Transferability of Neural Network Clinical De-identification Systems

TL;DR

This study evaluates how well a neural network for clinical de-identification can transfer across different datasets, note types, and institutions, highlighting fine-tuning and external data use as key factors.

Contribution

It systematically assesses transferability of NeuroNER across multiple clinical datasets and proposes architectural modifications for domain generalization.

Findings

External sources improve transfer performance to around 80% F1-score.

Fine-tuning is the most effective transfer strategy.

External data remains useful even with in-domain training data.

Abstract

Objective: Neural network de-identification studies have focused on individual datasets. These studies assume the availability of a sufficient amount of human-annotated data to train models that can generalize to corresponding test data. In real-world situations, however, researchers often have limited or no in-house training data. Existing systems and external data can help jump-start de-identification on in-house data; however, the most efficient way of utilizing existing systems and external data is unclear. This article investigates the transferability of a state-of-the-art neural clinical de-identification system, NeuroNER, across a variety of datasets, when it is modified architecturally for domain generalization and when it is trained strategically for domain transfer. Methods and Materials: We conducted a comparative study of the transferability of NeuroNER using four clinical note corpora with multiple note types from two institutions. We modified NeuroNER architecturally to integrate two types of domain generalization approaches. We evaluated each architecture using three training strategies. We measured: transferability from external sources; transferability across note types; the contribution of external source data when in-domain training data are available; and transferability across institutions. Results and Conclusions: Transferability from a single external source gave inconsistent results. Using additional external sources consistently yielded an F1-score of approximately 80%. Fine-tuning emerged as a dominant transfer strategy, with or without domain generalization. We also found that external sources were useful even in cases where in-domain training data were available. Transferability across institutions differed by note type and annotation label but resulted in improved performance.