Neural interval-censored survival regression with feature selection

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 nonlinear regres...

Descripción completa

Detalles Bibliográficos
Autores: Meixide, C.G., Matabuena, M., Abraham, L., Kosorok, M.R.
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/381357
Acceso en línea:http://hdl.handle.net/10261/381357
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85198642338&doi=10.1002%2fsam.11704&partnerID=40&md5=854f6fd0389ed86944438f6d71d5a204
Access Level:acceso abierto
Palabra clave:Diabetes research
High-dimensional data
Interval-censoring
Survival analysis
Nonlinear regression
Descripción
Sumario: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 nonlinear regression algorithms and variable selection techniques for interval-censoring is either limited or nonexistent, 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 nonlinear relationships. © 2024 The Author(s). Statistical Analysis and Data Mining: The ASA Data Science Journal published by Wiley Periodicals LLC.