COIT20253 Assessment 2: EHR Strategy for Big Data in Healthcare

This document presents a comprehensive analysis of Electronic Health Records (EHR) within the context of big data in healthcare. The assignment outlines a strategic approach to leveraging big data, encompassing data sources like medical imaging, EHRs, and wearable technologies. It explores technology stacks including Java, SQL databases, and streaming engines. The strategy section covers business and corporate strategies, providing an example of how EHRs can create value for different patient segments. The document details the functionality of EHRs, their advantages, and the implementation of big data. It also addresses challenges, such as the organization of hospitals around medical specialties rather than patient value. A cross-sectional study methodology is mentioned, along with results from a survey of healthcare professionals. The document also discusses corporate unit strategy, advantages, and the implementation of big data in EHRs. The assignment concludes by highlighting the potential of EHRs and references relevant research papers.

ELECTRONIC HEALTH RECORD
(EHR)
NAME OF THE STUDENT
NAME OF THE UNIVERSITY

BIG DATA IN HEALTH CARE
 “Big data in health care” refers to the health data that
are abundant and amassed from the various sources that
includes medical imaging, Electronic Health Records,
wearable technologies, payor device, medical devise and
genomic sequencing. This is available in the form of
extraordinary large volume. Big data spans the massive
digital universe of the health industrye. As big data
derives from several sources this is highly differentiable
in nature and structure.

ELECTRONIC HEALTH RECORD:
 The health services area, regardless of its significance,
is behind most different businesses, for example, retail,
producing, and monetary administrations to use IT for
operational.
 Powerful improvement and effective execution of IT
frameworks are basic in human services as these
frameworks have direct ramifications for patient
wellbeing, mortality, as well as better personal
satisfaction.

TECHNOLOGY STACK:
 Coding language: As Java is a cross platform and
reliable it is used in this application.
 Database: Database is the most important thing for the
big data platform. SQL is used for that.
 Streaming engines: IBM InfoSphere Streams is used.
 Data Visualization: This is a great idea for applying data
visualization tools. Tableau is used for that

STRATEGY:
 A clinic joins numerous organizations, normally
depicted as administration lines, inside one
association. Thus, they are having two sorts of
systems. Business procedures consider how
singular administration lines orthopedics and
obstetrics.

EXAMPLE:
 For the instance it make an incentive for various
portions of patients by giving administrations and
answers for address patients' issues. Corporate system
looks to build the estimation of the individual
organizations.

HOW EHR WORKS:
 EHR usage results in the nature of consideration that is
improved client introduction and auspicious access to
finish data.
 The potential advantages of the EHR, its usage is a
troublesome as well as complex undertaking whose
achievement relies upon numerous elements.
 The motivation behind this examination is surely to
distinguish the key achievement elements of the EHR.

METHODS AND MATERIALS:
 This is a cross sectional study led with support of
340 work powers from various kinds of
occupation from Hospitals of TUMS in 2014.
Information were gathered utilizing a selfly
organized survey that was assessed as both
dependable as well as legitimate. The information
were examined by SPSS programming distinct
insights and expository measurements.

RESULTS:
 58.2% of the respondents were ladies and the
expeience of work were 37.7 and 11.2 years.
 Individually as well as most of the respondents
(52.5%) was unhitched male. As far as
employment, the most extreme rate was
identified with nursing (33 %) and doctor (21 %).

CORPORATE UNIT STRATEGY:
 Emergency clinics must choose what administrations to
give as well as how to sort out the organizations to
accomplish more prominent monetary outcomes than
would be conceivable working them freely.

PROVIDED SERVICES:
 A medical clinic offering orthopedics, heart care, and
ladies' wellbeing would plan its corporate technique to
make those administration lines more beneficial than if
they were remain solitary units.
 While corporate system envelops the exciting stuff of
portfolios, cooperative energies, and reconciliation, it's
broadly hard to do effectively.

ADVANTAGES:
 Crafted by doctors, attendants, and different
clinicians is to address the issues of patients.
 The various specialty unit systems inside an
emergency clinic are essentially not the same as
each other relying upon the medical issues of the
patients.

Benefits
IMPLEMENTATATION OF BIG DATA IN
EHR
AND BENEFITS:

CHALLENGES:
 Clinics aggravate the trouble since they sort out around
medicinal claims to fame, techniques, and offices, not
how every business makes an incentive for the patients.
The standard cycle of aggregation and divestiture.
 In social insurance and each other field that
demonstrates that accomplishing more prominent
outcomes through blends is troublesome.

THE STRATEGY INDUCED EHR
PROBLEM:
 In the period of paper records, medical clinics
attempted to gather data from over their
specialty units.
 Charging required staffs of specialists drudging
in prison like record rooms, pulling sheets of
paper from documents, and physically
accumulating articulations.

TOWARDS AN EHR SOLUTION:
 Looking forward, suppliers can support the reason. Past
requesting that clinicians pick minimal terrible of poor
decisions, care conveyance associations ought to put
resources into clinician-helped creators to all the more
likely lucid data needs. At Boston-based essential
consideration supplier.

CONCLUSION:
 EHRs were announced the answer for these and
different difficulties. Medication cooperations
could be foreseen and kept away from, all
clinicians. Electronic requests could improve
charge catch and robotize charging. EHRs'
potential appeared to be limitless.

REFERENCES:
 Miotto, R., Li, L., Kidd, B.A. and Dudley, J.T., 2016. Deep patient: an unsupervised
representation to predict the future of patients from the electronic health records. Scientific
reports, 6, p.26094.
 Nguyen, L., Bellucci, E. and Nguyen, L.T., 2014. Electronic health records implementation: an
evaluation of information system impact and contingency factors. International journal of
medical informatics, 83(11), pp.779-796.
 Fildes, A., Charlton, J., Rudisill, C., Littlejohns, P., Prevost, A.T. and Gulliford, M.C., 2015.
Probability of an obese person attaining normal body weight: cohort study using electronic
health records. American journal of public health, 105(9), pp.e54-e59.
 Boonstra, A., Versluis, A. and Vos, J.F., 2014. Implementing electronic health records in
hospitals: a systematic literature review. BMC health services research, 14(1), p.370.
 Boyle, R., Solberg, L. and Fiore, M., 2014. Use of electronic health records to support
smoking cessation. Cochrane Database of Systematic Reviews, (12).
 Mandel, J.C., Kreda, D.A., Mandl, K.D., Kohane, I.S. and Ramoni, R.B., 2016. SMART on FHIR:
a standards-based, interoperable apps platform for electronic health records. Journal of the
American Medical Informatics Association, 23(5), pp.899-908.
 Ho, J.C., Ghosh, J. and Sun, J., 2014, August. Marble: high-throughput phenotyping from
electronic health records via sparse nonnegative tensor factorization. In Proceedings of the
20th ACM SIGKDD international conference on Knowledge discovery and data mining (pp.