BOLD, a blood-gas and oximetry linked dataset

Pulse oximeters measure peripheral arterial oxygen saturation (SpO2)
noninvasively, while the gold standard involves arterial blood gas measurement
(SaO2). There are known racial and ethnic disparities in their performance.
BOLD is a new comprehensive dataset that aims to underscore the importance of
addressing biases in pulse oximetry accuracy, particularly affecting people
with darker skin tones. The dataset was created by harmonizing three
Electronic Health Record databases (MIMIC-III, MIMIC-IV, eICU-CRD) comprising
Intensive Care Unit stays. Paired SpO2 and SaO2 measurements were time-aligned
and combined with various other clinical parameters to provide a detailed
picture of each patient. It includes 49,099 such paired measurements within a
5-minute window, with oxygen saturation levels between 70-100%. Significantly,
about 25% of the data represents minority racial and ethnic groups, a
proportion seldom achieved in previous studies. The code scripts have been
made publicly available to facilitate replication.We hope that BOLD is poised
to be a valuable resource for health equity studies, that can be used to
develop pulse oximetry debiasing algorithms.

脉搏血氧仪（pulse oximeter）可无创检测外周动脉血氧饱和度（peripheral arterial oxygen saturation, SpO₂），而动脉血气测量（arterial blood gas measurement）为其金标准检测方法，对应动脉血氧饱和度（arterial oxygen saturation, SaO₂）。现有研究已证实，此类设备的性能表现存在明确的种族与族裔差异。BOLD是一套全新的综合性数据集，旨在凸显校正脉搏血氧仪检测偏差的重要性——此类偏差对肤色较深人群的影响尤为显著。该数据集通过标准化整合三类电子健康档案数据库（MIMIC-III、MIMIC-IV、eICU-CRD）构建而成，涵盖重症监护病房（intensive care unit, ICU）的住院病例数据。研究人员将配对的SpO₂与SaO₂检测结果进行时间对齐，并结合多种其他临床参数，以完整呈现每位患者的诊疗细节。数据集共包含49099组符合要求的配对检测数据，所有配对检测的时间间隔均不超过5分钟，血氧饱和度取值范围为70%~100%。尤为重要的是，约25%的数据来自少数种族与族裔群体，这一比例在既往相关研究中极为罕见。相关代码脚本已公开，以方便研究人员复现实验结果。我们期望，BOLD数据集能够成为健康公平研究领域的宝贵资源，并助力脉搏血氧仪偏差校正算法的开发。

搜集汇总

背景与挑战

背景概述

BOLD是一个专注于血氧饱和度测量偏差研究的数据集，整合了ICU电子健康记录数据，包含约4.9万对时间对齐的SpO2和SaO2测量值，其中25%来自少数种族和民族群体。该数据集旨在揭示脉搏血氧仪在深肤色人群中的性能差异，并提供公开代码支持健康公平算法的开发。