Tools to spot hidden bias in how metal mixtures affect young children's development
Machine Learning remedies to unmeasured confounding biases in environmental mixture studies
This project builds computer methods to find and adjust for hidden sources of bias when researchers look at how mixtures of metals in the environment affect young children, using data from a Bangladeshi birth cohort.
Quick facts
| Grant type | R21 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Columbia University Health Sciences NIH-funded |
| Lab location | 1 site (New York, United States) |
| Project ID | NIH-11184447 on NIH RePORTER |
What this research studies
If you're a parent or caregiver, this work aims to make studies about environmental metal exposures and child development more trustworthy. The team will create new sensitivity-analysis methods that use machine learning to detect and correct for hidden (unmeasured) factors that can skew results when multiple pollutants are present. They will apply these methods to data from a birth cohort of Bangladeshi mothers and infants to study joint effects of metal exposures on child development. Finally, they will package the methods into user-friendly software so other researchers and public-health teams can use them.
Who could benefit from this research
Good fit: Ideal candidates for the human part are pregnant women and infants enrolled in the Bangladeshi birth cohort with measured metal exposures and developmental follow-up data.
Not a fit: People without measured exposure or developmental data, or those with unrelated health conditions, would not directly benefit from participating in this specific cohort analysis.
Why it matters
Potential benefit: If successful, this could make research on environmental mixtures and child development more reliable, supporting better public-health guidance and policies to protect children.
How similar studies have performed: Existing quantitative-bias methods generally handle single pollutants or single hidden confounders, so extending machine-learning sensitivity analyses to complex mixtures is relatively new and not yet widely proven.
Where this research is happening
New York, United States
- Columbia University Health Sciences — New York, United States (Active)
Researchers
- Principal investigator: Valeri, Linda — Columbia University Health Sciences
- Study coordinator: Valeri, Linda
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.