Format

Send to

Choose Destination
BMC Med Genomics. 2016 Jan 20;9:4. doi: 10.1186/s12920-016-0165-x.

Machine learning derived risk prediction of anorexia nervosa.

Author information

1
The Center for Applied Genomics, Abramson Research Center, The Children's Hospital of Philadelphia, Philadelphia, PA, 19104, USA. guoy@email.chop.edu.
2
Department of Computer Science, New Jersey Institute of Technology, Newark, NJ, 07102, USA.
3
The Center for Applied Genomics, Abramson Research Center, The Children's Hospital of Philadelphia, Philadelphia, PA, 19104, USA.
4
Department of Pediatrics, School of Medicine University of Pennsylvania, Philadelphia, PA, 19104, USA.
5
The Center for Applied Genomics, Abramson Research Center, The Children's Hospital of Philadelphia, Philadelphia, PA, 19104, USA. hakonarson@email.chop.edu.
6
Department of Pediatrics, School of Medicine University of Pennsylvania, Philadelphia, PA, 19104, USA. hakonarson@email.chop.edu.

Abstract

BACKGROUND:

Anorexia nervosa (AN) is a complex psychiatric disease with a moderate to strong genetic contribution. In addition to conventional genome wide association (GWA) studies, researchers have been using machine learning methods in conjunction with genomic data to predict risk of diseases in which genetics play an important role.

METHODS:

In this study, we collected whole genome genotyping data on 3940 AN cases and 9266 controls from the Genetic Consortium for Anorexia Nervosa (GCAN), the Wellcome Trust Case Control Consortium 3 (WTCCC3), Price Foundation Collaborative Group and the Children's Hospital of Philadelphia (CHOP), and applied machine learning methods for predicting AN disease risk. The prediction performance is measured by area under the receiver operating characteristic curve (AUC), indicating how well the model distinguishes cases from unaffected control subjects.

RESULTS:

Logistic regression model with the lasso penalty technique generated an AUC of 0.693, while Support Vector Machines and Gradient Boosted Trees reached AUC's of 0.691 and 0.623, respectively. Using different sample sizes, our results suggest that larger datasets are required to optimize the machine learning models and achieve higher AUC values.

CONCLUSIONS:

To our knowledge, this is the first attempt to assess AN risk based on genome wide genotype level data. Future integration of genomic, environmental and family-based information is likely to improve the AN risk evaluation process, eventually benefitting AN patients and families in the clinical setting.

PMID:
26792494
PMCID:
PMC4721143
DOI:
10.1186/s12920-016-0165-x
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for BioMed Central Icon for PubMed Central
Loading ...
Support Center