Improving birth outcomes by addressing racial disparities in predictive models.
Algorithmic fairness in predictive models to eliminate disparities in adverse infant outcomes: A case for race
This study is looking at ways to help babies be born healthier by creating tools that take into account race and ethnicity, especially to understand and reduce the differences in low birthweight rates between Black and White infants, so that healthcare providers can make better decisions and improve care for all families.
Quick facts
| Grant type | Career grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Univ of Arkansas for Med Scis NIH-funded |
| Lab location | 1 site (Little Rock, United States) |
| Project ID | NIH-10881738 on NIH RePORTER |
What this research studies
This research investigates how to improve birth outcomes for infants by developing predictive models that account for race and ethnicity. It aims to address the significant disparities in low birthweight rates between Black and White infants by using an algorithmic fairness framework. The study will analyze medical claims and birth certificate data to create models that not only predict low birthweight but also ensure fairness in their predictions across different racial groups. By including race/ethnicity data, the research seeks to provide evidence-based recommendations for healthcare payers to better allocate resources and improve health outcomes.
Who could benefit from this research
Good fit: Ideal candidates for this research include pregnant individuals, particularly those from Black and other minority racial backgrounds, who may be at risk for low birthweight births.
Not a fit: Patients who are not pregnant or those who do not belong to racial or ethnic groups disproportionately affected by low birthweight may not benefit from this research.
Why it matters
Potential benefit: If successful, this research could lead to more equitable healthcare practices that reduce the rates of low birthweight and improve overall infant health outcomes.
How similar studies have performed: Other research has shown that incorporating race and ethnicity into predictive models can lead to more accurate and fair healthcare outcomes, suggesting that this approach has potential for success.
Where this research is happening
Little Rock, United States
- Univ of Arkansas for Med Scis — Little Rock, United States (Active)
Researchers
- Principal investigator: Brown, Clare — Univ of Arkansas for Med Scis
- Study coordinator: Brown, Clare
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.