{
  "fetched_at": "2026-10-20T03:41:45Z",
  "source_url": "https://www.kaggle.com/competitions/challenge-ML-MIHE-UC3M/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h2>Provided Files</h2>\n<ul>\n<li><strong>data.csv</strong> - patient information from moth 0 to 24</li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n<h2>Data description (data.csv)</h2>\nThis file contains all the available information of the 1739 patients during a two-year follow-up. Each row of this file is associated to a single patient and the columns have the following characteristics:\n\n\n<ul>\n<li><strong>Id</strong> - anonymous id. Every patient has its own unique Id</li>\n<li><strong>test_sample</strong> - a boolean variable (value 0 or 1) indicating with a value of 1 that this patient will be included in the test data</li>\n<li><strong>GENDER</strong> - Female or Male (0, 1) </li>\n<li><strong>AGE</strong> -Patient age at month 0</li>\n<li><strong>PTEDUCAT</strong> - Years of education</li>\n<li><strong>APOE4</strong> - Number of this gene in the patient (0,1,2)</li>\n<li><strong>FDG-PET derived measures: AngularLeft, AngularRight, CingulumPostBilateral, TemporalLeft, TemporalRight</strong> - FDG-PET measurements in different brain regions at month 0 (measure the presence of Fluorodeoxyglucose from PET data)</li>\n<li><strong>Temporal diagnosis change: DXCHANGE</strong> - Categorical variable indicating a change in the patient diagnosis. Considering four states S0 (control patient), S1 (medium state), S2 (severe state) (1 = Stable:S0 to S0, 2=Stable:S1 to S1, 3=Stable:S2 to S2,  4=Conv:S0 to S1, 5=Conv:S1 to S2, 6 = Conv:S0 to S2, 7 = Rev:S1 to S0, 8 = Rev:S2 to S1, 9 = Rev:S2 to S0, -1 = Not available)</li>\n<li><strong>Temporal evolution in neurophysiological and behavioural tests </strong> - For each time-stamp we have 5 entries: <strong>MMSE</strong>, <strong>RAVLT learning</strong>, <strong>RAVLT immediate</strong>, <strong>RAVLT perc forgetting</strong>,   <strong>FAQ</strong></li>\n<li><strong>MRI summarized data </strong> - For each time-stamp we have average MRI data from 7 brain regions: <strong>Ventricles</strong>, <strong>Hippocampus</strong>, <strong>Whole Brain</strong>, <strong>Entorhinal</strong>,   <strong>Fusiform</strong>, <strong>MidTemp</strong> and <strong>ICV</strong></li>\n<li><strong>Temporal evolution  of AV45-PET derived measures</strong> - For each time-stamp we have 7 AV45-PET measurements in different brain regions: <strong>Cerebellum Grey Matter</strong>, <strong>Whole Cerebellum</strong>, <strong>Eroded Subcortical </strong>, <strong>Frontal</strong>,   <strong>Cingulate</strong>, <strong>Parietal</strong> and  <strong>Temporal</strong></li>\n\n\n</ul>\n\nAll features with temporal evolution are indicated with a flag <strong>t_X_</strong>, where X denotes the acquisition month (0, 3, 6, 12, 18, 24, 30, 36).\n\nFor each patient we have demographic information (age, gender, education level, genetic information, …) together with different medical tests performed periodically (month 0, 3, 6, 12, 18, 24) that provide FDG-PET and AV45-PET derived measures, neurophysiological and behavioural tests, MRI summarized data, and CSF (cerebrospinal fluid) biomarkers.\n\nBesides, together this information, we have a scoring characterizing the Disease Progression (DP).\n\nSo, the final goal of this challenge is the estimation of the DP scoring at month 36 using all the patient information collected from months 0 to 24.\n\n<h2>Prediction submission (sampleSubmission.csv)</h2>\nThis file is an example of the submission file format and, besides, it contains the results of the baseline approach. \nThis file has to contain, for each patient, two columns: Id and Predictions. Note that only Id patients with flag 'test_sample'=1 will be considered for the testing evaluation</p>\n<p>The submission file should contain a header and have the following format:</p>\n<pre>Id,Predictions<br>1,1.0<br></pre>\n\n\nHere, you can find a demo notebook to generate the baseline solution:\n\nhttps://www.kaggle.com/vgverdejo/baseline",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>Introduction</h2>\n\nWelcome to the Challenge for the students of the Machine Learning course of the Masters in Information Health Engineering (UC3M).\n\nThis challenge opens on November 24th, 2020 and ends two months later (January 20, 2021). \n\n<h2>Problem description</h2>\n\nThe goal of this problem is to predict the evolution of a mental disease in a set of subjects. For this purpose, we have a group of 1739 patients who have been followed for two years (24 months) and want to estimate the disease stage one year later (month 36th).\n\nFor each patient we have demographic  information (age, gender, education level, genetic information, ...) together with different medical tests performed periodically (at month 0, 3, 6, 12, 18, 24) that provide FDG-PET and AV45-PET derived measures, neurophysiological and behavioural tests, MRI summarized data, and CSF (cerebrospinal fluid) biomarkers. \n\nBesides, together with this information, we have a scoring, called DP (Disease Progression), related to the disease progression. So, the final goal of this challenge is the estimation of the DP scoring on month 36 using all the patient information collected  from months 0 to 24.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is the <a href=\"https://scikit-learn.org/stable/modules/generated/sklearn.metrics.r2_score.html#sklearn.metrics.r2_score\"> R^2 score</a>.\n</p><h2>Submission Format</h2>\n<p>Every submitted file must contain two columns: Id and Predictions. In the data description we point out the existence of a flag called 'test_sample'. For every patient in the dataset with the flag 'test_sample' set to 1 (test_sample=1) you will need to write a row in the submitted file with this patient Id and the prediction of the DP score for this patient. Only the predictions for the patients with 'test_sample' set to one will be considered for computing the performance of your models.</p>\n<p>The submission file should contain a header and have the following format:</p>\n<pre>Id,Predictions<br>1,1.0<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}