Machine learning derived risk prediction of anorexia nervosa

• Published in: BMC medical genomics Vol. 9; no. 1; p. 4
• Main Authors: Guo, Yiran, Wei, Zhi, Keating, Brendan J., Hakonarson, Hakon
• Format: Journal Article
• Language: English
• Published: London BioMed Central 20.01.2016; BioMed Central Ltd
• Subjects: Adolescent; Adult; Anorexia nervosa; Anorexia Nervosa - genetics; Biomedical and Life Sciences; Biomedicine; Care and treatment; Complications and side effects; Databases, Genetic; Development and progression; Female; Gene Expression; Genetic Predisposition to Disease; Genomics; Human Genetics; Humans; Logistic Models; Machine Learning; Microarrays; Patient outcomes; Reproducibility of Results; Research Article; Risk Factors; Sample Size; United States; Genome wide association; Risk prediction; Anorexia nervosa; Genotyping; Machine learning
• ISSN: 1755-8794; 1755-8794
• DOI: 10.1186/s12920-016-0165-x

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.