Page 56 - Big Data Analytics for Intelligent Healthcare Management

48 CHAPTER 3 BIG DATA ANALYTICS IN HEALTHCARE: A CRITICAL ANALYSIS

with other kinds of EHR (electronic health record) data and genomic data is also required to advance
the accuracy and lessen the time taken for a diagnosis. Medical imaging can be defined as the technique
of generating a visual demonstration of the interior of a body for clinical investigation and medical
intervention, as well as a visual demonstration of the function of some organs or tissues (physiology)
[16]. Some of the frequently used medical imaging techniques are computed tomography (CT), fluo-
roscopy, magnetic resonance imaging (MRI), mammography, molecular imaging, photoacoustic
imaging, positron emission tomography-computed tomography (PET-CT), ultrasound, and X-ray
etc. [15]. The size of these medical image data can vary from a few megabytes for a single study
(e.g., histology images) to hundreds of megabytes per study (e.g., thin-slice CT readings covering
up to 2500+scans per study [15, 17]). This much data requires large amounts of storage with adequate
durability. To analyze this data, it needs some high processing, swift, and optimal algorithms. An
example of such a high processing technique is AMIGO (advanced multimodal image-guided operat-
ing) and it is a suite designed with an angiographic X-ray system, 3D ultrasound, MRI, and PET/CT
imaging in the operating room (OR) [18]. This system has been efficiently employed for cancer therapy
and helped to progress the localization and marking of the diseased tissue.
The medical image processing domain has a large role in determining efficient healthcare big data
analysis.
Recently, many different techniques and frameworks have been proposed for big data
analytics in healthcare research. Some of the noteworthy contributions are described in the below
Section 3.5.

3.5 RECENT WORKS IN BIG DATA ANALYTICS IN HEALTHCARE DATA
In this section, a few recent works in the field of big data analytics in healthcare are briefly presented.
Ojha et al. [19] presented an insight into how big data analytics tools like Hadoop can be used
with healthcare data. They discuss how meaningful information can be extracted from EHR (elec-
tronic health record). For this work, they conducted their experiments on the healthcare data
obtained from central India’s major government hospital, Maharaja Yeshwantrao Hospital (M.
Y.) situated in Indore, Madhya Pradesh, India. This hospital generates a large amount of data every
day, which the authors suggest to store in EHR. A unique number is assigned to every patient
whose data is stored here. With this number, information about any patient can be accessed more
easily and quickly. Also, the data warehouse, EDH (enterprise data hub), can be used to store this
data. Different data mining techniques such as classification, clustering, and association can easily
be performed on this data directly. This implies a steady and efficient medical big data analysis
technique.
Koppad et al. [20] introduced an application of big data analytics in the healthcare system with
an aim to predict COPD (chronic obstructive pulmonary disease). They have used the Decision
Tree technique, a data mining technique to perform COPD diagnosis in an individual patient. The
Aadhar number is used to refer to the patient’s details that are stored in a centralized clinical data
repository. As the Aadhar number is unique, it links to the treatments given to the patient in dif-
ferent hospitals and also about the doctors in charge. The authors claim an encouraging accuracy
in diagnosing COPD patients and the efficacy of the proposed system through experimental
results.