Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A novel neural network-based survival analysis model.

Antonio Eleuteri1, Roberto Tagliaferri, Leopoldo Milano

  • 1DMA, Università di Napoli Federico II, Naples, Italy. eleuteri@na.infn.it

Neural Networks : the Official Journal of the International Neural Network Society
|July 10, 2003
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Investigating infection and clinical data to predict effective antibiotic therapy and monitor resistance trends.

International journal of infectious diseases : IJID : official publication of the International Society for Infectious Diseases·2026
Same author

Impact of preoperative education on early outcomes following hip and knee arthroplasty : a 21,000-patient multicentre NHS analysis.

Bone & joint open·2026
Same author

Multigene assays in early breast cancer: Current evidence, limits and future directions.

Cancer treatment reviews·2026
Same author

Effect of Nitisinone on Aortic Stenosis Disease Progression in Patients With Alkaptonuria: An Analysis of the Suitability of Nitisinone in Alkaptonuria (SONIA) 2 Study.

Cureus·2026
Same author

Vitreoretinal Surgery for Intraocular Complications Following Radiotherapy Treatment of Uveal Melanoma.

Cancers·2026
Same author

Tumour control, eye retention and visual acuity after radiotherapy for choroidal melanoma.

BMJ open ophthalmology·2026

This study introduces a novel feedforward neural network for survival probability estimation, outperforming standard models. The approach uses a hierarchical Bayesian framework for accurate survival analysis with system features.

Area of Science:

  • Machine Learning
  • Survival Analysis
  • Bayesian Statistics

Background:

  • Standard survival analysis models are often linear and limited in capturing complex relationships.
  • Accurate estimation of survival probability is crucial in various fields, including medicine and engineering.

Purpose of the Study:

  • To present a generalized feedforward neural network architecture for survival probability estimation.
  • To approximate survival probability conditional on system features using a novel network architecture.
  • To evaluate the performance of the proposed model against established methods.

Main Methods:

  • Development of a feedforward neural network architecture.
  • Implementation within a hierarchical Bayesian framework.
  • Comparative experiments using synthetic and real-world datasets.

Related Experiment Videos

Main Results:

  • The proposed neural network model demonstrates superior performance compared to standard survival models.
  • The model effectively approximates survival probability by incorporating system features.
  • The hierarchical Bayesian framework provides a robust structure for the network.

Conclusions:

  • The novel feedforward neural network offers a powerful and generalized approach to survival probability estimation.
  • This method enhances the accuracy and applicability of survival analysis, particularly for complex systems.
  • The findings suggest a promising direction for advancing survival analysis techniques through deep learning.