the Challenges Data Structure Issues category. Volume and variety are seen by name under the theme Issues related to data structure were addressed in the majority of Data structure. Variety is also implied in the same theme, of the papers reviewed for this study. It is essential that the key but listed as Incompatible formats, as well as Raw and functions of data processing are supported by the applications unstructured datasets. Variety can also be inferred from the of big data [13]. Big data applications should be user-friendly, theme of Data standardization, listed as Limited interoperability. transparent, and menu-driven [13,14]. The majority of data in Velocity is seen in the theme Real-time analytics. Veracity is health care is unstructured, such as from natural language seen under the theme of Data Standardization, but listed as Data processing [12]. It is often fragmented, dispersed, and rarely acquisition and cleansing, Terminology, and Language barriers. standardized [12,13,15-21]. It is no secret that the EHRs do not It is also inferred in the theme Inaccuracies listed as share well across organizational lines, but with unstructured Inconsistencies and Lack of precision. data, even within the same organization, unstructured data is http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 4 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al difficult to aggregate and analyze. It is no wonder that 61% of Managerial Issues the articles analyzed listed this as a concern; big data analytics Data governance will need to move up on the priority list of will need to address this large challenge. organizations, and it should be treated as a primary asset instead of a by-product of the business [15]. Data ownership and data Research data within the health care sector is more stewardship should create new roles in business that consider heterogeneous than the research data produced within other big data analytics [15], and new partnerships will need to be research fields [3,5,12]. Data from both research and public brokered when sharing data [23,24,27]. About 14% of the health is often produced in large volumes [15,22,23]. Another literature mentioned this point. structure-related issue results from the changing health care fee-for-service care model [4]. Finally, big data will need to Lack of Appropriate Skills address issues with the transparency of metadata [16,24]. It is important that health care workers are also kept up to date Security Issues with the use of constantly changing technology, techniques, and a constantly moving standard of care [5,24]. Due to the constant There are considerable privacy concerns regarding the use of evolution of technology, there exist populations of individuals big data analytics, specifically in health care given the enactment lacking specific skills; as such this is also a significant of Health Insurance Portability and Accountability Act(HIP   AA) continuing barrier to the implementation of big data [12]. About legislation [15]. Data that is made available on open source is 11% of the literature expressed this challenge. freely available and, hence, highly vulnerable [12,13,18,20]. Further, due to the sensitivity of health care data, there are Inaccuracies (Veracity) significant concerns related to confidentiality [25,26]. Moreover, Self-reported data is extensively used in health care, and so it this information is centralized, and as such, it is highly is crucial that the data collected in this manner be consistent vulnerable to attacks [25]. For these reasons, enabling privacy [12]. Keeping information current as well as accurate is another and security is very important, as illustrated by a frequency of challenge of data collection. Precision of data is also needed to mention in 50% of the literature reviewed. provide accurate information [12]. Only 4% of the literature Data Standardization Issues mentioned this challenge. Although the EHRs share data within the same organization, Regulatory Compliance Issues intra-organizational, EHR platforms are fragmented, at best. Health care organizations should be aware of the various legal Data is stored in formats that are not compatible with all issues that can surface in the process of managing high volume applications and technologies [13,22]. This lack of data of sensitive information. Organizations implementing