Epi and
Big Data
Big Data
Vast electronic storehouses on information that includes internet searches, social media, EMRs, data from health insurance programs, etc.
What is big data?
What are births, deaths, marriages, divorces, and fetal deaths?
Centralized database for information collection about a disease
What is a registry?
What is the National Health and Nutrition Examination Survey?
First person to quantify population statistics (history of epidemiology)
Who John Graunt?
Gathering and exploring large amounts of data to find patterns
What is data mining?
Name the two types of birth statistics
What are live births and fetal deaths?
BRFSS surveys down to this level of the US population
What is state-level?
Full name of BRFSS
The most important characteristic of epidemiologic data
What is quality?
The three V's of big data
What are volume, variety, and velocity?
Reason birth statistics are often reliable
What is unlikely to go unreported?
Level reportable/notifiable diseases are regulated at
What is state?
Characteristic unique to NHANES that makes it more reliable
What is conducting physical examinations?
Statistically, what do these large surveillance systems not have to worry about?
What is sample normality?
The two limitations of data mining in epidemiologic studies
What are protecting personal privacy and ensuring the reliability and validity of data?
Factor in death statistics that may be unreliable
What is cause of death?
Diseases required by law to be reported to prevent further spread
What are reportable/notifiable diseases?
Collects information about vital events in the US
What is the National Vital Statistic System (NVSS)?
Considering research ethics, list 3 reasons why researchers should be careful when using big data.
What are...
Promote the aims of research like knowledge, truth, and avoidance of error
Promote values essential to collaborative work (trust, respect, fairness)
Researchers should be held accountable to the public
Build public support for research
Promote moral and social values like social responsibility, human rights, etc.
Four questions that should be raised about a data source when considering using it (name 3/4)
What is the nature of the data? (what kind of data is it?)
How available is the data? (is it supposed to be private?)
How complete is the population coverage? (is it representative?)
What are the appropriate uses of the data? (what questions can it answer?)
Factor in birth statistics that can be unreliable
What are the conditions affecting pregnancy?
Types of PH surveillance (name 4)
What are...
syndromic surveillance
infectious disease surveillance
chronic disease surveillance
risk factor surveillance
sentinel surveillance
rumor surveillance
Based on what data they collect, NHIS and NHANES are examples of...
What are morbidity surveys?
What census data vs surveillance system data is used for in statistical/epidemiologic measures
What is using census data as the denominator and surveillance system data as the numerator