Multitask Boosting for Survival Analysis with Competing Risks

Authors: Alexis Bellot, Mihaela van der Schaar

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the performance of our algorithm on synthetic and real data. ... 5 Experiments ... 5.2 Synthetic Studies ... 5.3 Real data studies: SEER
Researcher Affiliation Academia Alexis Bellot University of Oxford Oxford, United Kingdom alexis.bellot@eng.ox.ac.uk Mihaela van der Schaar University of Oxford and The Alan Turing Institute London, United Kingdom mschaar@turing.ac.uk
Pseudocode Yes Algorithm 1 Multitask Boosting
Open Source Code No The paper does not provide any concrete access information (e.g., a link or explicit statement of code release) for the source code.
Open Datasets Yes We investigate a patient population extracted from the Surveillance, Epidemiology, and End Results (SEER) repository similarly to [2]. ... We generate 5 data sets (by sampling variables and parameters randomly) of 1000 instances for each individual scenario and set a random 50% of the population to be uniformly censored.
Dataset Splits Yes Deep Learning architecture (Deep Hit) [18] with hyperparameters optimized with a validation set. ... these are averages over 4 fold cross-validation estimates and confidence bands are standard deviations.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory) used for running the experiments.
Software Dependencies No The paper mentions the use of statistical methods and models but does not specify any software dependencies with version numbers (e.g., specific Python libraries or statistical packages with their versions).
Experiment Setup Yes On all experiments we train SMTBoost with a tree-depth of 3 and 250 boosting iterations, our default parameter settings.