Predicting Severe Asthma Exacerbations in Children Using Genetic Data
Author Information
Author(s): Xu Mousheng, Tantisira Kelan G, Wu Ann, Litonjua Augusto A, Chu Jen-hwa, Himes Blanca E, Damask Amy, Weiss Scott T
Primary Institution: Channing Laboratory, Brigham and Women's Hospital, Harvard Medical School
Hypothesis
Using random forests classifiers to select SNPs would result in an improved predictive model of asthma exacerbations.
Conclusion
A random forests algorithm can effectively extract and use information from a small number of samples to predict severe asthma exacerbations.
Supporting Evidence
- The study identified 127 cases of severe asthma exacerbations among 417 children.
- Using 160 SNPs improved the predictive model's accuracy to an AUC of 0.66.
- Clinical traits alone yielded a lower AUC of 0.54, indicating the importance of genetic factors.
Takeaway
Scientists used a computer program to look at many tiny differences in genes to help predict when kids with asthma might have a bad attack.
Methodology
The study used random forests classifiers to analyze SNPs and clinical traits to predict severe asthma exacerbations in children.
Limitations
The study had a limited sample size and potential for false positives with more SNPs used.
Participant Demographics
Participants were Caucasian children with mild to moderate asthma.
Statistical Information
P-Value
0.000266
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website