Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mitra, Avijit, Yang, Zhichao, Druhl, Emily, Goodwin, Raelene, Yu, Hong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911139690971136
author Mitra, Avijit
Yang, Zhichao
Druhl, Emily
Goodwin, Raelene
Yu, Hong
author_facet Mitra, Avijit
Yang, Zhichao
Druhl, Emily
Goodwin, Raelene
Yu, Hong
contents Social and behavioral determinants of health (SBDH) play a crucial role in health outcomes and are frequently documented in clinical text. Automatically extracting SBDH information from clinical text relies on publicly available good-quality datasets. However, existing SBDH datasets exhibit substantial limitations in their availability and coverage. In this study, we introduce Synth-SBDH, a novel synthetic dataset with detailed SBDH annotations, encompassing status, temporal information, and rationale across 15 SBDH categories. We showcase the utility of Synth-SBDH on three tasks using real-world clinical datasets from two distinct hospital settings, highlighting its versatility, generalizability, and distillation capabilities. Models trained on Synth-SBDH consistently outperform counterparts with no Synth-SBDH training, achieving up to 63.75% macro-F improvements. Additionally, Synth-SBDH proves effective for rare SBDH categories and under-resource constraints while being substantially cheaper than expert-annotated real-world data. Human evaluation reveals a 71.06% Human-LLM alignment and uncovers areas for future refinements.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06056
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text
Mitra, Avijit
Yang, Zhichao
Druhl, Emily
Goodwin, Raelene
Yu, Hong
Computation and Language
Social and behavioral determinants of health (SBDH) play a crucial role in health outcomes and are frequently documented in clinical text. Automatically extracting SBDH information from clinical text relies on publicly available good-quality datasets. However, existing SBDH datasets exhibit substantial limitations in their availability and coverage. In this study, we introduce Synth-SBDH, a novel synthetic dataset with detailed SBDH annotations, encompassing status, temporal information, and rationale across 15 SBDH categories. We showcase the utility of Synth-SBDH on three tasks using real-world clinical datasets from two distinct hospital settings, highlighting its versatility, generalizability, and distillation capabilities. Models trained on Synth-SBDH consistently outperform counterparts with no Synth-SBDH training, achieving up to 63.75% macro-F improvements. Additionally, Synth-SBDH proves effective for rare SBDH categories and under-resource constraints while being substantially cheaper than expert-annotated real-world data. Human evaluation reveals a 71.06% Human-LLM alignment and uncovers areas for future refinements.
title Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text
topic Computation and Language
url https://arxiv.org/abs/2406.06056