Implicit bias in Critical Care Data: Factors affecting sampling frequencies and missingness patterns of clinical and biological variables in ICU Patients

Author:

Shi Junming (Seraphina)ORCID,Hubbard Alan E.ORCID,Fong NicholasORCID,Pirracchio RomainORCID

Abstract

AbstractThe presence of missing values in Electronic Health Records (EHRs) is a widespread and inescapable issue. Publicly available data sets mirror the incompleteness found in EHRs. Although the existing literature largely approaches missing data as a random phenomenon, the mechanisms behind these missing values are often not random with respect to important characteristics of the patients. Similarly, the sampling frequency of clinical or biological parameters is likely informative. The possible informative nature of patterns in missing data is often overlooked. For both missingness and sampling frequency, we hypothesize that the underlying mechanism may be at least consistent with implicit bias.To investigate this important issue, we introduce a novel analytical framework designed to rigorously examine missing data and sampling frequency in EHRs. We utilize the MIMIC-III dataset as a case study, given its frequent use in training machine learning models for healthcare applications. Our approach incorporates Targeted Machine Learning (TML) to study the impact of a series of demographic variables, including protected attributes such as age, sex, race, and ethnicity on the rate of missing data and sampling frequency for key clinical and biological variables in critical care settings. Our results expose underlying differences in the sampling frequency and missing data patterns of vital sign measurements and laboratory tests between different demographic groups. In addition, we find that these measurement patterns can provide significant predictive insights into patient outcomes. Consequently, we urge a reevaluation of the conventional understanding of missing data and sampling frequencies in EHRs. Acknowledging and addressing these biases is essential for advancing equitable and accurate healthcare through machine learning applications.

Publisher

Cold Spring Harbor Laboratory

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3