Purpose: Artificial intelligence (AI) is rapidly reshaping how radiology is practiced. Its susceptibility to biases, however, is a primary concern as more AI algorithms become available for widespread use. So far, there has been limited evaluation of how sociodemographic variables are reported in radiology AI research. This study aims to evaluate the presence and extent of sociodemographic reporting in human subjects radiology AI original research.
Methods: All human subjects original radiology AI articles published from January to December 2020 in the top six US radiology journals, as determined by impact factor, were reviewed. Reporting of any sociodemographic variables (age, gender, and race or ethnicity) as well as any sociodemographic-based results were extracted.
Results: Of the 160 included articles, 54% reported at least one sociodemographic variable, 53% reported age, 47% gender, and 4% race or ethnicity. Six percent reported any sociodemographic-based results. There was significant variation in reporting of at least one sociodemographic variable by journal, ranging from 33% to 100%.
Conclusions: Reporting of sociodemographic variables in human subjects original radiology AI research remains poor, putting the results and subsequent algorithms at increased risk of biases.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jacr.2023.03.014 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Distress and coping mechanisms among people with diabetes: cross-sectional assessment from an NCD screening clinic of a tertiary care hospital in North India.
Diabetol Metab Syndr
January 2025
Department of Endocrinology, Bharti Hospital, Karnal, Haryana, India.
Background: Of the numerous complications encountered by people with diabetes (PWD), the effect on mental health is concerning. Within mental health, diabetes distress (DD) occurs when a patient has unfavourable emotional stress while managing their condition, which can be managed by coping strategies but are less studied together in Indian settings. So, the present study aimed to determine the proportion of DD and associated factors and coping skills among the PWD.
View Article and Find Full Text PDFObjectives: This study aims to estimate the impact of the co-occurrence of behavioural risk factors on mortality in the Spanish adult population.
Design: Population-based cohort study based on data from the 2011-2012 Spanish National Health Survey and the 2014 European Health Survey (n=35 053 participants ≥15 years of age) both linked to mortality data as of December 2022. Risk factors included tobacco use, high-risk alcohol consumption, low adherence to the Mediterranean diet, leisure time sedentary lifestyle and body mass index outside the 18.
Abortion provision and characteristics of abortion patients in an academic medical center in Washington state before and after Dobbs.
Sex Reprod Healthc
January 2025
Department of Obstetrics and Gynecology, University of Washington, Seattle, WA, USA.
Objective: To examine abortion care in the largest academic medical center in Washington, a state protective of abortion rights, before and after the Supreme Court Dobbs decision.
Methods: This retrospective cohort study evaluated abortion provision at the University of Washington between January 1, 2022 and October 31, 2023. Data on patient sociodemographic and clinical characteristics were extracted from electronic medical records.
Urinary Fluoride Levels Among Youth in the National Health and Nutrition Examination Survey (NHANES) 2015-2016: Potential Differences According to Race.
Nutrients
January 2025
College of Public Health and Health Professions, University of Florida, Gainesville, FL 32611, USA.
Background/objectives: Urinary fluoride (UF) is the most well-established biomarker for fluoride exposure, and understanding its distribution can inform risk assessment for potential adverse systemic health effects. To our knowledge, this study is the first to report distributions of UF among youth according to sociodemographic factors in a nationally representative United States (US) sample.
Methods: The study included 1191 children aged 6-11 years and 1217 adolescents aged 12-19 years from the National Health and Nutrition Examination Survey (NHANES) 2015-2016.
Diet Quality, Metabolic Syndrome, and Nativity Status: Elucidating Metabolic Advantage and Disadvantage Among Non-US-Native and US-Native Populations Using NHANES Data (2013-2018).
Nutrients
January 2025
Office of Minority Health and Health Disparities Research, Georgetown Lombardi Comprehensive Cancer Center, Georgetown University, 1010 New Jersey Ave. SE, Washington, DC 20003, USA.
Background/objectives: Nutrient-poor diet quality is a major driver of the global burden of metabolic syndrome (MetS). The US ranks among the lowest in diet quality and has the highest rate of immigration, which may present unique challenges for non-US-native populations who experience changes in access to health-promoting resources. This study examined associations among MetS, nativity status, diet quality, and interaction effects of race-ethnicity among Hispanic, Asian, Black, and White US-native and non-US-native adults.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!