big data standardization also causes problems in transfer of that data analytics as a part of their information systems will have to [5,25]. It complicates data acquisition and cleansing [5,25,26]. comply with a significant amount of standards and regulatory About 39% of the literature mentioned this challenge. compliance issues specific to health care [28]. Only 4% of the Limited interoperability poses a large challenge for big data, as literature mentioned this challenge. data is rarely standardized [12,13,16,22]. This leaves big data Real-Time Analytics (Velocity) to face issues related to the acquisition and cleansing of data One of the key requirements in health care is to be able to utilize into a standardized format to enable analysis and global sharing big data in real time. Real time is defined by enabling the use [13,17,23,25,27]. With globalization of data, big data will have of applications such as cloud computing to view said data in to deal with a variety of standards, barriers of language, and real time. The use of these technologies leads to issues of different terminologies. security and privacy within patient information [12]. Only 4% Storage and Transfers of the literature mentioned this challenge. Challenges most often Data generation is inexpensive compared with the storage and mentioned or discussed were data structure (17/28, 61%), transfer of the same. Once data is generated, the costs associated security (14/28, 50%), data standardization (11/28, 39%), and with securing and storing them remain high [25]. Costs are also data storage and transfers (8/28, 29%). The other five challenges incurred with transferring data from one place to another as well comprised less than 15% of the observations. as analyzing it [14,21,22]. Some researchers have been able to Opportunities for Big Data in Health Care combine the themes of Data structure and Storage and transfers Fourteen themes emerged under the category of opportunities: when they illustrate how structured data can be easily stored, improve quality of care, managing population health, early queried, analyzed, and so forth, but unstructured data is not as detection of diseases, data quality, structure, and accessibility, easily manipulated [13]. Cloud-based health information improve decision making, cost reduction, patient-centric care, technology has the additional layer of security associated with enhances personalized medicine, globalization, fraud detection, the extraction, transformation, and loading of patient-related and health-threat detection. Examples of each theme are listed data [27]. The use of big data should address issues related to in Table 2. A total of 113 observations were made for increased expenditures as well as the transmittance of secure opportunities. or insecure information. About 28% of the literature mentioned this challenge. http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 5 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al Table 2. Themes that emerged from the opportunities for big data in health care. Themes Examples Number of articles Articles themes appeared in % of total articles (n) (N=28) Improve quality of care Improve efficiency 18 2, 4, 5, 6, 8-13, 18-20, 22-25, 64% Improve outcomes Reduce waste Reduce readmissions Increased productivity and performance Risk reduction Process optimization Managing population Managing population health 17 2, 5, 8-10, 12-14, 16, 18-20, 23, 61% health 25, 26, 28 Early detection of diseases Predicting epidemics 17 2, 4, 5, 7-13, 15, 18-20, 23, 24, 61% Disease monitoring Health tracking Adopt and track healthier behaviors Predicting patient vulnerability Improved treatments Data quality, structure, and Large volumes 16 2, 4, 6, 9, 11, 12, 16, 18, 20- 23, 57% accessibility 25-28 Wide variety Creating transparency High-velocity capture Access to primary data Reusable data Weed out unwanted data Open source—free access Improve decision making Evidence-based medicine 11 2,-4, 7, 9, 12, 16, 20, 22, 23, 24 39% New treatment guidelines Accuracy in information Cost reduction Inexpensive 10 1, 3, 4, 7, 9, 11, 12, 14, 16, 18 36% Reducing health care spending Patient-centric health care Empowering patients 8 2, 3, 5, 12, 14, 20, 22, 24 29% Patients making informed decisions Increased communication Enhancing personalized Targeted approach 6 4-6, 24, 25, 28 24% medicine