A0451
Title: Neural network on interval-censored data with application to the prediction of Alzheimer's disease
Authors: Tao Sun - Renmin University of China (China) [presenting]
Ying Ding - University of Pittsburgh (United States)
Abstract: Alzheimer's disease (AD) is a progressive and polygenic disorder that affects millions of individuals each year. Given that there have been few effective treatments yet for AD, it is highly desirable to develop an accurate model to predict the full disease progression profile based on an individual's genetic characteristics for early prevention and clinical management. Data composed of all four phases of the Alzheimer's Disease Neuroimaging Initiative (ADNI) study is used, including 1,740 individuals with 8 million genetic variants. Several challenges are tackled in this data, characterized by large-scale genetic data, interval-censored outcomes due to intermittent assessments, and left truncation in one study phase (ADNIGO). Specifically, a semiparametric transformation model is first developed on interval-censored and left-truncated data, and parameters are estimated through a sieve approach. Then, a computationally efficient generalized score test is proposed to identify variants associated with AD progression. Next, a novel neural network is implemented on interval-censored data (NN-IC) to construct a prediction model using top variants identified from the genome-wide test. Comprehensive simulation studies show that the NN-IC outperforms several existing methods in terms of prediction accuracy. Finally, the NN-IC is applied to the full ADNI data, and subgroups with differential progression risk profiles are successfully identified.
