Analysis of US Health Industry using SAS Visualization Analytics

This assignment analyzes the US health industry using SAS Visualization Analytics. It covers topics such as ICU days, diagnosis groups, patient numbers, and more. The analysis provides insights into the most popular diseases and suggests training more doctors to specialize in them.

Running Head: BIG DATA 1
US health department
<Name>
<University Name>

BIG DATA 2
Task 1: Background Information 3
Task 2: Reporting and Dashboard 4
ICU_DAYS and DIAGNOSIS GROUP 4
REGION, RACE, DIAGNOSIS AND DISCHARGED TO 8
TREND, DIAGNOSIS AND PATIENTS NUMBER BY ADMISION DATE 10
HOSPITAL AND PATIENT NUMBER MAP 14
Task 3: Additional Visualizations 15
Task 4: Justification 18
Task 5: Discussions 18
Task 6: Executive summary 19
Task 7: The Reflection (Individual Task) 20
Conclusion 20
References 21
Appendices 22

BIG DATA 3
Task 1: Background Information
Generally, analysis is important for every health organization that has a specific focus in order
to; enhance productivity and, therefore, more efficiency and effectivity, various valuable health
insights are gained, organization’s reputation can be upheld, Health Organizations or business
firms can remain competitive and improve overall performance and operations.
In this assignment, the "READMIT-HISTORICAL" dataset from teradatauniversitynetwork.com
has been considered. The SAS visualization analytics have been used since it has data
visualization that enhances decision-making process as well as communicating the trend and
discovers hidden patterns. The analysis of the health industry of America is important since; it
has become an expensive industry, development, and updating of health strategic plans
addressing health issues and to identify the patient number and Admission dates.
Big Data analysis is key since it is considered as a tool for evaluating quality of service provided
by the health industry in general, huge data of numerous hospitals, (June 2011 – July 2012).
Additionally, visualization of health conditions via SAS Visual Analytics predict the future of
U.S Health Services. These results are useful to US health departments since they are dealing
with the lives of people as well as continual operational improvement is necessary.
Normally, data visualization comes with a wide range of benefits ranging from but not limited to
having a glance to changes exposed within a timely manner, (Yang, Li, & Zhang, 2018). For
example, dashboards can be manipulated to uncover other findings especially hidden factors
affecting the general performance of an organization. This makes the data visualizations better
than static charts which may not have additional interactions except what has been presented. As
a result, people tend to enjoy data visualizations due to its interactive measures that change the
general perception of many analytics, (Hepworth, & C Canon, 2018).

BIG DATA 4
Task 2: Reporting and Dashboard
ICU_DAYS and DIAGNOSIS GROUP

BIG DATA 5
• Acute Myocardial Infarction (AMI) and COPD HIGHEST ICU DAYS for male's region
11.
• Congestive Heart Failure (CHF) HIGHLY DIAGNOSED in region 10 and 11.
• COPD has been identified as the diagnosis group which is least popular disease whereas
Congestive Heart Failure (CHF) is the most popular disease
• Include training of Congestive Heart Failure (CHF) in most learning institutions so that
more doctors can be trained to tackle the disease due to its popularity.
• Deploy more doctors specializing in Congestive Heart Failure (CHF) in Region 10 and
11 than other regions since the disease is highly diagnosed in these regions.
• Health education and promotion programs to target more males than females since they
have Congestive Heart Failure (CHF) and COPD conditions in higher proportions than
their female counterparts.
MOST AND LEAST POPULAR DISEASES
• Under Congestive Heart Failure (CHF), Heart Failure; 85, 138 cases has been identified
as the most popular diseases while disorders of disease electrolyte; 94 cases have been
identified as the least popular disease
• In addition, Pneumonia Organism Unspecified; 31, 245 is the most popular disease under
Acute Myocardial Infarction (AMI) while Bronchopneumonia; 94 is the least popular
disease
• In COPD, Chronic Bronchitis ; 75, 538 has been identified as the most popular disease
whereas Others ; 48 is seen to be the least popular disease.
• Train more doctors to specialize in Congestive Heart Failure (CHF), Pneumonia
Organism Unspecified and Chronic Bronchitis since they are considered to be the most
popular diseases affecting the US general populations.

