Big Data Science and its Applications in Healthcare and Medical Research: Challenges and Opportunities

  

    
Hierarchical Domains
    
Software
    
Features/Tasks/Outcomes
    
Examples, Cases, Resources
    
Some References
  
  

    
Platforms,Hardware, Physical    Capacity
    
Hadoop system
    
Parallel distributed,    multicore, cloud and clustering for timeliness, privacy, transparency, data    sharing, and integrity
    
Map-Reduce framework: Open flow    application programming to interfaces or a virtual network overlay for    controlling, understanding and dealing with Big Data, which could also create    agility and automation with a centrally programmable network
    
[43-49]
  
  

    
Data Storage Databases
    
HDFS distributed file systems
    
Storage, backup, retrieval,    acquisition, formatting to remove redundancy, inaccuracy
    
Big data Script Database: DBMS,    RDBMS or ORDBMS
    
[50-53]
  
  

    
Fundamental Data Preprocessing
    
R/pbdR; bioconductor, SAS JMP,    SPSS, Matlab
    
Data cleaning, extracting,    integration, aggregation, visualizations
    
Software-defined data center or    software-defined network, SoFIA, ExScalibur
    
[ 25,35,72-74,80-83]
  
  

    
Advanced Computational    Approaches
    
R/pbdR; Revolution Analytics,    Tableau Software, SAS JMP, Matlab
    
Modeling, analysis, computing,    interpretations
    
Network and systematic based    approaches
    
[13,75-79,84-87]
  
  

    
Resources Domain, Data/    Variable Types and Applications
    
Bioconductor/R; BRB-ArrayTools
    
Low cost, reduced medical    error, actionable knowledge high predictive value
    
1. OMICS, Precision Medicine,    The Cancer Genome Atlas(TCGA) project (large n, large p: next generation    sequencing, genomes, transcriptomes, epigenomes from cells, tissues and    organisms)
    
[1-5,24,88,89]
  
  

    
Heterogeneity
    
2. Comparative Effectiveness    and Patient Centered OutcomeResearch, implementation sciences(large n, large    p): hospital, lab, biometric data such as finger prints, handwriting, retinal    scans, X-ray and other medical images, pulse-oximetry readings, and other    unstructured, semi structured, health device, media or censored and EHR data
    
[4-6,11,14,18-20]
  
  

    
Three Vs, large n, large p
    
3. Human genomics: clinical    trial or animal study (large p, small n)
    
[52,75-82,84-87]
  

Table 1: Table 1: Big Data Domains, Features, Software/Hardware, Analytical Approaches, and Examples/Applications.

Big data science debates, challenges, and opportunities

Big Data science is now considered as “interdisciplinary fields work principally in the social sciences, humanities and computing and their intersections with the natural sciences about the implications of Big Data for societies” [26]. Due to its real time nature, and rich information enabled by new technologies, Big Data science has potential to offer a higher form of intelligence and knowledge with the aura of truth, objectivity, and accuracy [61,62]. Currently, there is a good understanding that addressing researcher’s subjectivity with Big Data sciences could make research more scientific, robust, and ethical. However, how real time features shaping the researchers’ usage of Big Data during gathering, manipulating, analyzing, and visualization process could be a challenging issue, and need to be examined.

External factors or data types, e.g., in the social media contents for the health related issues, the streaming unstructured user-generated text based qualitative data derived from subjective perceptions and personal experience may interfere and paint data with a misleading picture, and, in the end, what it quantifies does not necessarily have a closer claim on objective truth. Therefore, developing conceptual models grounded in the complex and unstructured data in the qualitative research perspective for detecting the subjectivity, the external factors, and abnormality of Big Data that may affect outcomes is really in need, and might be new research opportunities [35].

Moreover, since Big Data is not a random sample, but contains all data, ‘The Age of Big Data’ explosion raises some debates and challenges regarding the need of new scientific computational methods, and the values of the traditional statistical inference theories that has prevailed for centuries in data sciences, but now might be outdated [63-66]. We all know that the Big Data era requires exhaustive, to the plenary, unlike the random sampling based traditional statistical approaches. Should the best analytical approach in this new big data era be exhaustive using of full data with more intelligent (be specific, artificial intelligence or machine learning based) rather than random sampling the big data?

To answer why plenary exhaustive might be more valuable, we may take a look at an evidence-based practice/medicine example. Based on the BMJ online forum, seventy five percent of doctors believe that adverse consequences has led the evidence-based practice/medicine moving toward collapse, and one real challenge is not evidence-based medical system itself, but that it is being improperly used due to the fact that most patients do not meet the clinical study inclusion criteria and most real cases are being considered as outliers. It is known that statistical significance does not imply the clinical significance, and correlation doesn’t conclude causal relationship.

