Steven A. Eschrich

This paper evaluates synthetic data generation methods using random projection and multivariate similarity assessment in low-dimensional settings to address small-sample challenges in biomedical research.

This paper develops an RNA sequencing-based radiosensitivity index (RSI-seq) that preserves the clinical utility of the genomic-adjusted radiation dose (GARD) model, enabling personalized radiotherapy across diverse cancer types.

The paper introduces CLONEID, a framework for organizing clone-resolved data to enable longitudinal genotype-to-phenotype mapping in experiments with repeated molecular and phenotypic measurements.

The paper evaluates the reproducibility and clinical applicability of two gene expression signatures under CLIA laboratory standards.

spatialGE simplifies spatial transcriptomics analysis by providing a user-friendly web interface for non-programmers, enabling tasks like quality control, domain detection, and spatial analysis.

The paper evaluates a synthetic data generation technique to address the small sample problem by creating statistically similar synthetic populations.

This study develops a clinical-radiomics model to predict immunotherapy response in NSCLC patients, identifying a radiomic feature linked to hypoxia and poor outcomes.

This paper introduces a method to generate synthetic populations from sparse biomedical data, showing they are statistically similar to observed samples and can help overcome small sample size limitations.