Globalization Widely accessible 6 2, 6-8, 10, 20 24% Global sharing Leveraging knowledge and practices Knowledge dissemination Fraud detection Fraud detection 3 8, 12, 28 11% Health-threat detection Health-threat detection 1 7 4% Despite the challenges that big data needs to overcome, the care industry (patient, provider, and payer). More than 64% of advanced analytics that are promised through big data offer the articles analyzed focused on quality improvement and more tremendous opportunities for most stakeholders in the health than 60% on managing population health and early detection http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 6 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al of diseases through big data analytics. If even some of the Data Quality, Structure, and Accessibility opportunities of big data are realized, they can radically change Literature suggests that big data enables rapid capture of data patient outcomes and the way decisions are made by providers, and the conversion of primary, raw and unstructured data into and help solve some macro-level issues related to health care meaningful information [15,17,31,34]. New knowledge can within countries such as the United States (cost, quality, and then be generated from high volumes of effective data, enabling access). reuse of the data [15,20,21,32,33]. Open-source technology increases accessibility to and transparency of the data Improve Quality of Care [12,25,26,30,35]. Finally, data quality can be maintained using Big data has the potential and ability to improve the quality and analytics to get rid of unnecessary information [27]. About 57% efficiency of care [5,15,23,29-31]. Big data offers an ability to of the literature mentioned this opportunity. predict outcomes using the available primary or historical data and provide proof of benefit that could change established, Improve Decision Making industry-wide standards of care [25,28]. Leveraging technology Big data enables appropriate use of evidence-based medicine at the patient end can also help with medication adherence and helps health care providers make more informed decisions [23,25]. This will most certainly play an important role in [12,13,15,22]. This, in turn, improves the quality of care improving outcomes [2,13] and improve the health-related provided to the patients [16,31,36]. Remote monitoring, patient quality of life [20,26,32]. profile analytics, and genomic analytics are examples of other applications that influence the decision-making process [13,25]. Quality of care will also be improved by reducing waste of information, which will reduce inefficiencies [13,26]. This will Decision-making process can be highly optimized by the also assist in analyzing real-time resource utilization productivity availability of accurate and up-to-date information, as decision [13]. Quality can also be improved by reducing the rates of making is influenced by the generation of new practices and readmissions, increasing operational efficiencies, and improving treatment guidelines within clinical research. Allowing big data performance [5,12,13]. About 64% of the literature mentioned to influence decision making will allow for a faster and simpler this opportunity. process. This is done by either supporting or replacing human decision making. About 39% of the literature mentioned this Managing Population Health opportunity. The management of population health and the early detection of diseases were topics that the authors thought would have Cost Reduction highly similar results after the analysis. Although there was a The literature suggests that the decrease in cost of the elements large overlap between the 2 themes, there was also specific of computing, such as storage and processing, leads to a decrease variation between them. So, the researchers chose to keep them in the cost of data-intensive tasks [2,13]. This pass-through of separate. The theme of managing population health focused on savings will be seen across the spectrum of medicine [24,36] special populations rather than public health. and the health care workforce [25]. Savings will be realized through more cost-effective treatments and monitoring to Big data analytics define populations at a finer level of improve medication adherence [25,31] and through the reduction granularity than has ever been previously