AI Analysis of Fetal Growth Restriction and Risks
Author Information
Author(s): Zimmerman Raquel M., Hernandez Edgar J., Yandell Mark, Tristani-Firouzi Martin, Silver Robert M., Grobman William, Haas David, Saade George, Steller Jonathan, Blue Nathan R.
Hypothesis
Can a probabilistic graphical model improve understanding of perinatal morbidity risk in fetal growth restriction?
Conclusion
Probabilistic graphical models can identify significant risk factors in fetal growth restriction that are not recognized in current clinical guidelines.
Supporting Evidence
- The model identified 16 key variables that influence perinatal morbidity risk.
- AUC for the model was 0.83, indicating good performance in risk discrimination.
- Certain fetal growth restriction scenarios showed nearly 10-fold differences in morbidity risk.
Takeaway
This study used AI to find out which pregnancies with fetal growth restriction are at higher risk for problems, helping doctors make better decisions.
Methodology
The study used data from 9,558 pregnancies to develop and validate a probabilistic graphical model to assess perinatal morbidity risk.
Potential Biases
Potential biases in data collection and selection of cohorts.
Limitations
The model may not account for all variables affecting perinatal outcomes.
Participant Demographics
Pregnancies delivered at ≥ 20 weeks.
Statistical Information
Confidence Interval
95% CI 0.79–0.87
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website