{
  "id": 177248,
  "title": "Pre-training 3D CNN with smoking status as label",
  "url": "/competitions/osic-pulmonary-fibrosis-progression/discussion/177248",
  "author_name": "",
  "post_date": "2020-08-25T08:55:59.676463Z",
  "votes": 6,
  "comment_count": 3,
  "views": 0,
  "content": "<p>I was thinking if our model can regconize if lungs belong to smoker or not could be beneficial for predicting FVC. It can extends to other patient's attribute like sex, age, etc. For example how old is this patient with this set of lungs…</p>",
  "messages": [
    {
      "id": "984743",
      "postDate": "08/25/2020 08:55:59",
      "content": "<p>I was thinking if our model can regconize if lungs belong to smoker or not could be beneficial for predicting FVC. It can extends to other patient's attribute like sex, age, etc. For example how old is this patient with this set of lungs…</p>",
      "rawMarkdown": "I was thinking if our model can regconize if lungs belong to smoker or not could be beneficial for predicting FVC. It can extends to other patient's attribute like sex, age, etc. For example how old is this patient with this set of lungs...",
      "votes": null
    },
    {
      "id": "985356",
      "postDate": "08/25/2020 17:19:08",
      "content": "<p>I think it is not that important to recognise whether the patient is a smoker or not when you already have the information.</p>",
      "rawMarkdown": "I think it is not that important to recognise whether the patient is a smoker or not when you already have the information.",
      "votes": null
    },
    {
      "id": "986247",
      "postDate": "08/26/2020 10:08:44",
      "content": "<p><a href=\"https://www.kaggle.com/Quan\" target=\"_blank\">@Quan</a>, that's clearly possible. But what's the intention? How do you want to use it for FVC or 'confidence' prediction?</p>",
      "rawMarkdown": "Quan, that's clearly possible. But what's the intention? How do you want to use it for FVC or 'confidence' prediction?",
      "votes": null
    },
    {
      "id": "986356",
      "postDate": "08/26/2020 12:11:57",
      "content": "<p>That's nice but only requirement is data ....Lol !!</p>",
      "rawMarkdown": "That's nice but only requirement is data ....Lol !!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 985356,
      "author_name": "servietsky",
      "author_url": "",
      "post_date": "08/25/2020 17:19:08",
      "content": "<p>I think it is not that important to recognise whether the patient is a smoker or not when you already have the information.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 986247,
      "author_name": "ChristianDenich",
      "author_url": "",
      "post_date": "08/26/2020 10:08:44",
      "content": "<p><a href=\"https://www.kaggle.com/Quan\" target=\"_blank\">@Quan</a>, that's clearly possible. But what's the intention? How do you want to use it for FVC or 'confidence' prediction?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 986356,
      "author_name": "sukanthen",
      "author_url": "",
      "post_date": "08/26/2020 12:11:57",
      "content": "<p>That's nice but only requirement is data ....Lol !!</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "984743": "I was thinking if our model can regconize if lungs belong to smoker or not could be beneficial for predicting FVC. It can extends to other patient's attribute like sex, age, etc. For example how old is this patient with this set of lungs...",
    "985356": "I think it is not that important to recognise whether the patient is a smoker or not when you already have the information.",
    "986247": "Quan, that's clearly possible. But what's the intention? How do you want to use it for FVC or 'confidence' prediction?",
    "986356": "That's nice but only requirement is data ....Lol !!"
  },
  "source": "meta"
}