achieved [5,14,15,33]. of costly transportation costs, as is experienced in cardiology It can help in managing the overall health of a population as [12,17,22,34]. About 36% of the literature mentioned this well as specific individual health [13,26,29]. Big data can enable opportunity. population health management from a local or global perspective [31,34]. This capability becomes more salient from the global Patient-Centric Care perspective when considering the aging of the population and Increasing the use of technology is slowly changing the direction age-related health issues shared by many populations and of the health care sector from disease-centric care toward subpopulations, many of which are underserved patient-centric care [5]. Big data will play a significant role in [17,19,21,24,28,32]. About 61% of the literature mentioned this this transformation [37]. It will allow the information to be opportunity. delivered to patients directly and empower them to play an Early Detection of Diseases active part in their care [5,15,27]. When patients are provided with the appropriate information, it will influence their decision Big data allows for the early detection of diseases, which aids making and allow them to make informed decisions [13,24]. in clinical objectives related to achieving improved treatments Informed decisions will also be influenced by increased and higher patient outcomes [12,13,15,22,25]. It is in this area communication between patients, providers, as well as their that the authors found great promise in age-related illness and communities [5,24,32,36]. About 29% of the literature disease. Along with early detection, big data analytics can also mentioned this opportunity. help in the prevention of a wide range of deadly illnesses and personalized disease management and monitoring Enhancing Personalized Medicine [5,19,21,22,29,34]. It enables providers to track healthy With the use of big data, the objectives of personalized medicine behaviors and helps patients in monitoring their respective can be translated into clinical practice [5,25,30]. Access to and conditions [25,32,33]. This capability holds great potential when processing of large volumes of data should enable a personalized faced with either age-related diseases, or worldwide health patient-specific record of risks of disease [25,29,32]. Big data issues such as cardiology [16,22,28,31,34]. About 61% of the literature mentioned this opportunity. http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 7 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al applications aim to make this process more efficient [12]. About previously unpublished. These tables identify challenges and 24% of the literature mentioned this opportunity. opportunities and illustrate their frequency of mention in the literature. This information is helpful to other researchers and Globalization innovators because it provides direction and proper emphasis Big data will actively help in disseminating the knowledge of research effort. The listed challenges and opportunities are acquired from the data collected [15,22,30]. Big data plays an ordered by their frequency found in the literature. active role in leveraging the practices and knowledge not only Limitations regionally but globally [12,15,29]. By globalizing data, it is made more widely accessible and providers may access new A big limitation in this review is the low number of articles information from all regions [22,23,32]. About 24% of the used in the analysis. If we were to do this over again, we would literature mentioned this opportunity. query another database to see whether additional articles were available for analysis. Fraud Detection Selection bias seems to exist in any study. Our control for One of the most significant benefits offered by big data is that selection bias was the initial research up front to agree on a it is instrumental in detecting fraud in an efficient and effective definitive definition of the concept of big data, and our manner [13,23]. For example, the unauthorized use of specific consensus meetings to discuss findings. The consensus meetings user accounts by third parties can be minimized [21]. Only about offered great value to the process because they enabled the 11% of the literature mentioned this opportunity. group to hear the focus of an individual and