# CIBMTR - Equity in post-HCT Survival Predictions — Data

来源：https://www.kaggle.com/competitions/equity-post-HCT-survival-predictions/data

采集时间：2026-10-19T19:44:30Z

The dataset consists of 59 variables related to hematopoietic stem cell transplantation (HSCT), encompassing a range of demographic and medical characteristics of both recipients and donors, such as age, sex, ethnicity, disease status, and treatment details. The primary outcome of interest is event-free survival, represented by the variable efs, while the time to event-free survival is captured by the variable efs_time. These two variables together encode the target for a censored time-to-event analysis. The data, which features equal representation across recipient racial categories including White, Asian, African-American, Native American, Pacific Islander, and More than One Race, was synthetically generated using the data generator from [synthcity](https://github.com/vanderschaarlab/synthcity), trained on a large cohort of real [**CIBMTR**](https://cibmtr.org/CIBMTR/About) data. 

We have used the SurvivalGAN method, introduced in the paper "[SurvivalGAN: Generating Time-to-Event Data for Survival Analysis](https://proceedings.mlr.press/v206/norcliffe23a.html)" which addresses the generation of synthetic survival data with special considerations for censoring.  SurvivalGAN is adept at capturing the intricate relationships and interactions among variables within survival data and their influence on time-to-event outcomes. This generative model utilizes a conditional Generative Adversarial Network (GAN) framework, which is specifically tailored to address the complexities of survival analysis, including the critical task of managing censored data. By conditioning on additional information such as censoring status and actual survival times, SurvivalGAN effectively learns the underlying distribution of the data, ensuring that the generated synthetic dataset retains the essential interactions among variables that are predictive of survival outcomes.

## Files
 - **train.csv** - the training set, with target `efs` (Event-free survival)
 - **test.csv** - the test set; your task is to predict the value of `efs` for this data
 - **sample_submission.csv** - a sample submission file in the correct format with all predictions set to 0.50
 - **data_dictionary.csv** - a list of all features and targets used in dataset and their descriptions

**Note:** The rerun test data contains approximately the same number of observations as the training data.