Project Summary

One of PCORI’s goals is to improve the methods that researchers use for patient-centered outcomes research. PCORI funds methods projects like this one to better understand and advance the use of research methods that improve the strength and quality of comparative effectiveness research.

What is the project about?

Tailoring treatments to specific patients can improve patient outcomes. But doing so can require doctors and patients to make many complex decisions over time. For example, doctors may need to decide when to change or add medicines based on how well a treatment works. Patients may have multiple health problems, each of which requires a different treatment.

Statistical methods can help researchers estimate the best ways to tailor treatments based on a patient’s traits, such as their other health conditions or their current blood count. But current methods are limited. For example, they don’t account for missing data on patient traits that change over time or for when a patient takes multiple treatments at once.

In this study, the research team is using machine learning to develop new methods for estimating the best treatment approaches for individual patients. Machine learning uses data to learn how to perform tasks with little or no human input.

How can this project help improve research methods?

Results may help researchers estimate the best treatment approaches for individual patients.

What is the research team doing?

First, the research team is developing new methods for estimating treatment approaches for individual patients. The methods account for missing data on patient traits that change over time. They also measure the combined effects of multiple treatments taken at the same time. The team is testing the new methods using data from children with leukemia.

Research methods at a glance

Design ElementDescription
Goal
  • Develop new statistical methods to evaluate dynamic treatment and monitoring strategies in chronic disease settings with multiple risk trade-offs
  • Develop new statistical methods for time-varying mediation in order to identify causal mechanisms that may serve as targets for optimizing dynamic treatment and monitoring strategies
  • Estimate and understand the optimal chemotherapy treatment regimen and echocardiographic measurement strategies for pediatric patients with acute myeloid leukemia by synthesizing multiple complementary data resources
ApproachBayesian machine learning, G-computation, inverse probability of treatment weighted estimators

Project Information

Jason Roy, PhD, MS
Rutgers University School of Public Health
$1,077,183
Statistical Methods for Optimizing Dynamic Patient-Level Treatment and Monitoring Strategies

Key Dates

July 2022
January 2027
2022

Tags

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: May 15, 2024