BIG DATA 6

BIG DATA 7
DEPARTMENTS AND NUMBER OF PATIENTS SEEN
• Heart department has the highest number of patients; 770 followed by general medicine
department; 290.
• Oncology and Transplant department accounted for 103 and 83 total number of patients
seen.
• Neurosciences is the department that sees the lowest number; 10 of patients.
• There is need to add more medical doctors in Heart and General medicine given the fact
that they see the highest number of patients compared to other patients.

BIG DATA 8
REGION, RACE, DIAGNOSIS AND DISCHARGED TO
• Highest female patients seen comes from region 11
• A total of 89,075 patients are discharged to home after the treatment
• Highest “Black race” patients are from region 8
• Highest ASTHMA patients; 87 are from Hosp 35.
• Increase more female doctors in region 11 and more doctors in general in region 8 which
sees many patients.
• Deploy more doctors specializing in ASTHMA in hospital 35 since they see many
clients suffering from ASTHMA.

BIG DATA 9

BIG DATA 10
TREND, DIAGNOSIS AND PATIENTS NUMBER BY ADMISION DATE
• Highest admission of patient's number WITH Congenital Heart Failure was in in March
2012 while June 2012 recorded low admission of patients with the CHF condition
• January 2012 recorded the highest number of patients with COPD and AMI
• In December 2011, heart department have the highest operations

BIG DATA 11
MONTH, CITY, ADMIN DATE, GENDER AND THE NUMBER OF PATIENTS
• Highest admission of patient's number is in March 2012 while October – January 2012
recorded low admission
• Highest Patient numbers: DELRAY BEACH compared to other cities
• Increase the number of staff being deployed at the city of Delray Beach

BIG DATA 12

BIG DATA 13

BIG DATA 14
HOSPITAL AND PATIENT NUMBER MAP
 Data collection have been based in 10 states: Florida, Alabama, Georgia, Texas, Virginia,
Illinois, Mississippi, Arkansas, Missouri and Tennessee.
 The highest count of patient number by hospital is from Florida
 The lowest count is from Tennessee
The average ICU DAYS are high; 2.5-10 among the older populations while it is low
among the younger populations.

BIG DATA 15
Task 3: Additional Visualizations
 More females are suffering from COPD
 More males are suffered from CHF

BIG DATA 16
 In COPD, diagnosis group with the highest frequency of admission date occurred
between Dec 2011 and Jan 2012.
 In addition, highest diagnosis group with the highest frequency admission among AMI
occurred in Feb 2012.
 Moreover, CHF ighest frequency of admission occurred between March and April 2012.

BIG DATA 17
 Additionally, Heart departments have the highest operation count of about 60000 and
above followed by General medicine at 21000 operation counts.
 Females are more likely to experience higher frequency of admission than their male
counterparts.

BIG DATA 18
Task 4: Justification
In the present analysis, some of the data visualizations used include; a horizontal graph, line
graphs, and a bar graph which plays an important role while categorizing variables to indicate the
general distribution of frequencies of the variable of interest. Through the horizontal graphs,
numerical numbers of different categories have been indicated as shown. These graphs are also
relevant since it gives summaries that can be easily interpreted by just having a visual form of
the dataset, (Dobbs, 2018). Comparing the results shown in the horizontal graphs to the results
normally indicated in the Tables, the horizontal graphs gives better visualization hence it is easy
to give estimations of very essential values at a glance. Additionally, the accuracy level of
horizontal graphs is at par now that it can be checked if the calculations are right or not
specifically while arranging the bars in ascending order, levels of accuracy are automatically
detected.
These horizontal graphs have been used in several organizations especially those that are dealing
with big datasets like in machine learning and business intelligence to display various
dashboards which can be easily interpreted by the management without necessarily making the
management to acquire specific or statistical knowledge to understand and interpret the results.
Task 5: Discussions
Results show that Acute Myocardial Infarction (AMI) and COPD HIGHEST ICU DAYS for
male's region 11 while Congestive Heart Failure (CHF) HIGHLY DIAGNOSED in region 10
and 11. This implies that the are some kind of geographical settings in region 10 and 11 that in
one way or the other exposes populations to Acute Myocardial Infarction (AMI) and Congestive
Heart Failure (CHF).
In addition, results show that COPD is the diagnosis group which is least popular disease
whereas Congestive Heart Failure (CHF) is the most popular disease. Therefore, majority of the
US populations suffer from Congestive Heart Failure (CHF) than any other condition. As a
result, there is need to train more medical specialists in Congestive Heart Failure (CHF).