either provide Health-Threat Detection feedback to confirm the focus or agree that the unique focus Big data offers opportunity for improving capabilities of threat was warranted for all the articles in the review. detection quickly and more accurately. This can be especially Another bias that we discuss regularly is publication bias. beneficial for government use [22]. Big data augments the Journals tend to publish results that are statistically significant, current acquisition of protection against the increasing threats which inherently limits the publication of research that may not of foreign countries, criminals, terrorists, and others. Only 3.6% reach that level. Our control for publication bias was to include of the literature mentioned this opportunity. Google Scholar in our search. Our intent was to identify material Opportunities most often mentioned or discussed were improve in lesser-known journals that might not be indexed in PubMed quality of care (18/28, 64%), managing population health (17/28, (MEDLINE) or CINAHL. 61%), early detection of diseases (17/28, 60.7%), data quality Conclusions structure and accessibility (16/28, 57%), improve decision Big data and the use of advanced analytics have the potential making (11/28, 39.3%), cost reductions (10/28, 36%), to advance the way in which providers leverage technology to patient-centric health care (8/28, 29%), enhancing personalized make informed clinical decisions. However, the vast amounts medicine (6/28, 24%), and globalization (6/28, 24%). The other of information generated annually within health care must be two opportunities each comprised less than 15% of the organized and compartmentalized to enable universal observations. accessibility and transparency between health care organizations. Discussion Our systematic literature review revealed both challenges and opportunities that big data offers to the health care industry. Summary of Evidence The literature mentioned the challenges of data structure and Although the integration of big data is well underway in security in at least 50% of the articles reviewed. The literature industries such as finance and advertising, it has not yet fully also mentioned the opportunities of increased quality, better assimilated into health care. Challenges and opportunities were management of population health, early detection of disease, made quite clear in the articles analyzed in this review. Three and data quality structure and accessibility in at least 50% of of the 4 Vs (volume, velocity, and variety) were consistently the articles reviewed. These findings identify foci for future adhered to. The fourth V, veracity, was found, but rarely listed research. by name. Tables 1 and 2 provide insightful information that is Conflicts of Interest None declared. Multimedia Appendix 1 Summary or relevance of cited work. [PDF File (Adobe PDF File), 33KB-Multimedia Appendix 1] References 1. PRISMA. Welcome to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) website! 2009. URL: http://www.prisma-statement.org/ [accessed 2015-07-30] [WebCite Cache ID 6aPmhFUMM] http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 8 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al 2. McAfee A, Brynjolfsson E. Big data: the management revolution. Harv Bus Rev 2012 Oct;90(10):60-6, 68, 128. [Medline: 23074865] 3. Heudecker N. Hype Cycle for Big Data. Gartner. 2013 Jul 31. URL: https://www.gartner.com/doc/2574616/ hype-cycle-big-data- [accessed 2016-11-08] [WebCite Cache ID 6lsI6Sxxr] 4. Kayyali B, Knott D, Van Kuiken S. The big-data revolution in US health care: accelerating value and innovation. McKinsey & Company. 2013 Apr. URL: https://digitalstrategy.nl/wp-content/uploads/E2-2013. 04-The-big-data-revolution-in-US-health-care-Accelerating-value-and-innovation.pdf [accessed 2016-11-11] [WebCite Cache ID 6lvquouez] 5. Chawla NV, Davis DA. Bringing big data to personalized healthcare: a patient-centered framework. J Gen Intern Med 2013 Sep;28(Suppl 3):S660-S665 [FREE Full text] [doi: 10.1007/s11606-013-2455-8] [Medline: 23797912] 6. US Department of Health and Human Services. Genomics Data Sharing. 2014. URL: https://gds.nih.gov/ 17summary_dbGaP_statistics.html[WebCite Cache ID 6m62Idais] 7. Feldman B, Martin E, Skotnes T. Big data in healthcare hype and hope. GHDonline. 