A Marker-based Neural Network System for Extracting Social Determinants of Health

TL;DR

This paper presents a novel marker-based neural network pipeline that effectively extracts social determinants of health from clinical notes, outperforming existing models and aiding in understanding healthcare disparities.

Contribution

The study introduces a marker-based NER model within a multi-stage pipeline, improving extraction of overlapping SDoH entities from clinical notes compared to prior span-based models.

Findings

Outperforms state-of-the-art span-based models in handling overlapping entities

Achieves state-of-the-art performance on the N2C2 shared task data

Demonstrates effective extraction of SDoH information from clinical notes

Abstract

Objective. The impact of social determinants of health (SDoH) on patients' healthcare quality and the disparity is well-known. Many SDoH items are not coded in structured forms in electronic health records. These items are often captured in free-text clinical notes, but there are limited methods for automatically extracting them. We explore a multi-stage pipeline involving named entity recognition (NER), relation classification (RC), and text classification methods to extract SDoH information from clinical notes automatically. Materials and Methods. The study uses the N2C2 Shared Task data, which was collected from two sources of clinical notes: MIMIC-III and University of Washington Harborview Medical Centers. It contains 4480 social history sections with full annotation for twelve SDoHs. In order to handle the issue of overlapping entities, we developed a novel marker-based NER model. We used it in a multi-stage pipeline to extract SDoH information from clinical notes. Results. Our marker-based system outperformed the state-of-the-art span-based models at handling overlapping entities based on the overall Micro-F1 score performance. It also achieved state-of-the-art performance compared to the shared task methods. Conclusion. The major finding of this study is that the multi-stage pipeline effectively extracts SDoH information from clinical notes. This approach can potentially improve the understanding and tracking of SDoHs in clinical settings. However, error propagation may be an issue, and further research is needed to improve the extraction of entities with complex semantic meanings and low-resource entities using external knowledge.