Deep Neural Network for Cure Fraction Survival Analysis Using Pseudo Values

Background:The hidden assumption in most of survival analysis models is the occurrence of the event of interest for all study units. The violation of this assumption occurs in several situations. For example, in medicine, some patients may never have cancer, and some may never face Alzheimer.  Igno...

Full description

Saved in:
Bibliographic Details
Main Author: Ola Abuelamayem
Format: Article
Language:English
Published: Tehran University of Medical Sciences 2025-04-01
Series:Journal of Biostatistics and Epidemiology
Subjects:
Online Access:https://jbe.tums.ac.ir/index.php/jbe/article/view/1503
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235860514406400
author Ola Abuelamayem
author_facet Ola Abuelamayem
author_sort Ola Abuelamayem
collection DOAJ
description Background:The hidden assumption in most of survival analysis models is the occurrence of the event of interest for all study units. The violation of this assumption occurs in several situations. For example, in medicine, some patients may never have cancer, and some may never face Alzheimer.  Ignoring such information and analyzing the data with traditional survival models may lead to misleading results. Analyzing long term survivals can be performed using both traditional and neural networks. There has been an increasing interest in modeling lifetime data using neural network. However, for long-term survivors only one neural network was introduced to estimate the uncured proportion together with the EM algorithm to account for the latency part. Neural network in survival analysis requires special cost function to account for censoring. Methods: In this paper, we extend the neural network using pseudo values to analyze cure fraction model. It neither requires the use of special cost function nor the EM algorithm. Results: The network is applied on both synthetic and Melanoma real datasets to evaluate its performance. We compared the results using goodness of fit methods in both datasets with cox proportional model using EM algorithm. Conclusion: The proposed neural network has the flexibility of analyzing data without parametric assumption or special cost function. Also, it has the advantage of analyzing the data without the need of EM algorithm. Comparing the results with cox proportional model using EM algorithm, the proposed neural network performed better.
format Article
id doaj-art-6ef1bd1e76c040c3ba0dea79bf7715c6
institution Kabale University
issn 2383-4196
2383-420X
language English
publishDate 2025-04-01
publisher Tehran University of Medical Sciences
record_format Article
series Journal of Biostatistics and Epidemiology
spelling doaj-art-6ef1bd1e76c040c3ba0dea79bf7715c62025-08-20T04:02:36ZengTehran University of Medical SciencesJournal of Biostatistics and Epidemiology2383-41962383-420X2025-04-0110410.18502/jbe.v10i4.18524Deep Neural Network for Cure Fraction Survival Analysis Using Pseudo ValuesOla Abuelamayem0Dr Background:The hidden assumption in most of survival analysis models is the occurrence of the event of interest for all study units. The violation of this assumption occurs in several situations. For example, in medicine, some patients may never have cancer, and some may never face Alzheimer.  Ignoring such information and analyzing the data with traditional survival models may lead to misleading results. Analyzing long term survivals can be performed using both traditional and neural networks. There has been an increasing interest in modeling lifetime data using neural network. However, for long-term survivors only one neural network was introduced to estimate the uncured proportion together with the EM algorithm to account for the latency part. Neural network in survival analysis requires special cost function to account for censoring. Methods: In this paper, we extend the neural network using pseudo values to analyze cure fraction model. It neither requires the use of special cost function nor the EM algorithm. Results: The network is applied on both synthetic and Melanoma real datasets to evaluate its performance. We compared the results using goodness of fit methods in both datasets with cox proportional model using EM algorithm. Conclusion: The proposed neural network has the flexibility of analyzing data without parametric assumption or special cost function. Also, it has the advantage of analyzing the data without the need of EM algorithm. Comparing the results with cox proportional model using EM algorithm, the proposed neural network performed better. https://jbe.tums.ac.ir/index.php/jbe/article/view/1503Cure fractionDeep learningNeural NetworkPseudo Values.
spellingShingle Ola Abuelamayem
Deep Neural Network for Cure Fraction Survival Analysis Using Pseudo Values
Journal of Biostatistics and Epidemiology
Cure fraction
Deep learning
Neural Network
Pseudo Values.
title Deep Neural Network for Cure Fraction Survival Analysis Using Pseudo Values
title_full Deep Neural Network for Cure Fraction Survival Analysis Using Pseudo Values
title_fullStr Deep Neural Network for Cure Fraction Survival Analysis Using Pseudo Values
title_full_unstemmed Deep Neural Network for Cure Fraction Survival Analysis Using Pseudo Values
title_short Deep Neural Network for Cure Fraction Survival Analysis Using Pseudo Values
title_sort deep neural network for cure fraction survival analysis using pseudo values
topic Cure fraction
Deep learning
Neural Network
Pseudo Values.
url https://jbe.tums.ac.ir/index.php/jbe/article/view/1503
work_keys_str_mv AT olaabuelamayem deepneuralnetworkforcurefractionsurvivalanalysisusingpseudovalues