Data and Performance: Futurelearn

Dr. Patricia Davidson discusses the importance of data-driven decision making during the COVID-19 pandemic. She explains that collecting measurable data, analyzing patterns, and using the information to develop strategies can help effectively respond to the crisis. The COVID-19 pandemic has increased the focus on big data and analytics to aid health service planning. In particular, she highlights the valuable data and maps created by Professor Lauren Gardner at Johns Hopkins University, which provide verifiable and frequently updated case information to inform decisions at granular levels. Data analytics can be descriptive, predictive, or prescriptive, and understanding these different types is useful for nurses and decision makers during the pandemic.

Uploaded by

Chlodette Eizl M. Laurente

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

0% found this document useful (0 votes)

50 views3 pages

Data and Performance: Futurelearn

Uploaded by

Chlodette Eizl M. Laurente

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

You are on page 1/ 3

Data and performance

Welcome to Effective Nursing in Times of Crisis, from Johns Hopkins University.

In this audio clip, Dr Patricia Davidson explains the importance of data-driven

decision making, and outlines how collecting data based upon measurable goals and
analysing patterns can help develop strategies and activities to underpin effective
responses to the COVID-19 pandemic.

Patricia:
It is hard to turn on the television or listen to a radio broadcast without hearing about
data related to COVID-19. Certainly, the COVID-19 pandemic has thrown big data
and information sources front and centre to help us with health service planning.

Data-driven decision making involves collecting data based upon measurable goals,
analysing patterns, and using this information to help develop strategies and activities
that benefit a particular activity. We've seen COVID-19 giving rise to many different
models and big data and analytical tools have been front and centre.

It's important when we're looking at each of these models that we make sure that
they come from a credible source and are built upon verifiable data. It's also
important to think of low tech solutions, particularly if other means are not available to
you. So contact tracing and following peoples’ movements and where they have been
can also be powerful tools in containing the pandemic.

We've also seen that some particular sites such as church gatherings and particular
cruise ships, have been a focus for the spread of the infection.

During this course, we've emphasised the importance of following the data and where
possible making data-driven decision making. And for these, we've used the
resources available on the Johns Hopkins website. The Johns Hopkins novel
Coronavirus website was built by Professor Lauren Gardner, a civil and systems
engineering professor at the Johns Hopkins University, and she built this with her
graduate student Ensheng Dong from scratch. And this has been such a formidable
and credible achievement. Professor Gardner and colleagues' career is built upon
identifying infectious diseases and following how they spread.

The Johns Hopkins database and map is maintained at the Centre for System
Science and Engineering in the Whiting School of Engineering at Hopkins and has
technical support from the Johns Hopkins University Applied Physics Laboratory.

1
FutureLearn
It's important to consider where information comes for these data maps. Professor
Gardner and colleagues map uses verifiable data sources including from the World
Health Organisation, the Centres for Disease Control and Prevention in the United
States, the European Centre for Disease Prevention and Control, the National Health
Commission of the People's Republic of China, and many other verifiable data
sources. This map is maintained in near real time throughout the day through a
combination of manual and automated updating. And sometimes more frequent
updates of the map often result in high case numbers that may be available from
other sources that are updated less frequently.

It's important to consider that there may be variation between different maps or
different data sources based upon the level of screening and diagnosis and how
cases are counted. And you will have heard debate and discussion in the media that
some people are considering that many individuals may die from Coronavirus, and
these are not diagnosed cases and therefore not counted.

This important data set developed by Professor Gardner has led to the ability to look
at information in a much more granular sense. So you will see for the United States
on this map a drill down to the county or regional level, which helps us draw upon a
range of data from available intensive care beds, issues of composition of the
workforce, and also individual characteristics that can help in health services
planning.

Having this kind of granular data and contextual information is really important to help
nurses make data-informed decisions. And this is particularly important for us as
nurses where we have to think about deploying additional resources such as
ventilators or nurses, and importantly, as the pandemic evolves, this information can
help us understand whether infection control procedures such as social distancing
measures need to change.

So as we look at these important sources, we recognise that data is a valuable tool

for nurses, and there are other courses in the FutureLearn platform that you may
want to explore. But understanding the different types of analytics is also useful.

Descriptive analytics are dashboards or scorecards that can illustrate events that
have happened in the past, but not what might happen or change in the future.

Predictive analytics use past data to model future outcomes. For example, there
could be in a model if 20% of people went back to their normal routines, there could
be 5000 additional fatalities. And prescriptive analytics is a type of data analytics that
uses technology to help make better decisions through the analysis of a range of
data sources. Prescriptive analytics factors information about possible situations or
scenarios and available resources, past performance and suggests a course of
action or strategy.

2
FutureLearn
And this is not just defined to health services and health services management.
Scientists are also using a range of big data and analytical techniques to map how
the virus has spread throughout the world and identify potential different viral
lineages. So optimising the use of these analytical techniques is dependent upon
valid input of data and assumptions, and asking important questions. So in spite of
the huge amount of data, this approach is only effective if you know how to
interrogate the data, that is what questions to ask, and, more importantly, as you
engage in managing the COVID-19 pandemic, how you react to the answers.

So, many people talk about us living in this system of information overload and data
overload, but sometimes we have very little specific strategies to work forward. So
extracting information and manageable strategies from these data are really, really
important. Most importantly, what some of these big data techniques have shown us
and suggest to us; three potential futures for the COVID-19 pandemic. And there are
different models presented, going from recurring small outbreaks, a huge wave or a
persistent crisis.

What we have to remember is that the reason that the COVID-19 pandemic is playing
such a devastating role on individuals and societies is that no one had immunity to
this novel Coronavirus. And until we get a level of herd immunity in society,
COVID-19 is going to continue to wreak havoc.

As we see through different models, changing one variable in the model can change
to a different outcome. So relaxing social distancing may lead to an increased
number of cases and fatalities. So the process of lessening isolation restrictions
around the world are varied, and we hope will be driven by the data and fundamental
principles of monitoring the COVID-19 pandemic.

So, as we look at some of our data sources, we want to think about, has there been a
sustained reduction in cases for 14 days consecutively? Do we have enough
intensive care beds, and are they able to manage the demand? Do we have sufficient
testing available and opportunities for quarantine? And how are we dealing with
screening and tracing strategies?

Data should lead us to answering each of these questions, and failing to answer each
of these questions will only lead to more suffering and devastation from the
COVID-19 pandemic.

3
FutureLearn