THE FRAMINGHAM HEART STUDY

Evaluating Risk Factors to Save Lives

15.071x – The Analytics Edge

Franklin Delano Roosevelt (FDR)
•  President of the United
States, 1933-1945
•  Longest-serving president
•  Led country through Great
Depression
•  Commander in Chief of U.S.
military in World War II
•  Died while president, April
12, 1945

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 1
FDR’s Blood Pressure
•  Before presidency, blood pressure of 140/100
•  Healthy blood pressure is less than 120/80
•  Today, this is already considered high blood pressure
•  One year before death, 210/120
•  Today, this is called Hypertensive Crisis, and emergency care
is needed
•  FDR’s personal physician:
“A moderate degree of arteriosclerosis, although no more
than normal for a man of his age”
•  Two months before death: 260/150
•  Day of death: 300/190
15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 2
Early Misconceptions
•  High blood pressure dubbed essential hypertension
•  Considered important to force blood through arteries
•  Considered harmful to lower blood pressure
•  Today, we know better
“Today, presidential blood pressure numbers like FDR’s
would send the country’s leading doctors racing down
hallways … whisking the nation’s leader into the cardiac
care unit of Bethesda Naval Hospital.”
-- Daniel Levy, Framingham Heart Study Director

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 3
How Did we Learn?
•  In late 1940s, U.S. Government set out to better
understand cardiovascular disease (CVD)
•  Plan: track large cohort of initially healthy patients
over time
•  City of Framingham, MA selected as site for study
•  Appropriate size
•  Stable population
•  Cooperative doctors and residents
•  1948: beginning of Framingham Heart Study
15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 4
The Framingham Heart Study
•  5,209 patients aged 30-59 enrolled
•  Patients given questionnaire and exam every 2 years
•  Physical characteristics
•  Behavioral characteristics
•  Test results
•  Exams and questions expanded over time
•  We will build models using the Framingham data to
predict and prevent heart disease

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 5
Analytics to Prevent Heart Disease
Identify Risk Factors
Data

Predict Heart Disease

More Data

Validate Model

Define Interventions
using Model

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 1
Coronary Heart Disease (CHD)
•  We will predict 10-year risk of CHD
•  Subject of important 1998 paper, introducing the
Framingham Risk Score

•  CHD is a disease of the blood vessels supplying the

heart
•  Heart disease has been the leading cause of death
worldwide since 1921
•  7.3 million people died from CHD in 2008
•  Since 1950, age-adjusted death rates have declined 60%

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 2
Risk Factors
•  Risk factors are variables that increase the chances of a
disease

•  Term coined by William Kannell and Roy Dawber

from the Framingham Heart Study

•  Key to successful prediction of CHD: identifying

important risk factors

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 3
Hypothesized CHD Risk Factors
•  We will investigate risk factors collected in the first
data collection for the study
•  Anonymized version of original data
•  Demographic risk factors
•  male: sex of patient
•  age: age in years at first examination
•  education: Some high school (1), high school/GED (2),
some college/vocational school (3), college (4)

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 4
Hypothesized CHD Risk Factors
•  Behavioral risk factors
•  currentSmoker, cigsPerDay: Smoking behavior

•  Medical history risk factors

•  BPmeds: On blood pressure medication at time of first
examination
•  prevalentStroke: Previously had a stroke
•  prevalentHyp: Currently hypertensive
•  diabetes: Currently has diabetes

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 5
Hypothesized CHD Risk Factors
•  Risk factors from first examination
•  totChol: Total cholesterol (mg/dL)
•  sysBP: Systolic blood pressure
•  diaBP: Diastolic blood pressure
•  BMI: Body Mass Index, weight (kg)/height (m)2
•  heartRate: Heart rate (beats/minute)
•  glucose: Blood glucose level (mg/dL)

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 6
An Analytical Approach
•  Randomly split patients into training and testing sets

•  Use logistic regression on training set to predict

whether or not a patient experienced CHD within 10
years of first examination

•  Evaluate predictive power on test set

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 1
Model Strength
•  Model rarely predicts 10-year CHD risk above 50%
•  Accuracy very near a baseline of always predicting no
CHD
•  Model can differentiate low-risk from high-risk
patients (AUC = 0.74)
•  Some significant variables suggest interventions
•  Smoking
•  Cholesterol
•  Systolic blood pressure
•  Glucose

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 2
Risk Model Validation
•  So far, we have used internal validation
•  Train with some patients, test with others

•  Weakness: unclear if model generalizes to other

populations

•  Framingham cohort white, middle class

•  Important to test on other populations

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 1
Framingham Risk Model Validation
•  Framingham Risk Model tested on diverse cohorts
Study Population
Atherosclerosis Risk in Communities (ARIC) Study White and Black
Honolulu Heart Program (HHP) Japanese American
Puerto Rico Heart Health Program (PR) Hispanic
Strong Heart Study (SHS) Native American

•  Cohort studies collecting same risk factors

•  Validation Plan
•  Predict CHD risk for each patient using FHS model
•  Compare to actual outcomes for each risk decile

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 2
Validation for Black Men
•  1,428 black men in
ARIC study
•  Similar clinical
characteristics, except
higher diabetes rate
•  Similar CHD rate
•  Framingham risk
model predictions
accurate
15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 3
Validation for Japanese American Men

•  2,755 Japanese
American men in HHS

•  Lower CHD rate

•  Framingham risk
model systematically
overpredicts CHD risk

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 4
Recalibrated Model
•  Recalibration adjusts
model to new
population

•  Changes predicted risk,

but does not reorder
predictions

•  More accurate risk

estimates

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 5
Interventions
Identify Risk Factors
Data

Predict Heart Disease

More Data

Validate Model

Define Interventions
using Model

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 1
Drugs to Lower Blood Pressure
•  In FDR’s time, hypertension drugs too toxic for
practical use
•  In 1950s, the diuretic chlorothiazide was developed
•  Framingham Heart Study gave Ed Freis the evidence
needed to argue for testing effects of BP drugs
•  Veterans Administration (VA) Trial: randomized,
double blind clinical trial
•  Found decreased risk of CHD
•  Now, >$1B market for diuretics worldwide

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 2
Drugs to Lower Cholesterol
•  Despite Framingham results, early cholesterol drugs
too toxic for practical use
•  In 1970s, first statins were developed
•  Study of 4,444 patients with CHD: statins cause 37%
risk reduction of second heart attack
•  Study of 6,595 men with high cholesterol: statins
cause 32% risk reduction of CVD deaths
•  Now, > $20B market for statins worldwide

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 3
The Heart Study Through the Years
•  More than 2,400 studies
use Framingham data
•  Many other risk factors
evaluated
•  Obesity
•  Exercise
•  Psychosocial issues
•  …
•  Texas Heart Institute
Journal: top 10 cardiology
advances of 1900s
15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 1
Available Online

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 2
Research Directions and Challenges
•  Second generation enrolled in 1971, third in 2002
•  Enables study of family history as a risk factor
•  More diverse cohorts begun in 1994 and 2003
•  Social network analysis of participants
•  Genome-wide association study linking studying
genetics as risk factors
•  Many challenges related to funding
•  Funding cuts in 1969 nearly closed study
•  2013 sequester threatening to close study

15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 3
Clinical Decision Rules
•  Paved the way for clinical
decision rules
•  Predict clinical
outcomes with data
•  Patient and disease
characteristics
•  Test results
•  More than 75,000
published across
medicine
•  Rate increasing
15.071x –The Framingham Heart Study: Evaluating Risk Factors, Saving Lives 4