BIG DATA 19
Furthermore, Health education and promotion programs should be periodically done to target
more males than females since they have Congestive Heart Failure (CHF) and COPD conditions
in higher proportions than their female counterparts.
Other conditions diagnosed to be affecting the citizens of US are the Pneumonia Organism
Unspecified and Chronic Bronchitis. On this note, there is need to sensitize the populations
against these conditions and raise awareness on the best prevention strategies.
Given the fact that the Heart department has the highest number of patients show that the
government need to employ more heart specialist in these departments now that they tend to see
many patients compared to other departments.
Furthermore, highest admission of patient's number is in March 2012 while October – January
2012 recorded low admission means that there are some hidden factors that leads to these high
number of admission cases in these months.
Again, now that the highest Patient numbers comes from the DELRAY BEACH compared to
other cities need specialize attention so that the population can be sensitized on best prevention
and management strategies to address various causes of admission in the hospital.
From the map, it seems that data collection has been based in only 10 states: Florida, Alabama,
Georgia, Texas, Virginia, Illinois, Mississippi, Arkansas, Missouri and Tennessee. This means
that the findings cannot be generalized into other settings of US due to smaller sampled size
depicted.
Task 6: Executive summary
Acute Myocardial Infarction (AMI) and COPD HIGHEST ICU DAYS for male's region 11.
Congestive Heart Failure (CHF) HIGHLY DIAGNOSED in region 10 and 11. COPD has been
identified as the diagnosis group which is least popular disease whereas Congestive Heart Failure
(CHF) is the most popular disease. Include training of Congestive Heart Failure (CHF) in most
learning institutions so that more doctors can be trained to tackle the disease due to its
popularity. Under Congestive Heart Failure (CHF), Heart Failure; 85, 138 cases have been
identified as the most popular diseases while disorders of disease electrolyte; 94 cases have been
identified as the least popular disease. In addition, Pneumonia Organism Unspecified; 31, 245 is
the most popular disease under Acute Myocardial Infarction (AMI) while Bronchopneumonia;
94 is the least popular disease. In COPD, Chronic Bronchitis; 75, 538 has been identified as the
most popular disease whereas Others; 48 is seen to be the least popular disease. Train more
doctors to specialize in Congestive Heart Failure (CHF), Pneumonia Organism Unspecified and
Chronic Bronchitis since they are considered to be the most popular diseases affecting the US
general populations. Highest admission of patient's number is in March 2012 while October –
January 2012 recorded low admission. Highest Patient numbers: DELRAY BEACH compared to
other cities. Increase the number of staff being deployed at the city of Delray Beach. Data
collection have been based in 10 states: Florida, Alabama, Georgia, Texas, Virginia, Illinois,
Mississippi, Arkansas, Missouri and Tennessee. The highest count of patient number by hospital
is from Florida. The lowest count is from Tennessee.

BIG DATA 20
Task 7: The Reflection (Individual Task)
Individual 1: On challenges, issues of data quality and timeliness have been witnessed in the
analysis. For instance, several variables have missing dataset, and this affected the results. This is
a common factor, especially where the organizations or companies deal with bigger dataset and
should be controlled.
Individual 2: In addition, it was difficult to display some results like displaying or plotting a
graph where billions of observations are observed in the dataset. However, the solution to this
issue was made possible by doing cluster analysis.
Individual 3: Additionally, in a large amount of dataset, its velocity is affected since data takes
several minutes to load into the system and display results.
Individual 1: Some of the lessons learned during the SAS visual analytics is that it gives findings
that have deep insights that in one way or the other can support processes involving decision
making. This is possible because SAS analytical visualization gives various techniques that can
be employed while doing analytical reasoning to make decisions.
Individual 2: Furthermore, this system provides an opportunity to simultaneously understand
information with large amounts of observations by giving visual representations and interaction
techniques like graphs and maps.
Individual 3: Through SAS analytical visualization, it is easy to support various results produced,
presented and disseminated in a clear and logical way to different types of audiences.
Individual 2: Finally, through SAS analytical visualization, various hidden patterns within the
dataset can easily be discovered.
Individual 3: As much as there were some challenges, every team member made it possible to
see that these challenges are identified and dealt with appropriately. For example, filtering
options were identified to help in dropping cases with missing values as well as displaying only
the required results.
Conclusion
Visualization of huge datasets using SAS Visual Analytics can be used by U.S. Department of
Health and Human Services to control hazards via predictive forecasting and also helps in
generating real-time responses for immediate action.

