Scribd
Upload
176 views

Assignment 1&2

The document discusses predictive analytics and its use in healthcare. Specifically, it describes the FICO Medication Adherence Score, which uses data like age, gender, and medical history to predict a patient's likelihood of adhering to their medication regimen. The score is generated using a predictive model trained on data from millions of patients. Hospitals can use the score to develop strategies to help patients at risk of non-adherence, such as sending reminders or having nurses check on patients at home. The document also provides examples of how predictive analytics has helped optimize business processes and revenue.

Uploaded by

nasreen mody
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
176 views

Assignment 1&2

The document discusses predictive analytics and its use in healthcare. Specifically, it describes the FICO Medication Adherence Score, which uses data like age, gender, and medical history to predict a patient's likelihood of adhering to their medication regimen. The score is generated using a predictive model trained on data from millions of patients. Hospitals can use the score to develop strategies to help patients at risk of non-adherence, such as sending reminders or having nurses check on patients at home. The document also provides examples of how predictive analytics has helped optimize business processes and revenue.

Uploaded by

nasreen mody
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

1.

Read the article “Predictive Analytics—Saving Lives and Lowering


Medical Bills.” Answer the following questions:

 a. What problem is being addressed by applying predictive analytics?

Predictive analytics is the branch of the advanced analytics used to make predictions about
unknown future events; it tends to analyze historical data, predict outcomes, or give
recommendations that can help business owners improve service.

With the help of predictive analytics solutions, businesses can:

 Predict churn
 Predict and optimize LTV
 Segment customers
 Forecast the demand
etc.,

In short, with the help of predictive analytics, you make sense of your business data and find
hidden patterns that help you figure out the insights that can boost your revenue. This is the
main problem that most business owners are trying to solve.

Remember that there is no one-size-fits-all approach or a silver bullet that automatically solve
your challenges.

Before opting for a predictive analytics solution, you should figure out what goals you are
trying to achieve and what problems need to be addressed.

Start your project with a free consultation or exploratory stage; it will save you time, money
and also help figure out the exact solution that you need.

It is one of examples of analytic approach and based on models developed from publicly
available data like age, gender, marital status. By combining these data, they can build score
with range of 1-500 to indicate the probability of patients adhering to prescription for first year
of therapy.

 b.  What is the FICO Medication Adherence Score?

The FICO Medication Adherence Score is a predictive analytics tool developed by the same
organization responsible for FICO credit scores. The adherence score forecast an individual’s
likelihood of taking his or her prescription medication as directed.

 c.  How is a prediction model trained to predict the FICO Medication


Adherence Score HoH? Did the prediction model classify the FICO Medication
Adherence Score?

The score is using to identify patients by pharmacy-benefits manager. The manager uses the
five data sets, so analytics scientists are able to track the pattern of patients who filled and
refilled prescriptions and those who didn't. The patients who record top decile on the scale
actually stuck to their prescriptions for average of 129 more days.
d. Zoom in on Figure 4, and explain what kind of technique is applied on
the generated results.

By graphing the average days of adherence over first year by score, the author uses data of
recording millions of patients for prediction analytics to point out how the score is related to the
problem and forecast how patients of the certain amount of score will act based on the data.
2. Read the article “Big Data, Analytics and Elections,” and answer the
following questions:

a.  What kinds of Big Data were analyzed in the article Coo? Comment on
some of the sources of Big Data.

State economic, Social media, demographic, voter sentiment, behavioral analysis and political
data

 e. List some of the actionable decisions that were based on the prediction
results.

Analytics scientists and doctors can develop strategy and tactic for patients who got risk
score. One of example is that sending reminders through e-mail and text, simplifying drug
regimens to avoid confusion, offering information of drug programs and other financial
resources that can help patients to cover the cost of prescription, providing instruction in
patient's native language and having some extra care such as sending nurse to patient's
house to ensure that medications are taken properly.

b.  Explain the term integrated system. What is the other technical term
that suits an integrated system?

True definition: a system that has combined different functions together in order to work as
one entity.

Relation to the article: " The advantage of the integrated system is that analytics could be
performed effectively across multiple datasets from multiple channels- the ability to connect
the digital dots." Integrated systems evolved the way data was once executed; data could now
be used and shared simultaneously.

Another term that suits integrated data is Data Integration Process; "They first went through a
data integration process to consolidate many disparate databases and create a single,
massive system that merged information collected from pollsters, fundraisers, field workers,
and customer databases as well as social-media and mobile contacts with the Democratic
voter files in the swing states. "

 c.  What kinds of data analysis techniques are employed in the project?


Comment on some initiatives that resulted from data analysis.

Comment on some initiatives that resulted from data analysis.


Majority of the techniques were quantitative which means they had little room for variation in
the ways data was collected. Polls were taken, advisers ran experimental campaigns, data
from previous elections was evaluated, and after collect the data models were created. The
Obama campaigns used combined analytic techniques that were not used in the past and it
lead to triumph.

 d.  What are the different prediction problems answered by the models?


It uses historical data to predict future events. There are many different types of predictive
modeling techniques including ANOVA, linear regression (ordinary least squares), logistic
regression, ridge regression, time series, decision trees, neural networks, and many more ;‫ز‬

 e.  List some of the actionable decisions taken that were based on the
prediction results.

Analytics scientists and doctors can develop strategy and tactic for patients who got risk score.
One of example is that sending reminders through e-mail and text, simplifying drug regimens
to avoid confusion, offering information of drug programs and other financial resources that
can help patients to cover the cost of prescription, providing instruction in patient's native
language and having some extra care such as sending nurse to patient's house to ensure that
medications are taken properly.

You might also like