2012 Oct. URL: https://www. ghdonline.org/uploads/big-data-in-healthcare_B_Kaplan_2012.pdf [accessed 2016-11-09] [WebCite Cache ID 6lt9sqaYc] 8. Hillestad R, Bigelow J, Bower A, Girosi F, Meili R, Scoville R, et al. Can electronic medical record systems transform health care? Potential health benefits, savings, and costs. Health Aff (Millwood) 2005;24(5):1103-1117 [FREE Full text] [doi: 10.1377/hlthaff.24.5.1103] [Medline: 16162551] 9. US Department of Health and Human Services. 28. Medicare and Medicaid Programs; Electronic Health Record Incentive Program. US Government Printing Office. Federal Register. 2010 Jul 28. URL: https://www.federalregister.gov/documents/ 2010/07/28/2010-17207/medicare-and-medicaid-programs-electronic-health-record-incentive-program [accessed 2016-11-09] [WebCite Cache ID 6ltJ4cdh3] 10. US Department of Health and Human Services. State Health Information Exchange Cooperative Agreement Program. US Printing Office. HealthIT. 2011. URL: https://www.healthit.gov/policy-researchers-implementers/ state-health-information-exchange [accessed 2016-11-09] [WebCite Cache ID 6ltJbJxRk] 11. Murdoch TB, Detsky AS. The inevitable application of big data to health care. JAMA 2013 Apr 3;309(13):1351-1352. [doi: 10.1001/jama.2013.393] [Medline: 23549579] 12. Jee K, Kim GH. Potentiality of big data in the medical sector: focus on how to reshape the healthcare system. Healthc Inform Res 2013 Jun;19(2):79-85 [FREE Full text] [doi: 10.4258/hir.2013.19.2.79] [Medline: 23882412] 13. Raghupathi W, Raghupathi V. Big data analytics in healthcare: promise and potential. Health Inf Sci Syst 2014;2:3 [FREE Full text] [doi: 10.1186/2047-2501-2-3] [Medline: 25825667] 14. Song TM, Song J, An JY, Hayman LL, Woo JM. Psychological and social factors affecting Internet searches on suicide in Korea: a big data analysis of Google search trends. Yonsei Med J 2014 Jan;55(1):254-263 [FREE Full text] [doi: 10.3349/ymj.2014.55.1.254] [Medline: 24339315] 15. Fernandes L, O'Connor M, Weaver V. Big data, bigger outcomes: healthcare is embracing the big data movement, hoping to revolutionize HIM by distilling vast collection of data for specific analysis. J AHIMA 2012 Oct;83(10):38-43; quiz 44. [Medline: 23061351] 16. Kim T, Park K, Yi S. A Big Data Framework for u-Healthcare Systems Utilizing Vital Signs. Presented at: Computer, Consumer and Control (IS3C), 2014 International Symposium; 10-12 June, 2014; Taichung, Taiwan. IEEE; 2014 Jun 30. [doi: 10.1109/IS3C.2014.135] 17. Augustine D. Leveraging big data analytics and Hadoop in developing India's healthcare service. Int J Comput Applications 2014 Mar;89(16):44-50 [FREE Full text] 18. Jiang P, Winkley J, Zhao C, Munnoch R, Min G, Yang LT. An intelligent information forwarder for healthcare big data systems with distributed wearable sensors. IEEE Systems Journal 2016 Sep;10(3):1147-1159. [doi: 10.1109/JSYST.2014.2308324] 19. Hrovat G, Stiglic G, Kokol P, Ojsteršek M. Contrasting temporal trend discovery for large healthcare databases. Comput Methods Programs Biomed 2014;113(1):251-257. [doi: 10.1016/j.cmpb.2013.09.005] [Medline: 24120407] 20. Baro E, Degoul S, Beuscart R, Chazard E. Toward a literature-driven definition of big data in healthcare. Biomed Res Int 2015;2015:639021 [FREE Full text] [doi: 10.1155/2015/639021] [Medline: 26137488] 21. Naqishbandi T, Imthyaz Sheriff C, Qazi S. Big data, CEP and IoT: redefining holistic healthcare information systems and analytics. Int J Eng Res and Technol 2015;4(1):1-6 [FREE Full text] 22. Hsieh JC, Li AH, Yang CC. Mobile, cloud, and big data computing: contributions, challenges, and new directions in telecardiology. Int J Environ Res Public Health 2013 Nov 13;10(11):6131-6153 [FREE Full text] [doi: 10.3390/ijerph10116131] [Medline: 24232290] 23. Sepulveda MJ. From worker health to citizen health: moving upstream. J Occup Environ Med 2013 Dec;55(12 Suppl):S52-S57 [FREE Full text] [doi: 10.1097/JOM.0000000000000033] [Medline: 24284749] 24. Baker TB, Gustafson DH, Shah D. How can research keep up with eHealth? Ten strategies for increasing the timeliness and usefulness of eHealth research. J Med Internet Res 2014;16(2):e36 [FREE Full text] [doi: 10.2196/jmir.2925] [Medline: 24554442] http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 9 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al 25. Mohr DC, Burns MN, Schueller SM, Clarke G, Klinkman M. Behavioral intervention technologies: