Project Summary

This research project is in progress. PCORI will post the research findings on this page within 90 days after the results are final.

What is the research about?

Scientists are doing studies to learn how things like genes, lifestyle, or the environment affect the risk of getting an illness in the future. Doctors know certain factors like smoking, family health history, and obesity affect the risk of getting an illness. But this information doesn’t help individual patients know how much these factors may affect them personally. The research team wants to develop statistical methods and software that can help predict an individual’s risk of getting a disease. Doctors and patients can use this information to talk about and help decide what treatment choices may be best for each patient.  In this project, the team is using breast cancer as an example.

Who can this research help?

Doctors can use results from this project to combine information about different types of risks for a disease into a prediction model that captures a patient’s overall risk for that disease. Patients and their doctors can use this information to help decide about treatments.

What is the research team doing?

The research team is developing ways to

  • Use information from studies about how genes and the environment affect a person’s risk for an illness
  • Combine data from different studies into a single risk prediction model
  • Confirm that the model works using studies that might be missing information about some of the risk factors

The team is testing its risk prediction model using studies on breast cancer.

Patients, doctors and researchers are working with the team to plan the study and discuss how doctors can use risk prediction models to provide care.

Research methods at a glance

Design Elements Description
Goal Improve methods for model building, validation, and delivery of risk prediction models
  • Use existing data sets on breast cancer biomarkers
  • Use genetic dimension reduction techniques to develop efficient ways to use data from case-control studies
  • Develop techniques for conducting meta-analyses of multivariate risk parameters using studies with varying underlying levels of risk factor information
  • Develop an efficient missing data framework for model validation in cohort studies

Project Information

Nilanjan Chatterjee, PhD
Johns Hopkins University
Statistical Methods for Development, Validation, and Implementation of Absolute Risk Models

Key Dates

December 2016
February 2022

Study Registration Information


Award Type
Health Conditions Health Conditions These are the broad terms we use to categorize our funded research studies; specific diseases or conditions are included within the appropriate larger category. Note: not all of our funded projects focus on a single disease or condition; some touch on multiple diseases or conditions, research methods, or broader health system interventions. Such projects won’t be listed by a primary disease/condition and so won’t appear if you use this filter tool to find them. View Glossary
State State The state where the project originates, or where the primary institution or organization is located. View Glossary
Last updated: March 4, 2022