Kaplan Meier

Description

This vantage6 algorithm computes the Kaplan-Meier curve in a federated manner. Hence, it allows for the estimation of survival probabilities across distributed datasets without sharing patient-specific information.

The Kaplan-Meier algorithm is a non-parametric statistic used to estimate the survival function from lifetime data. In medical research, it is often used to measure the fraction of patients that are alive for a certain amount of time after treatment.

Authors

• 2. Gottardelli [1] benedetta.gottardelli@gmail.com

• 1. Lobo Gomes [2] aiara.lobogomes@maastro.nl

• I. Zhovannik [3] ivan.zhovannik@medicaldataworks.nl

• 12. Sanchez [3] luis.sanchezgomez@medicaldataworks.nl

• F.C. Martin [4] f.martin@iknl.nl

• A.J. van Gestel [4] a.vangestel@iknl.nl

Thanks to M.J. Bijlsma [4] for the suggestion of applying Poisson noise to the event times.

[1]

Università Cattolica del Sacro Cuore, Italy

[2]

MAASTRO Clinic, The Netherlands

[3] (1,2)

Medical Data Works (MDW), The Netherlands

[4] (1,2,3)

Netherlands Comprehensive Cancer Organisation (IKNL), The Netherlands

Source code

Source code is available on GitHub.

Contents

• Implementation
  • Overview
  • Partials
  • Central
• How to use
  • Input arguments
  • Python client example
• Privacy
  • Guards
  • Data sharing
  • Vulnerabilities to known attacks
• Validation
• References
  • Cite this implementation
  • Used sources