Propensity score-integrated composite likelihood approach for incorporating real-world evidence in single-arm clinical studies

Chenguang Wang, Nelson Lu, Wei Chen Chen, Heng Li, Ram Tiwari, Yunling Xu, Lilly Q. Yue

Research output: Contribution to journalArticle

Abstract

In medical product development, there has been an increased interest in utilizing real-world data which have become abundant with recent advances in biomedical science, information technology, and engineering. High-quality real-world data may be analyzed to generate real-world evidence that can be utilized in the regulatory and healthcare decision-making. In this paper, we consider the case in which a single-arm clinical study, viewed as the primary data source, is supplemented with patients from a real-world data source containing both clinical outcome and covariate data at the patient-level. Propensity score methodology is used to identify real-world data patients that are similar to those in the single-arm study in terms of the baseline characteristics, and to stratify these patients into strata based on the proximity of the propensity scores. In each stratum, a composite likelihood function of a parameter of interest is constructed by down-weighting the information from the real-world data source, and an estimate of the stratum-specific parameter is obtained by maximizing the composite likelihood function. These stratum-specific estimates are then combined to obtain an overall population-level estimate of the parameter of interest. The performance of the proposed approach is evaluated via a simulation study. A hypothetical example based on our experience is provided to illustrate the implementation of the proposed approach.

Original languageEnglish (US)
JournalJournal of biopharmaceutical statistics
DOIs
StateAccepted/In press - Jan 1 2019

Fingerprint

Integrated Likelihood
Composite Likelihood
Propensity Score
Information Storage and Retrieval
Likelihood Functions
Information Science
Composite function
Likelihood Function
Decision Making
Estimate
Technology
Delivery of Health Care
Product Development
Evidence
Clinical Studies
Information Technology
Healthcare
Proximity
Weighting
Covariates

Keywords

  • composite likelihood
  • Covariate balance
  • overlapping coefficient
  • propensity score
  • PSCL
  • real-world data
  • real-world evidence

ASJC Scopus subject areas

  • Statistics and Probability
  • Pharmacology
  • Pharmacology (medical)

Cite this

Propensity score-integrated composite likelihood approach for incorporating real-world evidence in single-arm clinical studies. / Wang, Chenguang; Lu, Nelson; Chen, Wei Chen; Li, Heng; Tiwari, Ram; Xu, Yunling; Yue, Lilly Q.

In: Journal of biopharmaceutical statistics, 01.01.2019.

Research output: Contribution to journalArticle

@article{1b260a89df6d4b219b8b26e3b93475b2,
title = "Propensity score-integrated composite likelihood approach for incorporating real-world evidence in single-arm clinical studies",
abstract = "In medical product development, there has been an increased interest in utilizing real-world data which have become abundant with recent advances in biomedical science, information technology, and engineering. High-quality real-world data may be analyzed to generate real-world evidence that can be utilized in the regulatory and healthcare decision-making. In this paper, we consider the case in which a single-arm clinical study, viewed as the primary data source, is supplemented with patients from a real-world data source containing both clinical outcome and covariate data at the patient-level. Propensity score methodology is used to identify real-world data patients that are similar to those in the single-arm study in terms of the baseline characteristics, and to stratify these patients into strata based on the proximity of the propensity scores. In each stratum, a composite likelihood function of a parameter of interest is constructed by down-weighting the information from the real-world data source, and an estimate of the stratum-specific parameter is obtained by maximizing the composite likelihood function. These stratum-specific estimates are then combined to obtain an overall population-level estimate of the parameter of interest. The performance of the proposed approach is evaluated via a simulation study. A hypothetical example based on our experience is provided to illustrate the implementation of the proposed approach.",
keywords = "composite likelihood, Covariate balance, overlapping coefficient, propensity score, PSCL, real-world data, real-world evidence",
author = "Chenguang Wang and Nelson Lu and Chen, {Wei Chen} and Heng Li and Ram Tiwari and Yunling Xu and Yue, {Lilly Q.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1080/10543406.2019.1684309",
language = "English (US)",
journal = "Journal of Biopharmaceutical Statistics",
issn = "1054-3406",
publisher = "Taylor and Francis Ltd.",

}

TY - JOUR

T1 - Propensity score-integrated composite likelihood approach for incorporating real-world evidence in single-arm clinical studies

AU - Wang, Chenguang

AU - Lu, Nelson

AU - Chen, Wei Chen

AU - Li, Heng

AU - Tiwari, Ram

AU - Xu, Yunling

AU - Yue, Lilly Q.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In medical product development, there has been an increased interest in utilizing real-world data which have become abundant with recent advances in biomedical science, information technology, and engineering. High-quality real-world data may be analyzed to generate real-world evidence that can be utilized in the regulatory and healthcare decision-making. In this paper, we consider the case in which a single-arm clinical study, viewed as the primary data source, is supplemented with patients from a real-world data source containing both clinical outcome and covariate data at the patient-level. Propensity score methodology is used to identify real-world data patients that are similar to those in the single-arm study in terms of the baseline characteristics, and to stratify these patients into strata based on the proximity of the propensity scores. In each stratum, a composite likelihood function of a parameter of interest is constructed by down-weighting the information from the real-world data source, and an estimate of the stratum-specific parameter is obtained by maximizing the composite likelihood function. These stratum-specific estimates are then combined to obtain an overall population-level estimate of the parameter of interest. The performance of the proposed approach is evaluated via a simulation study. A hypothetical example based on our experience is provided to illustrate the implementation of the proposed approach.

AB - In medical product development, there has been an increased interest in utilizing real-world data which have become abundant with recent advances in biomedical science, information technology, and engineering. High-quality real-world data may be analyzed to generate real-world evidence that can be utilized in the regulatory and healthcare decision-making. In this paper, we consider the case in which a single-arm clinical study, viewed as the primary data source, is supplemented with patients from a real-world data source containing both clinical outcome and covariate data at the patient-level. Propensity score methodology is used to identify real-world data patients that are similar to those in the single-arm study in terms of the baseline characteristics, and to stratify these patients into strata based on the proximity of the propensity scores. In each stratum, a composite likelihood function of a parameter of interest is constructed by down-weighting the information from the real-world data source, and an estimate of the stratum-specific parameter is obtained by maximizing the composite likelihood function. These stratum-specific estimates are then combined to obtain an overall population-level estimate of the parameter of interest. The performance of the proposed approach is evaluated via a simulation study. A hypothetical example based on our experience is provided to illustrate the implementation of the proposed approach.

KW - composite likelihood

KW - Covariate balance

KW - overlapping coefficient

KW - propensity score

KW - PSCL

KW - real-world data

KW - real-world evidence

UR - http://www.scopus.com/inward/record.url?scp=85074861686&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074861686&partnerID=8YFLogxK

U2 - 10.1080/10543406.2019.1684309

DO - 10.1080/10543406.2019.1684309

M3 - Article

C2 - 31707908

AN - SCOPUS:85074861686

JO - Journal of Biopharmaceutical Statistics

JF - Journal of Biopharmaceutical Statistics

SN - 1054-3406

ER -