{
  "fetched_at": "2026-10-20T00:31:09Z",
  "source_url": "https://www.kaggle.com/competitions/cirrhosis-outcomes-prediction/data",
  "pages": [
    {
      "name": "Objectives",
      "content": "- Develop a multi-class classification model to predict patient outcomes.\n- Explore various modeling techniques, including but not limited to decision trees, ensemble methods, and neural networks.\n- Optimize models for accuracy, precision, and recall to achieve the best possible predictions.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "1. **Eligibility**\n- Open to everyone. Participants must follow Kaggle's terms of service.\n2. **Dataset Use**\n- Use the provided dataset for training and validation.\n- You can use external data, but must mention it in your submission.\n3. **Submissions**\n- You can submit up to 5 entries per day.\n- Each submission should include a model and the code used for evaluation.\n4. **Team Collaboration**\n- Teams can have up to [insert number, e.g., 5] members.\n- Each team must have a leader for submissions.\n5. **Fair Play**\n- All work must be original. Plagiarism will lead to disqualification.\n6. **Timeline**\nThe competition runs from **01.10.2024** to **29.11.2024**.\n\n*Ask questions in the competition forums. Be respectful and helpful.*",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "The dataset for this competition (both train and test) was generated from a deep learning model trained on the [Cirrhosis Patient Survival Prediction](https://www.kaggle.com/datasets/joebeachcapital/cirrhosis-patient-survival-prediction) dataset. Feature distributions are close to, but not exactly the same, as the original. Feel free to use the original dataset as part of this competition, both to explore differences as well as to see whether incorporating the original in training improves model performance.\n\n## Files\n\n*   **train.csv** - the training dataset; `Status` is the categorical target; `C` (censored) indicates the patient was alive at `N_Days`, `CL` indicates the patient was alive at `N_Days` due to liver a transplant, and `D` indicates the patient was deceased at `N_Days`.\n*   **test.csv** - the test dataset; your objective is to predict the probability of each of the three `Status` values, e.g., `Status_C`, `Status_CL`, `Status_D`.\n*   **sample_submission.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Welcome to the Multi-Class Prediction of Cirrhosis Outcomes Challenge! In this competition, participants will leverage a dataset derived from real-world patient records to build predictive models for liver cirrhosis outcomes. The primary goal is to accurately classify patient outcomes into multiple categories based on clinical and laboratory data.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions will be evaluated based on a specified metric (e.g., accuracy, F1 score) on a hidden test set. Detailed evaluation criteria will be provided, ensuring transparency and fairness in the competition.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}