Enhancing Inference for Small Cohorts via Transfer Learning and Weighted Integration of Multiple Datasets

TL;DR

This paper introduces TRANSLATE, a novel transfer learning weighting method that improves inference accuracy for small regional cohorts by integrating multiple datasets while accounting for heterogeneity.

Contribution

The paper proposes TRANSLATE, a new weighting approach that aligns external datasets with the target cohort, providing theoretical guarantees and practical improvements in sepsis outcome analysis.

Findings

TRANSLATE improves inference precision in simulations.

Application to Northeast sepsis data demonstrates enhanced accuracy.

Method effectively accounts for regional heterogeneity.

Abstract

Lung sepsis remains a significant concern in the Northeastern U.S., yet the national eICU Collaborative Database includes only a small number of patients from this region, highlighting underrepresentation. Understanding clinical variables such as FiO2, creatinine, platelets, and lactate, which reflect oxygenation, kidney function, coagulation, and metabolism, is crucial because these markers influence sepsis outcomes and may vary by sex. Transfer learning helps address small sample sizes by borrowing information from larger datasets, although differences in covariates and outcome-generating mechanisms between the target and external cohorts can complicate the process. We propose a novel weighting method, TRANSfer LeArning wiTh wEights (TRANSLATE), to integrate data from various sources by incorporating domain-specific characteristics through learned weights that align external data with the target cohort. These weights adjust for cohort differences, are proportional to each cohort's effective sample size, and downweight dissimilar cohorts. TRANSLATE offers theoretical guarantees for improved precision and applies to a wide range of estimands, including means, variances, and distribution functions. Simulations and a real-data application to sepsis outcomes in the Northeast cohort, using a much larger sample from other U.S. regions, show that the method enhances inference while accounting for regional heterogeneity.