Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/ai-care-consortium/survival-analysis-lung-cancer

https://github.com/ai-care-consortium/survival-analysis-lung-cancer

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 7 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.4%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: AI-CARE-Consortium
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 43 KB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 2
Created over 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme License

README.md

Survival Analysis for Lung Cancer Patients: A Comparison of Cox Regression and Machine Learning Models

DOI

Authors: Sebastian Germer, Christiane Rudolph, Louisa Labohm, Alexander Katalinic, Natalie Rath, Katharina Rausch, Bernd Holleczek, Heinz Handels and the AI-CARE consortium

How to Use

  • Install required packages (Pytorch, Scikit-Surv, Scikit-Learn, Tabnet, SHAP) via conda (see enviroment.yaml)
  • Edit the base_dir and the device for NN training ("cpu", "cuda:1",...) in your config.yaml

  • Run python parameterized_training_kfolds.py with the following arguments:

    • --imputation_method: Which imputation method to use ("none", "KNNImputer", "SimpleImputer", "MissForest")
    • --model: Which model to use ("rsf", "cox", "deep_surv", "tabnet")
    • --deep_surv_model: If model is deepsurv, which specific deepsurv model to use ("minimalistic_network")
    • --tnm: Use the TNM Subset instead of the UICC subset (optional)
    • --one-hot: Use one-hot encoding instead of label encoding (optional)
    • --loss: Which loss function to use ("pll", "mse")
    • --imputation_before: Apply imputation before data splitting in training, test and evaluation datasets
    • --dataset: Which dataset to use (vonko, aicare)")

  • Now, your chosen model is fitted and evaluated over 50 hyperparameter search epochs

  • For visualization, run python parameterized_evaluation_kfolds.py afterwards with the same parameters as above

How to Cite

Paper:

Germer, S., Rudolph, C., Labohm, L., Katalinic, A., Rath, N., Rausch, K., Holleczek, B., the AI-CARE Working Group & Handels, H. (2024). Survival analysis for lung cancer patients: A comparison of Cox regression and machine learning models. International Journal of Medical Informatics, 191. https://doi.org/10.1016/j.ijmedinf.2024.105607

Repository:

Germer, S., Rudolph, C., Labohm, L., Katalinic, A., Rath, N., Rausch, K., Holleczek, B. & Handels, H. (2024). Survival Analysis for Lung Cancer Patients: A Comparison of Cox Regression and Machine Learning Models. Zenodo. https://doi.org/10.5281/zenodo.10401220

Owner

  • Name: AI-CARE-Consortium
  • Login: AI-CARE-Consortium
  • Kind: organization

Code Repository of the AI-CARE Project

GitHub Events

Total
  • Fork event: 1
Last Year
  • Fork event: 1