Vous êtes sur la page 1sur 5

Big data and Healthcare in the United States

YUEN Yiu Wai


18039552D
Format B
Introduction
Healthcare expenditure in the United States has consumed a substantial proportion of the
national GDP of 17.1%. The expenditure is substantially greater amongst other developed
countries, outdistancing trailing countries like France, Germany, Canada with 11.5%, 11.1%,
10.5% of GDP respectively (Statista, 2019). However, sizeable spending does not translate to
better outcomes due system inefficiencies in healthcare. Duplication of procedures, medical
errors, unnecessary medical treatments and prescriptions, labor and administration costs are
main drivers of spending in the U.S. healthcare system. (Papanicolas, Jha, & Woskie, 2018).

Big data healthcare analytics reveal insights into patient medical records, outcomes
effectiveness, diagnoses, and hospital management and costs, and produce actionable
intelligence. Data sources consist, but are not limited to, electronic medical records (EMR),
laboratory results, pharmacy records, and billing and insurance claims. Software frameworks
like Hadoop distribute big data processing to different nodes and allow voluminous datasets
to be processed. The medical industry utilizes big data generated analytics to initiate
informed decisions that curb expenses and produce the most efficacious outcomes.

Applications and implications of big data in healthcare


Healthcare providers have adopted the Electronic Health Record Sharing System (eHRSS) to
facilitate medical information exchange readily across medical departments and institutions
(Ward, Marsolo, & Froehle, 2014). EMR is one of the data sources for big data analytics:
they are compiled into database management systems where the information is filtered and
systemized, then processed by analytical platforms.
Disease pattern analysis
Patterns for diseases can be identified by performing data mining on eHRSS databases.
Databases built with HMR data improve the understanding of disease causation and
classification in cardiovascular research (Hemingway, et al.) Big data processing analytical
platforms can identify reoccurring health symptoms that exist with disease bearing patients.
Big data produces actionable analytics and improve healthcare. Predictive models using big
data algorithm can predict patients diagnosed with heart disease to the accuracy of 93.02%
(Alharthi, 2018). Physicians utilize big-data generated insight to aid in their clinical
judgement to administer treatment provide better medical service to patients.

Wearable devices
IoT-enabled wearable devices allows remote monitoring of the patient. Through IoT, health
data is stored and managed through cloud-based database management system. Coupled with
data mining analytics, the system can identify abnormal vital patterns that indicate
developing symptoms for acute illnesses. For example, emergency services can be informed
when the IoT-enabled wearable device detects abnormal activity in vitals suggesting a heart
attack that requires immediate attention. Real-time monitoring and logging of patient health
information can also help identify developing chronic diseases with the help of disease
pattern analysis. Healthcare providers can have a more detailed understanding of patient
health and administer the appropriate treatment. This aligns with value pathway of right
living; prevention is better than cure. Any individual must closely monitor his health and
make lifestyle adjustments to prevent developing illnesses.

Intelligent staffing
Operational excellence can be achieved through effective hospital management with the help
of big data. Insights can be produced based on analyzing historical admission rates data, local
population and demographic data, seasonal sickness patterns in a predictive analytics model
(Deloitte, 2019). Accurate predictions can allow hospitals to prevent being short-staffed
during periods of patient influx and adjust for idle capital during off-peak hours, helping
optimize operations. Hospitals save $850,000 in human capital from intelligent staffing
adjustments from big-data analysis (Evariant, 2015). Predictive analytics with big data allow
operation optimization and enable hospitals to provide quality service and administer the
right treatment to patients.
Big data and privacy
The transition from traditional paper record keeping of medical information to EMRs has
made information more accessible. Big data analytics capitalizes on this abundant wealth of
medical information as larger data pools can produce new insights, derive more accurate
results, and give confidence to informed decision making. Big data analytics provide health
providers the opportunity to give patient quality treatment. However, greater information
accessibility has its own set of implications, particularly ethical issues of personal
information disclosure and privacy concerns that are commonly associated with big data.

Patient privacy is preserved when personal information from the EMRs are removed before
being transported into large databases as part of the data cleansing process (Groves, Kayyali,
Knott, & Kuiken, The 'big data' revolution in healthcare, 2013). Breach in patient information
can discourage trust between patients and health service providers. Partial disclosure of
patient medical history may lead to administering of wrong treatment from the physician.
(Lord, 2018). Breach in patient information may also allow health insurance companies to
discriminate against patients. Governing parties to set legislation and privacy controls to
make sure patient information are properly managed. It is also incumbent on health sector
providers to be reminded the Hippocratic oath to protect patient information and adhere to
policy.
Works Cited
Tracy, J. Y. (1986). Information Technology and Corporate Strategy: A Research
Perspective. Management Information Systems Research Center, 107-119.
Health & Pharmaceauticals. (2018). Global spending on medicines in 2010, 2018, and a
forecase for 2023 (in billion U.S. dollars). Statista.
Groves, P., Kayyali, B., Knott, D., & Kuiken, S. (2013). Center for US Health System Reform
Business Technology Office, The 'big data' revolution in Healthcare. McKindsey &
Company.
Statista. (2019). Health spending as a share of GDP in selected developed countries in 2011,
2013, and 2016. Statista 2019.
Statista. (2019). Projected expenditure on medicine of selected countries worldwide in 2023
(in billion U.S. dollars). Statista 2019.
Papanicolas, I., Jha, A., & Woskie, L. (2018). Health Care Spending in the United States and
Other High-Income Countries. American Medical Association.
Ward, M. J., Marsolo, K. A., & Froehle, C. M. (2014). Applications of Business Analytics in
Healthcare. Bus Horiz.
NAHU. (2015). Healthcare Cost Drivers White Paper. National Association of Health
Underwritetrs.
Groves, P., Kayyali, B., Knott, D., & Kuiken, S. V. (2013). The 'big data' revolution in
healthcare. McKindsey&Company.
Deloitte. (2019). Predictive analytics in healthcare. Deloitte Insights.
Hemingway, H. e., Hemingway, H., Asselbergs, F., Danesh, J., Dobson, R., Maniadakis, N.,
& Maggioni, A. (n.d.). Big data from electronic health records for early and late
translational cardiovascular research: challenges and potential. 2018: National
Center of Biotechnology Information.
Lord, R. (2018, September 18). Why Should We Care About Patient Privacy? Retrieved from
Forbes Technology Council.
Evariant. (2015, October 12). Evariant. Retrieved from Big Data Creates Big Improvements
in Healthcare.
Alharthi, H. (2018). Healthcare predictive analytics: An overview with a focus on Saudi
Arabia. Journal of Infection and Public Health, 749-756.

Vous aimerez peut-être aussi