Page 54 - Big Data Analytics for Intelligent Healthcare Management
P. 54
46 CHAPTER 3 BIG DATA ANALYTICS IN HEALTHCARE: A CRITICAL ANALYSIS
Provider Opt-in
Software Genome
Hospital Registries Patient
EHR’s Registries
Private
Non Retail
Outlets Payers and
Plan Claims
Mobile Government
Data and Health Plan
Wearables Claims
Medical Pharmacy
Claims Claims
FIG. 3.2
Different types of healthcare big data resources.
Based on Big Data in Healthcare Market Value Share of 20.69% With Cerner Co, Cognizant, Dell, Philips, Siemens and Business
Forecast to 2022j. (2018). Retrieved from: https://www.medgadget.com/2018/04/big-data-in-healthcare-market-value-share-of-20-
69-with-cerner-co-cognizant-dell-philips-siemens-and-business-forecast-to-2022.html; Elliott, R., Morss, P. (2018). Big Data: How It
Can Improve Our HealthjElliott Morss. Retrieved from: http://www.morssglobalfinance.com/big-data-how-it-can-improve-our-health/.
3.3.7 CLINICAL REFERENCE AND HEALTH PUBLICATION DATA
These are data collected from different publications such as journal articles, clinical practice guidelines
(text-based reference), health products, and clinical and medical research materials etc. [11].
3.3.8 ADMINISTRATIVE AND EXTERNAL DATA
These are the data that is generally collected through different external sources such as insurance state-
ments and correlated financial data, billing statements and scheduling [3], different biometric data such
as those collected through fingerprints, handwriting, and iris scans, etc.
Fig. 3.2 very clearly present the above discussed different sources of healthcare big data.
The following section concentrates on what medical image processing is and why we need it in
healthcare big data analysis.
3.4 MEDICAL IMAGE PROCESSING AND ITS ROLE IN HEALTHCARE DATA
ANALYSIS
Medical image processing means analysis of medical image data with the help of different image pro-
cessing algorithms. Image processing algorithms generally constitute contrast enhancement, noise re-
duction, edge sharpening, edge detection, segmentation etc. These techniques make the manual
diagnosis process of disease detection automatic or semiautomatic. Fig. 3.3 is an example of medical
