Datasets for Analysis
NHLBI created a longitudinal teaching dataset includes clinical, laboratory, and outcome data
on n = 4434 participants. Each participant has between one and three observations—which represent
The Framingham Heart Study—Integrative Exercises
Background
The National Heart, Lung, and Blood Institute (NHLBI)1 created a teaching dataset that
includes real but anonymized data collected as part of the Framingham Heart Study. The Framingham
Heart Study is one of the most influential and longest running epidemiological studies of risk factors
for cardiovascular disease ever run. The study started in 1948 and continues today to collect extensive
data from original participants, their children, and their children’s children. Much of what we know
about cardiovascular disease was discovered by investigators involved in the Framingham Heart Study.
In fact, studies to date using data collected in the Framingham Heart study have resulted in over 3000
publications in high impact, peer-reviewed medical journals.
The Framingham Heart Study has been widely discussed in the media. WGBH in Boston
produced a video documentary for PBS entitled “The Hidden Epidemic: Heart Disease in America”
that details the history of heart disease in this country and highlights the Framingham Heart Study.2 In
2007, CBS News did a story on the study, its participants, and its impact.3 Additionally, research results
from the Framingham Heart Study are communicated widely, most recently highlighting the discovery
of a gene that may promote obesity4 and new data showing declining rates of dementia.5 Interested
readers can visit the Framingham Heart Study website for a detailed history of this incredible study and
its many contributions to preventive medicine.6
1 http://www.nhlbi.nih.gov/
2 http://www.pbs.org/wgbh/takeonestep/heart/
3 http://www.cbsnews.com/videos/landmark-heart-study/
4 http://www.cbsnews.com/news/how-a-fat-gene-may-influence-your-weight/
5 http://www.cbsnews.com/news/dementia-alzheimers-risk-signs-of-hope-study/
6 https://www.framinghamheartstudy.org/about-fhs/history.php/
1
examinations held approximately 6 years apart. There are a total of 11,627 observations in the full
dataset. A detailed description of the Framingham Heart Study dataset and other public use datasets
available from NHLBI are available on the NHLBI Biologic Specimen and Data Repository
Information Coordinating Center (BioLINCC) website.7
Two datasets are available for analysis here—one is the complete dataset with n = 11,627
observations (or person-exams), and the second includes only data collected at the first examination for
each participant (n = 4434). The two datasets are available as comma separated values (.csv) files for
analysis in Excel, R, or other statistical computing packages. FHS-All.csv contains n = 11,627
observations and FHS-Exam1.csv contains n = 4434 observations.
Variables
The following variables are available in each dataset for analysis (extracted from the complete
documentation file, available on the NHLBI BioLINCC website 8).
Variable NameDescriptionCoding Details/Range
RANDIDUnique identification number for each participant2248-9999312
SEXParticipant sex1 = Male, 2 = Female
PERIODExam cycle1, 2, 3
TIMENumber of days since first (baseline) exam0–4854
AGEAge at exam, years32–81
SYSBPSystolic blood pressure, mmHg83–295
DIABPDiastolic blood pressure, mmHg30–150
BPMEDSUse of anti-hypertensive medication0 = No, 1 = Yes
CURSMOKECurrently smoking cigarettes0 = No, 1 = Yes
CIGPDAYNumber of cigarettes smoked per day0 (non-smoker)–90
TOTCHOLTotal serum cholesterol, mg/dL107–696
HDLC*High density lipoprotein cholesterol, mg/dL10–189
LDLC*Low density lipoprotein cholesterol, mg/dL20–565
BMIBody mass index = weight (kg)/height (m)214–57
GLUCOSESerum glucose, mg/dL39–478
DIABETESDiabetes (glucose > 200 mg/dL or on treatment)0 = No, 1 = Yes
HEARTRTEHeart rate, beats/minute37–220
PREVAPPrevalent angina pectoris0 = No, 1 = Yes
PREVCHDPrevalent coronary heart disease (CHD)0 = No, 1 = Yes
PREVMIPrevalent myocardial infarction (MI)0 = No, 1 = Yes
7 https://biolincc.nhlbi.nih.gov/static/studies/teaching/framdoc.pdf?link_time=2016-07-06_14:21:55.514359
8 https://biolincc.nhlbi.nih.gov/static/studies/teaching/framdoc.pdf?link_time=2016-07-06_14:21:55.514359
2
PREVSTRKPrevalent stroke0 = No, 1 = Yes PREVHYPPrevalent hypertension0 = No, 1 = Yes
The following are outcome events coded 1 if the event occurred during the
follow-up (only the first event is recorded).