BIG DATA 21
References
Anderson P. The beverage alcohol industry's social aspects organizations: a public health
warning. Addiction 2004; 99: 1376– 7.
Babor T., Caetano R., Casswell S., Edwards G., Giesbrecht N., Graham K. et al. Alcohol: No
Ordinary Commodity—Research and Public Policy. Oxford: Oxford University Press; 2003.
Dobbs, D, "Rational functions whose graphs intersect their horizontal asymptotes.". in Far East
Journal of Mathematical Education, 17, 2018, 133-162.
Green, Jesse, et al. "The Importance of Severity of Illness in Assessing Hospital Mortality."
Journal of the American Medical Association, January 12, 1990, pp.241-46.
Halpin, K, E Paprocki, & R McDonough, "Utilizing health information technology to improve
the recognition and management of the life-threatening adrenal crisis in the pediatric
emergency department: medical alert identification in the 21st century.". in Journal of
Pediatric Endocrinology and Metabolism, 32, 2019, 513-518.
Hepworth, K, & C Canon, "Improving Science Students’ Data Visualizations: A STEAM-Based
Approach.". in Dialectic, 2, 2018.
Jendrol', S, & M Kle????, "On graphs whose line graphs have crossing number one.". in Journal
of Graph Theory, 37, 2001, 181-188.
O'Dowd, A, "Social care can reduce demand on hospitals for end of life care.". in BMJ, 345,
2012, e6951-e6951.
Pearce N. Traditional epidemiology, modern epidemiology, and public health. Am J Public
Health 1996; 86: 678– 83.
Siegel M., Doner L. Marketing Public Health. Strategies to Promote Social Change. Sudbury,
MA: Jones & Bartlett; 2004.
The American Journal of Clinical Nutrition, Volume 36, Issue 4, October 1982, Pages 700–708,
https://doi.org/10.1093/ajcn/36.4.700
Yang, Y, N Li, & Y Zhang, "Networked Data Mining Based on Social Network Visualizations.".
in Journal of Software, 19, 2008, 1980-1994.

BIG DATA 22
Appendices
Some of the questions identified and needed response include;
Guided Questions
1. GROUP TASK: Create a data dictionary for the data source by the group.
2. What are the average number of ICU days with respect to diagnose group and gender?
3. For each region, what is most and least common diagnosis group?
4. For each diagnosis group, which is most and least popular disease?
5. What are top 5 departments with respect to number of patients?
6. What are top 3 regions with respect to female patient numbers?
7. What are top 5 places where patients are discharged?
8. What are top 3 regions with respect to “black” race?
9. What are the top 5 hospitals with respect to Asthma patients’ number of visits?
10. What are the active and inactive months in terms of admission for both male and female
patients? 11. What are top 3 regions with respect to average days spend in hospital? Hint- You
need to create a measure to calculate number of days spend in hospital
12. What are top 10 cities with respect to number of patients?
13. What is the trend of number of patient’s admission from October 2011 to June 2012 with
respect to region for both male and female? Hint- You need to use filter for the dates
14. Display only the most and least popular month in question 9 at a time.
15. What is the trend of patient numbers between Jan 2012 to June 2012 diagnosed with “CHF”
only?
16. What is the trend of different diagnose group over the months? 17. What are top 5
departments in terms of number of operations and how these operations vary across months?
18. What are the most appropriate predictors of heart disease? Hint- use decision tree
19. Create a geomap of the Hospitals and patient number.
20. Create a cluster analysis on patient related data.