Results Summary

What was the project about?

When choosing a treatment, doctors often look at research results that show how well the treatment worked in large groups of people. But many factors can affect how well a treatment works for an individual patient. These factors may include the patient’s sex, age, other health problems, or how they responded to treatments in the past. Some patient data sources, such as electronic health records, have this information. But existing statistical methods may not use these data well. For example, existing methods may not be able to take advantage of data that include measurements of a patient’s health from more than one point in time.

For this project, the research team developed new methods to analyze data that includes measurements of a patient’s health from different points in time. To develop the new methods, the team used a Bayesian approach. Bayesian approaches include findings from previous studies in the analysis, which can make results more accurate.

What did the research team do?

The research team used data on a patient’s own health and on how well a treatment worked for others to create the new methods. To help researchers use the new methods, the team created a computer program. Finally, the team used three studies to adapt the methods to predict health changes and responses to treatment for patients having one of three different health problems.

Patients, doctors, and a health plan administrative leader provided input to build and refine the methods. A group of researchers helped to create the computer program.

What were the results?

The methods predicted aspects of a patient’s health and changes in health over time. In the first study, the new methods helped researchers find out whether a child’s pneumonia was caused by a virus or bacteria. In the second study, the team used the new methods to see if active monitoring or surgery would work better for a patient with prostate cancer. In the third study, the new methods helped to predict a patient’s mental health symptoms over time.

What were the limits of the project?

The research team tested the new methods with three health problems; the methods might work differently for other health problems.

Future research could test the methods with other examples. Studies could also look at whether using the methods for treatment decisions can help improve patients’ health.

How can people use the results?

Researchers can use the methods to help predict changes in a patient’s health and how well a treatment will work.

Final Research Report

View this project's final research report.

Peer-Review Summary

Peer review of PCORI-funded research helps make sure the report presents complete, balanced, and useful information about the research. It also assesses how the project addressed PCORI’s Methodology Standards. During peer review, experts read a draft report of the research and provide comments about the report. These experts may include a scientist focused on the research topic, a specialist in research methods, a patient or caregiver, and a healthcare professional. These reviewers cannot have conflicts of interest with the study.

The peer reviewers point out where the draft report may need revision. For example, they may suggest ways to improve descriptions of the conduct of the study or to clarify the connection between results and conclusions. Sometimes, awardees revise their draft reports twice or more to address all of the reviewers’ comments. 

Peer reviewers commented and the researchers made changes or provided responses. Those comments and responses included the following:

  • Most of the research presented in this final report had already been published in peer-reviewed journals. The reviewers’ comments primarily related to the presentation of the research, acknowledging that it was difficult to apply the appropriate amount of technical information when summarizing mostly published research. The researchers made several changes in describing their research to improve the flow of the report and provide enough information for readers to understand the project.
  • The reviewers asked the researchers to clarify that their project was not intended to compare to existing approaches the impact of the new statistical models on diagnostic accuracy and treatment decisions. The researchers edited the text to clarify that this project was meant to be a proof-of-concept study that developed the new approaches. However, they noted that a larger study would be necessary for any comparisons to existing models.

Conflict of Interest Disclosures

Project Information

Scott Zeger, PhD
Johns Hopkins University
$779,615 *
Bayesian Hierarchical Models for the Design and Analysis of Studies to Individualize Healthcare

Key Dates

April 2015
August 2020

Study Registration Information

Final Research Report

View this project's final research report.

Journal Articles


Has Results
Award Type
State State The state where the project originates, or where the primary institution or organization is located. View Glossary
Last updated: January 20, 2023