Demographic Distribution Matching between real world and virtual phantom population

TL;DR

This paper presents DISTINCT, a statistical framework for selecting demographically aligned subsamples from large clinical datasets to improve the comparability of virtual imaging trials with real-world populations, enhancing their translational impact.

Contribution

The study introduces DISTINCT, a novel method for demographic matching in virtual trials, demonstrated on lung screening data to optimize sample size and subgroup analysis.

Findings

Identified a maximal demographic-aligned NLST subsample of 9,974 participants.

Demonstrated stabilized ROC AUC estimates beyond 6,000 participants.

Showed significant performance variation across demographic subgroups.

Abstract

Virtual imaging trials (VITs) offer scalable and cost-effective tools for evaluating imaging systems and protocols. However, their translational impact depends on rigorous comparability between virtual and real-world populations. This study introduces DISTINCT (Distributional Subsampling for Covariate-Targeted Alignment), a statistical framework for selecting demographically aligned subsamples from large clinical datasets to support robust comparisons with virtual cohorts. We applied DISTINCT to the National Lung Screening Trial (NLST) and a companion virtual trial dataset (VLST). The algorithm jointly aligned typical continuous (age, BMI) and categorical (sex, race, ethnicity) variables by constructing multidimensional bins based on discretized covariates. For a given target size, DISTINCT samples individuals to match the joint demographic distribution of the reference population. We evaluated the demographic similarity between VLST and progressively larger NLST subsamples using Wasserstein and Kolmogorov-Smirnov (K-S) distances to identify the maximal subsample size with acceptable alignment. The algorithm identified a maximal aligned NLST subsample of 9,974 participants, preserving demographic similarity to the VLST population. Receiver operating characteristic (ROC) analysis using risk scores for lung cancer detection showed that area under the curve (AUC) estimates stabilized beyond 6,000 participants, confirming the sufficiency of aligned subsamples for virtual imaging trial evaluation. Stratified AUC analysis revealed substantial performance variation across demographic subgroups, reinforcing the importance of covariate alignment in comparative studies.