Predicting outcomes for very preterm babies using blood tests, microbes, and AI
Machine Learning and Multiomics for Predictive Models and Biomarker Discovery in Preterm Infants.
This project uses babies' medical information, blood and microbial data, and machine learning to predict which very preterm infants are at higher risk of death or serious complications.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Baylor College of Medicine NIH-funded |
| Lab location | 1 site (Houston, United States) |
| Project ID | NIH-11184264 on NIH RePORTER |
What this research studies
Researchers will combine clinical records from very low birth weight infants (born <32 weeks and <1500 g) with blood-based multi-omic measurements and microbial data to build prediction models using machine learning. They will analyze retrospective patient cohorts and biospecimens to find metabolic and microbial signatures linked to outcomes such as late-onset sepsis, NEC, bronchopulmonary dysplasia, severe ROP, and severe IVH. The team will search for biomarkers and microbial metabolites that could explain how microbes influence disease and survival. Findings aim to move neonatal care toward more personalized monitoring and targeted interventions for high-risk preterm infants.
Who could benefit from this research
Good fit: Ideal candidates are very preterm infants born before 32 weeks gestation and weighing under 1500 g, especially those cared for at or with data/samples available from participating neonatal centers.
Not a fit: Full-term infants, older children, or preterm infants without accessible clinical records or stored biospecimens would not be eligible and are unlikely to benefit directly from this project.
Why it matters
Potential benefit: If successful, this work could help clinicians identify high-risk preterm infants earlier so care and monitoring can be tailored to reduce complications.
How similar studies have performed: Previous studies have linked microbial imbalance and certain metabolites to preterm complications and some machine-learning risk models have shown promise, but fully integrated multi-omic prediction for these outcomes is still relatively new.
Where this research is happening
Houston, United States
- Baylor College of Medicine — Houston, United States (Active)
Researchers
- Principal investigator: Pammi, Mohan — Baylor College of Medicine
- Study coordinator: Pammi, Mohan
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.