# Annotating Social Determinants of Health Using Active Learning, and Characterizing Determinants Using Neural Event Extraction

arXiv: https://arxiv.org/abs/2004.05438 · HTML: https://mlsanity.com/paper/2004.05438/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2020.

## Built on by (most cited first, 30 of 32)

- [The 2022 n2c2/UW Shared Task on Extracting Social Determinants of Health](https://mlsanity.com/paper/2301.05571/) (2023)
- [Hierarchical Annotation for Building A Suite of Clinical Natural Language Processing Tasks: Progress Note Understanding](https://mlsanity.com/paper/2204.03035/) (2022)
- [A Study of Social and Behavioral Determinants of Health in Lung Cancer Patients Using Transformers-based Natural Language Processing Models](https://mlsanity.com/paper/2108.04949/) (2021)
- [A Scoping Review of Publicly Available Language Tasks in Clinical Natural Language Processing](https://mlsanity.com/paper/2112.05780/) (2021)
- [Social and behavioral determinants of health in the era of artificial intelligence with electronic health records: A scoping review](https://mlsanity.com/paper/2102.04216/) (2021)
- [SODA: A Natural Language Processing Package to Extract Social Determinants of Health for Cancer Studies](https://mlsanity.com/paper/2212.03000/) (2022)
- [Prompt-based Extraction of Social Determinants of Health Using Few-shot Learning](https://mlsanity.com/paper/2306.07170/) (2023)
- [Leveraging Natural Language Processing to Augment Structured Social Determinants of Health Data in the Electronic Health Record](https://mlsanity.com/paper/2212.07538/) (2022)
- [An overview of event extraction and its applications](https://mlsanity.com/paper/2111.03212/) (2021)
- [Zero-shot Learning with Minimum Instruction to Extract Social Determinants and Family History from Clinical Notes using GPT Model](https://mlsanity.com/paper/2309.05475/) (2023)
- [Backdoor Adjustment of Confounding by Provenance for Robust Text Classification of Multi-institutional Clinical Notes](https://mlsanity.com/paper/2310.02451/) (2023)
- [Representation Learning for Person or Entity-centric Knowledge Graphs: An Application in Healthcare](https://mlsanity.com/paper/2305.05640/) (2023)
- [SDOH-NLI: a Dataset for Inferring Social Determinants of Health from Clinical Notes](https://mlsanity.com/paper/2310.18431/) (2023)
- [Leveraging Large Language Models to Extract Information on Substance Use Disorder Severity from Clinical Notes: A Zero-shot Learning Approach](https://mlsanity.com/paper/2403.12297/) (2024)
- [Extracting Social Determinants of Health from Pediatric Patient Notes Using Large Language Models: Novel Corpus and Methods](https://mlsanity.com/paper/2404.00826/) (2024)
- [Event-based clinical findings extraction from radiology reports with pre-trained language model](https://mlsanity.com/paper/2112.13512/) (2021)
- [Task formulation for Extracting Social Determinants of Health from Clinical Narratives](https://mlsanity.com/paper/2301.11386/) (2023)
- [Active Learning for Event Extraction with Memory-based Loss Prediction Model](https://mlsanity.com/paper/2112.03073/) (2021)
- [Question-Answering System Extracts Information on Injection Drug Use from Clinical Notes](https://mlsanity.com/paper/2305.08777/) (2023)
- [Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities](https://mlsanity.com/paper/2308.08407/) (2023)
- [Leveraging Social Determinants of Health in Alzheimer's Research Using LLM-Augmented Literature Mining and Knowledge Graphs](https://mlsanity.com/paper/2410.09080/) (2024)
- [Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models](https://mlsanity.com/paper/2506.00134/) (2025)
- [Cross-institution text mining to uncover clinical associations: a case study relating social factors and code status in intensive care medicine](https://mlsanity.com/paper/2301.06570/) (2023)
- [Enhancing Robustness of Foundation Model Representations under Provenance-related Distribution Shifts](https://mlsanity.com/paper/2312.05435/) (2023)
- [Identifying Health Risks from Family History: A Survey of Natural Language Processing Techniques](https://mlsanity.com/paper/2403.09997/) (2024)
- [Syntactic-GCN Bert based Chinese Event Extraction](https://mlsanity.com/paper/2112.09939/) (2021)
- [A Marker-based Neural Network System for Extracting Social Determinants of Health](https://mlsanity.com/paper/2212.12800/) (2022)
- [Leveraging Open-Source Large Language Models for encoding Social Determinants of Health using an Intelligent Router](https://mlsanity.com/paper/2405.19631/) (2024)
- [Improving Social Determinants of Health Documentation in French EHRs Using Large Language Models](https://mlsanity.com/paper/2507.03433/) (2025)
- [Using reasoning LLMs to extract SDOH events from clinical notes](https://mlsanity.com/paper/2604.13502/) (2026)

## Abstract (arXiv)

Social determinants of health (SDOH) affect health outcomes, and knowledge of SDOH can inform clinical decision-making. Automatically extracting SDOH information from clinical text requires data-driven information extraction models trained on annotated corpora that are heterogeneous and frequently include critical SDOH. This work presents a new corpus with SDOH annotations, a novel active learning framework, and the first extraction results on the new corpus. The Social History Annotation Corpus (SHAC) includes 4,480 social history sections with detailed annotation for 12 SDOH characterizing the status, extent, and temporal information of 18K distinct events. We introduce a novel active learning framework that selects samples for annotation using a surrogate text classification task as a proxy for a more complex event extraction task. The active learning framework successfully increases the frequency of health risk factors and improves automatic extraction of these events over undirected annotation. An event extraction model trained on SHAC achieves high extraction performance for substance use status (0.82-0.93 F1), employment status (0.81-0.86 F1), and living status type (0.81-0.93 F1) on data from three institutions.