GIST 2.0: A scalable multi-trait metric for quantifying population representativeness of individual clinical studies

Anando Sen; Shreya Chakrabarti; Andrew Goldstein; Shuang Wang; Patrick B Ryan; Chunhua Weng

doi:10.1016/j.jbi.2016.09.003

GIST 2.0: A scalable multi-trait metric for quantifying population representativeness of individual clinical studies

J Biomed Inform. 2016 Oct:63:325-336. doi: 10.1016/j.jbi.2016.09.003. Epub 2016 Sep 4.

Authors

Anando Sen¹, Shreya Chakrabarti², Andrew Goldstein³, Shuang Wang⁴, Patrick B Ryan⁵, Chunhua Weng⁶

Affiliations

¹ Department of Biomedical Informatics, Columbia University, New York, NY 10032, United States. Electronic address: [email protected].
² Department of Biomedical Informatics, Columbia University, New York, NY 10032, United States. Electronic address: [email protected].
³ Department of Biomedical Informatics, Columbia University, New York, NY 10032, United States; Department of Medicine, New York University, New York NY 10016, United States. Electronic address: [email protected].
⁴ Department of Biostatistics, Columbia University, New York, NY 10032, United States. Electronic address: [email protected].
⁵ Department of Biomedical Informatics, Columbia University, New York, NY 10032, United States; Janssen Research and Development, Titusville, NJ 08560, United States. Electronic address: [email protected].
⁶ Department of Biomedical Informatics, Columbia University, New York, NY 10032, United States. Electronic address: [email protected].

Abstract

The design of randomized controlled clinical studies can greatly benefit from iterative assessments of population representativeness of eligibility criteria. We propose a multi-trait metric - GIST 2.0 that can compute the a priori generalizability based on the population representativeness of a clinical study by explicitly modeling the dependencies among all eligibility criteria. We evaluate this metric on twenty clinical studies of two diseases and analyze how a study's eligibility criteria affect its generalizability (collectively and individually). We statistically analyze the effects of trial setting, trait selection and trait summarizing technique on GIST 2.0. Finally we provide theoretical as well as empirical validations for the expected properties of GIST 2.0.

Keywords: Clinical trials; Eligibility criteria; Generalizability; Population representativeness; Trait dependencies.

MeSH terms

Biomedical Research
Humans
Patient Selection*
Randomized Controlled Trials as Topic*
Software

Abstract

MeSH terms

Grants and funding