{
  "fetched_at": "2026-10-20T14:11:18Z",
  "source_url": "https://www.kaggle.com/competitions/covid-19-202408/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## 数据集：\n1. Analysis of altered level of blood-based biomarkers in the prognosis of COVID-19 patients数据集的sheet2和sheet3——用来判断某人是否属于新冠病人或健康人，预测新冠病人的死亡概率\n2. Clinical characteristics, risk factors and complications of COVID-19 among critically ill older adults – A case control study数据集的Data表——用来预测新冠病人的死亡概率，分析身体指标/并发症/发病症状与新冠患者死亡率的相关性。如果分类的数据量不够这个数据集也可加入到上一个数据集的新冠患者集合中。\n\n## 文件\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "新冠肺炎自从2020年爆发以来到现在已经过去了四年，直到今天，新冠在我国东南沿海地区仍有抬头的趋势。那么，我们应该如何判断某人感染了新冠，是否有除发病症状外更客观、定量的指标去判断呢？假如不幸感染了新冠，我们也希望知道从哪些身体指标和发病症状入手来降低新冠的死亡率。现在需要你建立模型：\n1.根据体检指标判断某人是否感染新冠\n2.如果感染新冠，那么当前的身体指标下，某人死亡的概率是多少？",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "1.判断某人是否属于新冠患者：准确率（Acc）、F1分数。（100分，两个指标各50分）\n2.预测某新冠患者的死亡率：平均绝对误差值（MAE）、均方根误差（RMSE），",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "规则",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "本竞赛为COVID-19诊断竞赛",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}