{
  "fetched_at": "2026-10-24T06:21:26Z",
  "source_url": "https://www.kaggle.com/competitions/aws-challenge-2020-phase-2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "# Train and Test Folders\nThe dataset is split into a train folder (aws-challenge-phase2-train) and test folder (aws-challenge-phase2-test).\n\nFor each folder, there are five csv files:\n\n- casevisitsyn – visits and encounters\n- labresultsyn – lab tests and results\n- patientdemosyn – patient demographics\n- surgicalsyn – surgery and procedures\n- medicationordersyn – medication orders\n\n# Dataset Description\nA detailed description of the dataset can be found in **MedicalSyn-Dataset-Description.pdf**. Do note that the number of rows stated differ as that mentioned in the pdf due to the train-test split. Some columns such as **Deceased_Ind** and **Death_Date** in the test set of **patientdemosyn.csv** are deleted as they are the target metric for Phase 2.\n\n# Diagnosis and Complications\nThe list of codes for diagnosis and complications relevant for this competition can be found in **Challenge-Statement.pdf**. \nThe list of relevant surgery codes associated with complications can be found in **DHL surgery codes.xlsx**.\n\n# Submission\nThe submission file format is **submission.csv**. The values of the column **Time\\_To\\_Death** is set as default to 0, and will need to be amended to the correct number of years to death (Please see Overview > Evaluation for more information). Do note that the **Patient\\_No** column only has unique values, and only contains a subset of **Patient No** in the test dataset.\n\nTo check accuracy of your prediction of number of years to death in the training dataset, the correct values are given in **train\\_time\\_to\\_death.csv**",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This Kaggle competition is for participants of the NUS AWS Challenge.\n\nThis is Phase 2, where participants are required to predict the time to death in patients with type 2 diabetes or hypertension\nor hyperlipidaemia from the time of first diagnosis.\n\nFurther details of the challenge statement can be found in Challenge-Statement.pdf under Data.\n\nParticipants will have access to AWS computing tools and resources. You can get more details at:\n\nhttp://medicine.nus.edu.sg/dbmi/aws-challenge.html\n\n### Please check under rules to see how to register your team and participate.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "# Evaluation Metric\nThe evaluation metric for this competition is *Mean Squared Error (MSE)* of \n**Time\\_To\\_Death**\n\nThe time to death is defined as the number of years to death after the first diagnosis of type 2 diabetes or hypertension or hyperlipidaemia. If there is no death since the first diagnosis, then time to death is 0. For the train set, the death year (if any) can be found in *patientdemo\\_phase2\\_train.csv* under the column **Death\\_Date**. For the test set, this column has been taken out.\n\nSpecial Case 1: If the time to death is the same year as the diagnosis, then time to death is 1.\nSpecial Case 2: If there is no first diagnosis, then time to death is 0.\n\n- Example 1: If the patient develops type II diabetes on 9 Jan 2019, and dies in 2019, then number of years to death is 1\n- Example 2: If the patient develops hypertension on 13 Jan 2019, and dies in 2020, then number of years to death is 2020 - 2019 = 1\n- Example 3: If the patient develops hypertension on 19 Jan 2017, and dies in 2020, then number of years to death is 2020 - 2017 = 3\n- Example 4: If the patient develops hyperlipidaemia on 23 Feb 2016, but does not die within the timeframe of the dataset, then number of years to death is 0.\n- Example 5: If the patient has no first diagnosis of type 2 diabetes or hypertension or hyperlipidaemia in all his visits, then number of years to death is 0.\n\n# Submission Format\nFor every **Patient\\_No** in *submission.csv*, output the corresponding **Time\\_To\\_Death**\n\n*submission.csv* contains 474 rows, and two columns (**Patient\\_No**, **Time\\_To\\_Death**).\nThe first row is the header row, and there will be subsequently 473 rows of unique **Patient No**. \nNote that *submission.csv* only contains a subset of **Patient No** which appears in the entire test dataset.\n\n# Extra: Training Set Time to Death (To check for Training Purposes)\nThe time to death from time of first diagnosis can be calculated from the training dataset directly itself. However, to assist you to verify if you have calculated correctly, we also provide *train\\_time\\_to\\_death.csv*, which contains a header row followed by 2677 rows of unique **Patient No** and their corresponding **Time\\_To\\_Death** from the training dataset.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\n1. Please register your team at the following link to participate in the competition:\n\n https://forms.office.com/Pages/ResponsePage.aspx?id=Xu-lWwkxd06Fvc_rDTR-gh9lb4_6fxlBg4JdfFPra9FUODFTUzRFRjZaR1VTTTRKS0RMUVlENEU4RC4u\n\nOnly the top 5 teams from Phase 1 will be given the link for Phase 2.\n\n2. No external datasets should be used for training your model other than the ones provided in this competition.\n\n3. The scoring for the competition is as follows:\n\n The leaderboard will be split into 50% public, and 50% private.\n\n Phase 2 ranking will be based purely on the 50% private leaderboard.\n\n4. The schedule and dates for the competition are as follows:\n\n- Phase 1 Submissions Due: 31 Jan 2021, 2359hrs (GMT+8)\n- Phase 1 Results Out: 1 Feb 2021\n- Phase 2 Submissions Due: 22 Feb 2021, 2359hrs (GMT+8)\n- Phase 2 Results Out: 24 Feb 2021\n\n5. Prizes will be awarded as follows:\n\n - 1st place: USD $15,000 AWS credits\n - 1st runner up: USD $10,000 AWS credits\n - 2nd runner up: USD $5,000 AWS credits\n\n6. To be eligible for the prizes, you must register your team at the link given above.\n\n\nHave a fun competition!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}