Note that a common ending for either Big Data or traditional sampling based inference in medical science is that 1) as the sample/ data size grows larger, the science gets stronger; 2) follow-up time (real) the longer, the results are closer to clinical, and the greater value for clinical significance and usefulness.

Therefore, as an important inevitable complementary, Big Data science may overcome some challenges in evidence-based medical system (practice or medicine), and should be emphasized from research and clinical perspective with better data sharing and security plan, transparency, and integrity. This is because not only Big Data science allows researchers to study treatment effectiveness, and patient heterogeneity, but also the need for treatments to be allocated by randomization with continuously arriving new sample. In addition, through the integration of large data from published literatures and meta-analysis, secondary literature conclusions reached as a use of scientific methods to guide clinical practice itself could have important clinical significance and scientific value.

On the other hand, traditional statistical inference perspective, an important merit that Big Data science brings in is that it allows continuous refinement of the computational or statistical model and the associated assumptions with continuous arrival of new data for more accurate outcome and better informed decision making due to its real time, evolving and dynamic feature. More importantly, it allows applying predictive analytics to understand not only what has happened and what is currently happening, but also to predict what will happen in the future. The key challenges researchers face today in the area of Big Data is still the ability of researchers to locate, analyze, integrate, and interact with all real time data and associated software due to the lack of adaptive intelligent tools, accessibility, and appropriate training at the current stages [67,68].

In order to overcome such challenge for interpretable outcomes and replicable or reproducible results, and arriving to actionable and accurate medical decision making, close multidisciplinary collaborations of Big Data analysts with domain experts are needed. First, traditional data analysts (e.g., statisticians and mathematicians) should join with the new evolving class of “data scientists” (e.g., computer scientist/engineers) and create intelligent automatic systems and high level adaptive analysis tools to make full use of the Big Data and let the data speak for itself. Second, the domain experts including biomedical, social/behavioral scientists and scientists in economics, business, and geosciences, etc. need to work closely with Big Data scientists to make sense of the big data in order to extract actionable knowledge. The next generation of good Big Data scientists are indeed in demand of persons with brains for math, skills with computers, eyes of artists and abilities to: i) write algorithms that filter data; ii) churn through billions or trillions of data points and show where patterns emerge and what matters; iii) understand what they are telling; iv) graphically represent the information; v) make the judgment more sound, and more objective that may lead to better decision-making [69].

Hospitals throughout the United States currently undergo major operational change in order to complete Electron Health Record implementations and demonstration of their Meaningful Use in order to qualify for Centers for Medicare & Medicaid Services Incentive Programs and to avoid penalties [58]. Hospital administrators typically do not have additional resources to perform their own Big Data Analysis and is not part of their scope of work [59]. Also, due to the variety of the EHRs which are being used at the different hospitals and the current lack of Health Information Exchange among vendors and EHR products, Big Data Analysis of hospital multisite EHR and other data are rare and difficult to perform. Even single site Big Data Analysis is often done by researchers or employees who would like to answer specific questions, as opposed to being done by the vendors or by the hospital administrators [59].

However, if and when Health Information Exchange finally happens, the doors will suddenly open to Big Data Analysis that is expected to have huge positive implications to knowledge generation that shall impact research and practice. Some of the current problems are that in the past and in the present, hospital data was guarded due to HIPAA, conflict of interest, and its potential negative financial implications to the owner institutions. Vendors also have motivation to not develop EHR and other software systems that are interoperable with other software systems developed by other vendors, since that would make it easier for hospitals to change vendor in the future, which would have negative financial impact on the vendor [60].

Big data analytic approaches

Ultimately, the value of Big Data is not about the Big Data, it’s about how to turn big data into good research problems/questions/ hypotheses, then transform into valuable solutions that benefit society [70,71]. This is rendered simpler by their applications, for instance, the rapid advance of EHRs, mHealth, eHealth, Smart and Connected Health, and telehealth devices merging with social, behavior science, genomics and economics have led to the development of new infrastructure and transformation of health care systems for precision medicine and better-individualized patient care.

One important question for Big Data scientists to ask: 1) How to transform some 300 billion data points into quantitative statistical evidence for diagnostics, therapeutics, and new insights into population health, disease and treatment? 2) What are the best approaches? Does the traditionally used inference technique continue to play some roles? For instance, should it be experimental versus computational; hypothesis driven versus data driven; traditional statistical modeling versus data mining and artificial intelligence approaches.

