Participant Flow Diagrams for Health Equity in AI Research
Preprint
Abstract
Biases in sample creation can arise at any study phase, including initial patient recruitment, exclusion criteria, input-level exclusion and outcome-level exclusion, and often reflect the underrepresentation or exclusion of demographic groups historically disadvantaged in medical research. The use of non-representative samples to construct clinical algorithms in artificial intelligence (AI) and machine learning (ML) applications may further amplify this selection bias. Building on the “Data Cards” initiative for transparency in AI research, we advocate for the addition of a detailed participant flow diagram for AI studies, emphasizing the need to detail excluded participant demographic characteristics at every study phase. This tracking of excluded participants enhances understanding of potential algorithmic biases before their clinical implementation, and thus deserves to be detailed in any medical AI study. We include both a model for this flow diagram as well as a brief case study explaining how it could be implemented in practice. Through standardized reporting of participant flow diagrams, we can better gauge the potential inequity embedded in AI applications, facilitating more reliable and equitable clinical algorithms.Keywords
This publication has 48 references indexed in Scilit:
- Race/Ethnic Differences in the Associations of the Framingham Risk Factors with Carotid IMT and Cardiovascular EventsPLOS ONE, 2015
- Handling missing data in RCTs; a review of the top medical journalsBMC Medical Research Methodology, 2014
- The statistical significance of randomized controlled trial results is frequently fragile: a case for a Fragility IndexJournal of Clinical Epidemiology, 2014
- Effect of race/ethnicity on participation in HIV vaccine trials and comparison to other trials of biomedical preventionHuman Vaccines & Immunotherapeutics, 2014
- Inclusion of minorities and women in cancer clinical trials, a decade later: Have we improved?Cancer, 2013
- CONSORT 2010 Explanation and Elaboration: updated guidelines for reporting parallel group randomised trialsBMJ, 2011
- Recruitment and retention results for a population-based cervical cancer biobehavioral clinical trialGynecologic Oncology, 2011
- Strengthening the Reporting of Observational Studies in Epidemiology (STROBE): Explanation and ElaborationPLOS Medicine, 2007
- External Validity of Clinical Trials in Acute Myocardial InfarctionArchives of internal medicine (1960), 2007
- Reporting the study populations of clinical trialsJournal of Clinical Epidemiology, 2000