ANGINAAngina pectoris0 = No, 1 = Yes HOSPMIHospitalized for MI0 = No, 1 = Yes
MI_FCHDHospitalized for MI or fatal CHD0 = No, 1 = Yes ANYCHDAny coronary heart disease
event0 = No, 1 = Yes STROKEStroke0 = No, 1 = Yes CVDCardiovascular disease0 = No, 1 = Yes
HYPERTENHypertension0 = No, 1 = Yes DEATHDeath from any cause0 = No, 1 = Yes
The following are numbers of days from the first (baseline) exam to the first event
during the follow-up. If no event occurred, time is end of follow-up,
death, or last known contact date.
TIMEAPTime from baseline to first angina
TIMEMITime from baseline to first myocardial infarction
TIMEMIFCTime from baseline to first MI or fatal CHD
TIMECHDTime from baseline to first CHD
TIMESTRKTime from baseline to first stroke
TIMECVDTime from baseline to first cardiovascular disease
TIMEHYPTime from baseline to first hypertension
TIMEDTHTime from baseline to death
*Available only at period = 3 exam, missing otherwise
3
2. Compare risk factors in men and women.
Complete the following table to compare men and women using data collected at the first
examination for each participant (n = 4434). Summarize your results in three to four sentences.
Patient Characteristic*Men (n = 1944)Women (n = 2490)
Age, years49.79, (8.72)50.03 (8.64)
Systolic blood pressure, mmHg131.74(19.44)133.82(8.64)
Diastolic blood pressure, mmHg83.71(11.44)82.60(12.50)
The average age of the sample was 49 years of age, extremely close to 50, for both men and
women. Men accounted for less than half of the study sample. The average blood pressure, considering
both systolic and diastolic findings for the sample, were considered in the normal range. Most
participants did not need medication to control blood pressure. The average BMI was 25.85.
Design, conduct and summarize results of the analyses outlined below using data collected in the
Framingham Heart Study using FHS-Exam1, the dataset that includes one observation per participant.
Analytic approaches and coding for solutions are detailed in the Excel file
1.Describe the study sample.
Complete the following table to describe the study sample using data collected at the first
examination for each participant (n = 4434). Summarize your results in three to four sentences.
Patient Characteristic*Total Sample (n = 4434)
Age, years49.93, (8.68)
Male sex1944, (43.84)
Systolic blood pressure, mmHg132.91(22.42)
Diastolic blood pressure, mmHg83.08(12.06)
Use of anti-hypertensive medication144(3.24)
Current smoker2181(49.19)
Total serum cholesterol, mg/dL236.98(44.65)
Body mass index25.85(4.10)
Diabetes121 (2.73)
* Mean (Standard deviation) or n (%)
4
Use of anti-hypertensive medication42(2.19)102(4.16)
Current smoker1175(60.44)1006(40.4)
Total serum cholesterol, mg/dL233.58(42.36)239.68(46.22)
Body mass index26.17(3.41)25.59(4.56)
Diabetes 59(3.04) 62(2.49)
* Mean (Standard deviation) or n (%)
The average age for both men and women was approximately 50 years of age. The systolic and
diastolic are relatively similar for both men and women, but according to the chart, women are much
more likely to be in use of anti-hypertensive medication as compared to the men. There is a higher
average of men who are current smokers in this sample, as well as a slightly higher average of BMI
compared to the women. Women also have a higher average of diabetes.
3.What characteristics are associated with BMI?
Use simple and multivariable linear regression analysis to complete the following table relating the
characteristics listed to BMI as a continuous variable. Before conducting the analysis, be sure that
all participants have complete data on all analysis variables. If participants are excluded due to
missing data, the numbers excluded should be reported. Then, describe how each characteristic is
related to BMI. Are crude and multivariable effects similar? What might explain or account for any
differences?
