Comparison of machine learning tools for the prediction of AMD based on genetic, age, and diabetes-related variables in the Chinese population

• Published in: Regenerative therapy Vol. 15; pp. 180 - 186
• Main Authors: Hao, Shaofeng, Bai, Junye, Liu, Huimin, Wang, Lijun, Liu, Tao, Lin, Chaobin, Luo, Xiangguang, Gao, Junhui, Zhao, Jiangman, Li, Huilin, Tang, Hui
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.12.2020; Japanese Society for Regenerative Medicine; Elsevier
• Subjects: Age; AMD; Diabetes; Machine learning tools; Original; SNPs; AMD; SNPs; Diabetes; Machine learning tools; Age
• ISSN: 2352-3204; 2352-3204
• DOI: 10.1016/j.reth.2020.09.001

Age-related macular degeneration (AMD) is the main cause of visual impairment and the most important cause of blindness in older people. However, there is currently no effective treatment for this disease, so it is necessary to establish a risk model to predict AMD development. This study included a total of 202 subjects, comprising 82 AMD patients and 120 control subjects. Sixty-six single-nucleotide polymorphisms (SNPs) were identified using the MassArray assay. Considering 14 independent clinical variables as well as SNPs, four predictive models were established in the training set and evaluated by the confusion matrix, area under the receiver operating characteristic (ROC) curve (AUROC). The difference distributions of the 14 independent clinical features between the AMD and control groups were tested using the chi-squared test. Age and diabetes were adjusted using logistic regression analysis and the “genomic-control” method was used for multiple testing correction. Three SNPs (rs10490924, OR = 1.686, genomic-control corrected p-value (GC) = 0.030; rs2338104, OR = 1.794, GC = 0.025 and rs1864163, OR = 2.125, GC = 0.038) were significant risk factors for AMD development. In the training set, four models obtained AUROC values above 0.72. We believe machine learning tools will be useful for the early prediction of AMD and for the development of relevant intervention strategies.