Search Articles

View query in Help articles search

Search Results (1 to 10 of 54 Results)

Download search results: CSV END BibTex RIS


Role and Use of Race in Artificial Intelligence and Machine Learning Models Related to Health

Role and Use of Race in Artificial Intelligence and Machine Learning Models Related to Health

Appropriate inclusion of race within AI and ML models can identify differences in the outcomes of people with different backgrounds, creating opportunities for mitigation [2]. Yet, numerous examples exist of inappropriate inclusion of race or proxies of race in health-related models, which can harm large segments of the population [3].

Martin C Were, Ang Li, Bradley A Malin, Zhijun Yin, Joseph R Coco, Benjamin X Collins, Ellen Wright Clayton, Laurie L Novak, Rachele Hendricks-Sturrup, Abiodun O Oluyomi, Shilo Anders, Chao Yan

J Med Internet Res 2025;27:e73996

Differential Analysis of Age, Gender, Race, Sentiment, and Emotion in Substance Use Discourse on Twitter During the COVID-19 Pandemic: A Natural Language Processing Approach

Differential Analysis of Age, Gender, Race, Sentiment, and Emotion in Substance Use Discourse on Twitter During the COVID-19 Pandemic: A Natural Language Processing Approach

Substance use (SU) prevalence varies across demographics such as age, gender, race, and ethnicity. During the COVID-19 pandemic, these differences became more pronounced. The pandemic not only increased global SU, with overdose deaths rising by 29.4% [1], but also exacerbated societal and racial inequalities [2,3] and significantly impacted mental health [4-7].

Julina Maharjan, Ruoming Jin, Jennifer King, Jianfeng Zhu, Deric Kenne

JMIR Infodemiology 2025;5:e67333

Association of Social Media Recruitment and Depression Among Racially and Ethnically Diverse Metabolic and Bariatric Surgery Candidates: Prospective Cohort Study

Association of Social Media Recruitment and Depression Among Racially and Ethnically Diverse Metabolic and Bariatric Surgery Candidates: Prospective Cohort Study

Covariates including age, sex, race and ethnicity, BMI, education level, and perceived financial well-being were obtained through self-report. Age was treated as a continuous variable, representing the participants’ age in years. Sex was a categorical variable, categorized as male, female, or other. Race and ethnicity were also categorical variables, encompassing diverse categories such as NHW, NHB, Hispanic, and Other.

Jackson M Francis, Sitapriya S Neti, Dhatri Polavarapu, Folefac Atem, Luyu Xie, Olivia Kapera, Matthew S Mathew, Elisa Marroquin, Carrie McAdams, Jeffrey Schellinger, Sophia Ngenge, Sachin Kukreja, Benjamin E Schneider, Jaime P Almandoz, Sarah E Messiah

JMIR Form Res 2025;9:e58916

Use of mHealth Technology for Improving Exercise Adherence in Patients With Heart Failure: Systematic Review

Use of mHealth Technology for Improving Exercise Adherence in Patients With Heart Failure: Systematic Review

Specifically, this review was done to (1) describe study characteristics of m Health interventions for exercise adherence in HF including details of sample demographics, sample sizes, exercise program, and theoretical frameworks; (2) summarize types of m Health technology used to improve exercise adherence in patients with HF; (3) highlight how the term “adherence” was defined and how it was measured across m Health studies and adherence achieved; and (4) highlight the effect of age, sex, race, NYHA functional

Pallav Deka, Erin Salahshurian, Teresa Ng, Susan W Buchholz, Leonie Klompstra, Windy Alonso

J Med Internet Res 2025;27:e54524

Addressing Information Biases Within Electronic Health Record Data to Improve the Examination of Epidemiologic Associations With Diabetes Prevalence Among Young Adults: Cross-Sectional Study

Addressing Information Biases Within Electronic Health Record Data to Improve the Examination of Epidemiologic Associations With Diabetes Prevalence Among Young Adults: Cross-Sectional Study

We estimated odds ratios (OR) for diabetes by race or ethnicity and asthma status under 4 EHR-based estimation methods that we describe herein. First, “naïve” models were estimated by fitting a logistic regression model for observed diabetes status (DM*) on the total sample (n=454,612).