evidence review and recommendations for future research in mental health. Gen Hosp Psychiatry 2013;35(4):332-338 [FREE Full text] [doi: 10.1016/j.genhosppsych.2013.03.008] [Medline: 23664503] 26. Mancini M. Exploiting big data for improving healthcare services. J e-Learning Knowledge Soc 2014;10(2):1-11 [FREE Full text] 27. Youssef AE. A framework for secure healthcare systems based on big data analytics in mobile cloud computing environments. Int J Ambient Syst Appl 2014;2(2):1-11. [doi: 10.5121/ijasa.2014.2201] 28. Schilsky RL, Michels DL, Kearbey AH, Yu PP, Hudis CA. Building a rapid learning health care system for oncology: the regulatory framework of CancerLinQ. J Clin Oncol 2014 Aug 1;32(22):2373-2379 [FREE Full text] [doi: 10.1200/JCO.2014.56.2124] [Medline: 24912897] 29. Moore P, Thomas A, Tadros G, Xhafa F, Barolli L. Detection of the onset of agitation in patients with dementia: real-time monitoring and the application of big-data solutions. IJSSC 2013;3(3):136-154. [doi: 10.1504/IJSSC.2013.056405] 30. Wang P, Chen Z. Traditional Chinese medicine ZHENG and OMICS convergence: a systems approach to post-genomics medicine in a global world. OMICS 2013 Sep;17(9):451-459. [doi: 10.1089/omi.2012.0057] [Medline: 23837436] 31. Lamarche-Vadel A, Pavillon G, Aouba A, Johansson LA, Meyer L, Jougla E, et al. Automated comparison of last hospital main diagnosis and underlying cause of death ICD10 codes, France, 2008-2009. BMC Med Inform Decis Mak 2014;14:44 [FREE Full text] [doi: 10.1186/1472-6947-14-44] [Medline: 24898538] 32. Howren MB, Vander Weg MW, Wolinsky FD. Computerized cognitive training interventions to improve neuropsychological outcomes: evidence and future directions. J Comp Eff Res 2014 Mar;3(2):145-154. [doi: 10.2217/cer.14.6] [Medline: 24645688] 33. Wlodarczyk TW, Hacker TJ. Current trends in predictive analytics of big data. Int J Big Data Intel 2014;1(3):172-122. [doi: 10.1504/IJBDI.2014.066326] 34. Sengupta PP. Intelligent platforms for disease assessment: novel approaches in functional echocardiography. JACC Cardiovasc Imaging 2013 Nov;6(11):1206-1211 [FREE Full text] [doi: 10.1016/j.jcmg.2013.09.003] [Medline: 24229773] 35. Issa NT, Byers SW, Dakshanamurthy S. Big data: the next frontier for innovation in therapeutics and healthcare. Expert Rev Clin Pharmacol 2014 May;7(3):293-298 [FREE Full text] [doi: 10.1586/17512433.2014.905201] [Medline: 24702684] 36. Beveridge R, Fox J, Higgins SA, Kohn M, Mahoney JJ, Newcomer LN, et al. Roundtable—the changing oncology landscape: evolution or revolution? J Natl Compr Canc Netw 2013 May;11(5 Suppl):636-638. [Medline: 23704232] 37. Kaushik K, Kapoor D, Varadharajan V, Nallusamy R. Disease management: clustering-based disease prediction. Int J Collaborative Enterprise 2014;4(1-2):69-82. [doi: 10.1504/IJCENT.2014.065047] Abbreviations ARRA: American Recover and Reinvestment Act EHR: electronic health record HIE: Health Information Exchange HIPAA: Health Insurance Portability and Accountability Act HITECH: Health Information Technology for Economic and Clinical Health MeSH: Medical Subject Headings PRISMA: Preferred Reporting Items for Systematic Reviews and Meta-analysis Edited by G Eysenbach; submitted 19.11.15; peer-reviewed by J Bian, D Maslove, MA Mayer, S Seevanayanagam, L Toldo; comments to author 03.01.16; revised version received 27.07.16; accepted 28.09.16; published 21.11.16 Please cite as: Kruse CS, Goswamy R, Raval Y, Marawi S JMIR Med Inform 2016;4(4):e38 URL: http://medinform.jmir.org/2016/4/e38/ doi: 10.2196/medinform.5359 PMID: 27872036 ©Clemens Scott Kruse, Rishi Goswamy, Yesha Raval, Sarah Marawi. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 21.11.2016. This is an open-access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 10 (page number not for citation purposes) XSL FO RenderX JMIR MEDICAL INFORMATICS Kruse et al bibliographic information, a link to the original publication on http://medinform.jmir.org/, as well as this copyright and license information must be included. http://medinform.jmir.org/2016/4/e38/ JMIR Med Inform 2016 | vol. 4 | iss. 4 | e38 | p. 11 (page number not for citation purposes) XSL FO RenderX

Journal

JMIR Medical InformaticsJMIR Publications

Published: Nov 21, 2016

Keywords: big data; analytics; health care; human genome; electronic medical record

There are no references for this article.