Neural interval-censored survival regression with feature selection
This addresses a gap in biomedical research for personalized medicine using high-dimensional data like omics, though it is incremental as it adapts existing neural network techniques to a specific problem.
The paper tackles the lack of non-linear regression and variable selection methods for interval-censored survival data by introducing a neural network framework based on Accelerated Failure Time models, which outperforms traditional algorithms in scenarios with non-linear relationships.
Survival analysis is a fundamental area of focus in biomedical research, particularly in the context of personalized medicine. This prominence is due to the increasing prevalence of large and high-dimensional datasets, such as omics and medical image data. However, the literature on non-linear regression algorithms and variable selection techniques for interval-censoring is either limited or non-existent, particularly in the context of neural networks. Our objective is to introduce a novel predictive framework tailored for interval-censored regression tasks, rooted in Accelerated Failure Time (AFT) models. Our strategy comprises two key components: i) a variable selection phase leveraging recent advances on sparse neural network architectures, ii) a regression model targeting prediction of the interval-censored response. To assess the performance of our novel algorithm, we conducted a comprehensive evaluation through both numerical experiments and real-world applications that encompass scenarios related to diabetes and physical activity. Our results outperform traditional AFT algorithms, particularly in scenarios featuring non-linear relationships.