Sarah Conderino, Rebecca Anthopolos, Sandra S Albrecht, Shannon M Farley, Jasmin Divers, Andrea R Titus, Lorna E Thorpe

JMIR Med Inform 2024;12:e58085

Implementation and Evaluation of a Home-Based Pre-Exposure Prophylaxis Monitoring Option: Protocol for a Randomized Controlled Trial

Implementation and Evaluation of a Home-Based Pre-Exposure Prophylaxis Monitoring Option: Protocol for a Randomized Controlled Trial

Younger age, Black race, and unstable or lower income are each associated with discontinuations and being lost to follow-up [14]. We have observed similar levels of Pr EP retention in the PHSKC Sexual Health Clinic (SHC), with 40% of Pr EP users discontinuing the intervention at least once within 12 months [15].

Chase Cannon, Katherine Holzhauer, Matthew Golden

JMIR Res Protoc 2024;13:e56587

Racial and Ethnic Differences in Mobile App Use for Meeting Sexual Partners Among Young Men Who Have Sex With Men and Young Transgender Women: Cross-Sectional Study

Racial and Ethnic Differences in Mobile App Use for Meeting Sexual Partners Among Young Men Who Have Sex With Men and Young Transgender Women: Cross-Sectional Study

Despite substantial evidence that Black YMSM-YTW experience sexual racism in online dating, there is no evidence about whether this results in quantifiable differences in online sexual partnering by race and ethnicity. Research consistently finds high levels of within–race and ethnicity sexual partnering among young MSM [7,13-17]. A recent study suggested that sexual exclusivity among Black sexual minority men may be partially protective against the psychological impacts of racial discrimination [18].

Kathryn Risher, Patrick Janulis, Elizabeth McConnell, Darnell Motley, Pedro Alonso Serrano, Joel D Jackson, Alonzo Brown, Meghan Williams, Daniel Mendez, Gregory Phillips II, Joshua Melville, Michelle Birkett

JMIR Public Health Surveill 2024;10:e54215

The Double-Edged Sword of Online Learning for Ethnoracial Differences in Adolescent Mental Health During Late Period of the COVID-19 Pandemic in the United States: National Survey

The Double-Edged Sword of Online Learning for Ethnoracial Differences in Adolescent Mental Health During Late Period of the COVID-19 Pandemic in the United States: National Survey

By “minoritized,” we refer to systemic oppression across a range of contexts by the majority group (in the United States, by White communities), and by “ethnoracial” we recognize that cultural groups are typically racialized, meaning treated as a race, and thus use a term that combines “ethnicity” and “race” [8]. Ethnoracial disparities are, therefore, inequalities along ethnic and racial group lines.

Celeste Campos-Castillo, Vijaya Tamla Rai, Linnea I Laestadius

JMIR Form Res 2024;8:e55759

Digitally Enabled Peer Support and Social Health Platform for Vulnerable Adults With Loneliness and Symptomatic Mental Illness: Cohort Analysis

Digitally Enabled Peer Support and Social Health Platform for Vulnerable Adults With Loneliness and Symptomatic Mental Illness: Cohort Analysis

We used ANOVA to assess engagement and changes in clinical outcomes by age, race/ethnicity, and gender. The study was approved by the WCG Institutional Review Board (Wisdo.001.1/26/2023). Since all data were routinely collected during the intervention, this protocol was considered exempt from additional consent. All data were deidentified. Participants received 1 year of free access to the platform but no other compensation.

Dena Bravata, Daniel Russell, Annette Fellows, Ron Goldman, Elizabeth Pace

JMIR Form Res 2024;8:e58263