Outcome Variable: BMI, kg/m2
Regression CoefficientRegression Coefficient
p-value p-value
CharacteristicCrude ModelsMultivariable Model
Age, years0.063<0.01<0.01
Male sex.579<0.01<0.001
Systolic blood pressure, mmHg.060<0.01<0.001
Total serum cholesterol, mg/dL.011<0.01<0.001
Current smoker-1.40<0.01<0.001
5
Diabetes 2.29 <0.01
4.Who is most likely to have prevalent coronary heart disease?
Test if there are significant differences in the following risk factors between persons with and
without prevalent coronary heart disease (CHD). Summarize the statistical results in the table
below and then compare risk factors in persons with and without prevalent CHD. Be sure to
indicate what statistical tests were used in the footnote to the table and in a brief summary of a
paragraph or less.
History of CHD No History of CHD
p-value*
Patient Characteristic*(n = 194)(n = 4240)
Age, years57.4849.58<0.001
Systolic blood pressure, mmHg144.99132.35<0.001
Diastolic blood pressure, mmHg87.1482.90<0.001
Total serum cholesterol, mg/dL243.20236.700.049
Body mass index26.8325.80.001
* Mean (Standard deviation). P-values are based on two independent samples t tests.
In this study, 70 participants were disqualified. The multivariable and crude effects are similar
since they are both used to analyze data, but the crude effects analysis specifically looks for
associations between a single risk factor and an outcome, while multivariable effect analysis looks at
multiple risk factors and their relation to an outcome. The regression coefficients of: age, male
identifying, systolic blood pressure, total serum cholesterol, and diabetes show a strong, positive
association with BMI. An increase in these factors show to likely contribute to an increase in BMI. The
regression coefficient of a current smoker shows a weak, negative association with BMI.
<0.01
6
6. Please Provide a Summary of the data analysis as a whole . Summary should include
pertinent information of all the questions above. This summary should not exceed 300
words.
5.Describe the Data Collection Methods used in the study
There are a variety of data collection methods used and analyzed within this study. The most
prevalent methods to analyze variables were mean and standard deviation. The mean provides an
average among the sample, while standard deviation depicts a measure of variability. Other methods
such as: regression coefficient, multivariate analysis, and crude analysis were used throughout the
study to analyze the variables. Regression coefficient provides a measure of a parameter, that depicts
the association between an independent variable and a specific outcome. When using this method, the
researcher is analyzing the change of an outcome to one unit change of the independent variable, given
all other independent variables remain constant. As stated above, the multivariate analysis is used to
find associations between several risk factors and an outcome, while a crude analysis is used to find
associations between a single risk factor and an outcome.
The chart analyzes characteristics in patients, that show the researcher which characteristics are
most correlated with having a history of coronary heart disease. The data shows that on average, those
who are over the age of 57, have slightly elevated blood pressure (144/87), elevated total serum
cholesterol and a higher BMI are more likely to have a history of coronary heart disease, as compared
to their counterparts.
7
The average age of participants in this study was between 49 and 50 years old, and there were
more women in the study sample. Overall, most blood pressure fell into the pre-hypertensive category.
Most participants were nonsmokers. Based on the data, the average risk factors between men and
women were relatively similar. Men, on average, were more likely to have a higher BMI, and were
more likely to be smokers. Thus, men were more likely to have prevalent coronary heart disease.
Women were significantly more likely to use anti-hypertensive medication, and had a higher average
of those with diabetes.
Throughout the study, it was noted that 70 participants were excluded from the study, leaving
the sample at 4364 participants. The last chart provides the researcher with numerical data on
characteristics in individuals that indicate a higher likelihood of having a history of coronary heart
disease. It was found that older patients and those with a higher BMI were at a higher risk for coronary
heart disease, and potentially other health complications. Aforementioned, the data indicates that on
average, those who are over the age of 57, have slightly elevated blood pressure (144/87), elevated
total serum cholesterol and a higher BMI are more likely to have a history of coronary heart disease, as
compared to their counterparts.
8