To make the overwhelming volume of Big Data actionable and analytics operational, several key issues of how we proceed and analyze the data requires special attentions. First, bottleneck of the Big Data: Analysis tools and the development of advanced statistical and computational techniques with pipelines that can easily scale up with the three V’s (Volume, Velocity, Variety) and its complexity. These tools make high-powered methods available to not only professional statisticians, but also to casual users. Second, creator of Big Data value is the integration and linkage of heterogeneous Big Data, which has formidable logistical and analytical challenges. Third, validation, interpretation, and visualization: are crucial to extracting actionable knowledge for decision making which require Big Data analysts to closely collaborate with domain experts.

Therefore, in order to transform the billions of data points into valuable and actionable solutions require deeper learning and data analysis at both fundamental and advanced levels [25,72-74]. The fundamental level analysis include 1) basic online real time queries, pipeline, flow, analysis tools; 2) data pre-processing or big data reduction: detecting the missing data, errors, outliers; extracting, transforming, loading part of data preprocessing, automated filtering of non-useful data, redundancy and correlations; 3) computational techniques for summarizing the qualitative and quantitative results, unveiling trends and patterns, and generating reports; 4) data automations and generations for metadata, e.g., computer-automated analysis of blog postings; 5) visualization tools with simple and easy models: interpreting and making sense of the data.

At the advanced level data analysis: systems based and network approaches for data integration in genomic research is a good example. The followings are lists but not limited potential sophisticated computational and statistical approaches 1) Real time analytics and Meta-analysis that integrates multiple data sources including bedside healthcare streaming data; 2) hierarchical or multi-level model for spatial (state and national) data; longitudinal and mixed model for real time or temporal dynamic data rather than static data; 3) data mining, pattern recognitions for trends, and pattern detection; 4) natural language processing for text data mining; machine learning, statistical learning, Bayesian learning with auto-extraction of data and variables; 5) artificial intelligence with deep learning (e.g., neural network, support vector machine, dynamic state space model), automatic ensemble techniques and intelligent agent for automated analysis and information retrieval; 6) causal inferences and Bayesian approach with probabilistic interpretations [13].

Comparing fundamental level analytic with advanced level analytic in Big Data science, fundamental analytic including descriptive analytics serves for the purpose to summarize “what has happened” (e.g., in a simplest type that allows you to break down big data into smaller, more useful pieces of information) and focus on the insight gained from historical data to provide trending information on past or current events (e.g., looks at data and information to describe the current situation in a way that trends, patterns, and exceptions become apparent). While the advanced level computational tools listed above in Big Data science focuses on predictive and prescriptive analytics, which intends to determine patterns and predict future outcomes and trends, and answers “what could happen” and “what should we do?” through quantifying effects of future decisions in order to advise on possible outcomes. Prescriptive Analytics includes functions as a decision support tool by exploring a set of possible actions and suggesting actions based on descriptive and predictive analyses of complex data. It also conducts real-time analytics by using point-of-care data and analyzes the data at the point of care to present immediate and actionable information to providers.

Human genomics/OMICS application and example

Patient centered Electronic Health Records (EHR) big data examples have been reviewed and discussed recently, mainly for the case of large sample size n in terms of three V’s, but not for large number of parameters p [2-6]. Therefore, here we focus on a human OMICS (large “p”: next generation high-throughput sequencing data, genomes, transcriptomes, epigenomes and other omics data from cells, tissues and organisms) in personalized and precision medicine research as an important application and great example of Big Data science in the medical fields. Figure 1 demonstrates this translational research scheme/process from Big data generating instrument/technology, to complex data preprocessing and analytical pipeline, procedures and approaches in order to transform 300 billion data points of disease data into diagnostics, therapeutics, and new insights into population health and disease treatment. We can see that both lower level fundamental analysis and high level advanced computational analytic tools could play significant roles and be a more cost effective way than experimental ways in the big data world.

    

    

    Figure 1:  Big Data science in the fields of biomedical research: Transforming big genome data into diagnostics, therapeutics, and new insights into population
health, disease treatment.
    
    

    

    

    Figure 2:  Comparison of gene selection/filtering methods in time course gene expression data: Identifications of significant differentially expressed genes in
response to the treatment from various methods (top); post clustering and path analysis for characterizing the dynamics and changes of gene expression from early
stage to intermediate to the late stage to determine the trajectories of significantly regulated genes to better understand the treatment effect (bottom).
    
    

Download PDF

Citation: Liang Y and Kelemen A. Big Data Science and its Applications in Healthcare and Medical Research: Challenges and Opportunities. Austin Biom and Biostat. 2016; 3(1): 1030. ISSN: 2378-9840

Home

Journal Scope

Online First

Current Issue

Editorial Board

Instruction for Authors

Submit Your Article

Contact Us