None of the training data contains participants with true FVC measurements for a range from week -12 to 133. The longest range is 61 weeks, less than half of the requested range.
\n\nHave you been extrapolating this data then training or are you training your model to predict a trend line for a participant?
", "messages": [ { "id": "956450", "postDate": "08/03/2020 14:10:06", "content": "None of the training data contains participants with true FVC measurements for a range from week -12 to 133. The longest range is 61 weeks, less than half of the requested range.
\n\nHave you been extrapolating this data then training or are you training your model to predict a trend line for a participant?
", "rawMarkdown": "None of the training data contains participants with true FVC measurements for a range from week -12 to 133. The longest range is 61 weeks, less than half of the requested range. \n\nHave you been extrapolating this data then training or are you training your model to predict a trend line for a participant?", "votes": null }, { "id": "957506", "postDate": "08/04/2020 11:13:34", "content": "I think that the date of the CT scan is random, so the FVC series should be shift invariant up to a degree
", "rawMarkdown": "I think that the date of the CT scan is random, so the FVC series should be shift invariant up to a degree", "votes": null }, { "id": "958467", "postDate": "08/05/2020 02:25:45", "content": "\n\n\nIn the dataset, you are provided with a baseline chest CT scan and associated clinical information for a set of patients. A patient has an image acquired at time Week = 0 and has numerous follow up visits over the course of approximately 1-2 years, at which time their FVC is measured.
\n \nIn the training set, you are provided with an anonymized, baseline CT scan and the entire history of FVC measurements.\n In the test set, you are provided with a baseline CT scan and only the initial FVC measurement. You are asked to predict the final three FVC measurements for each patient, as well as a confidence value in your prediction.\n Since this is real medical data, you will notice the relative timing of FVC measurements varies widely. The timing of the initial measurement relative to the CT scan and the duration to the forecasted time points may be different for each patient.
\n
I recommend you reread it carefully.
", "rawMarkdown": "> In the dataset, you are provided with a baseline chest CT scan and associated clinical information for a set of patients. A patient has an image acquired at time Week = 0 and has numerous follow up visits over the course of approximately 1-2 years, at which time their FVC is measured.\n\n> In the training set, you are provided with an anonymized, baseline CT scan and the entire history of FVC measurements.\nIn the test set, you are provided with a baseline CT scan and only the initial FVC measurement. You are asked to predict the final three FVC measurements for each patient, as well as a confidence value in your prediction.\n> Since this is real medical data, you will notice the relative timing of FVC measurements varies widely. The timing of the initial measurement relative to the CT scan and the duration to the forecasted time points may be different for each patient.\n\nI recommend you reread it carefully.", "votes": null }, { "id": "958833", "postDate": "08/05/2020 06:54:30", "content": "What I mean is that there is a degree of randomness in the date of the CT scan, for example for one patient it could be theee months after the first symptoms, while for another one it could be six months (not sure if these numbers make sense), so the zero week is not the same for everybody
", "rawMarkdown": "What I mean is that there is a degree of randomness in the date of the CT scan, for example for one patient it could be theee months after the first symptoms, while for another one it could be six months (not sure if these numbers make sense), so the zero week is not the same for everybody", "votes": null } ], "comments": [ { "id": 957506, "author_name": "abiolatti", "author_url": "", "post_date": "08/04/2020 11:13:34", "content": "I think that the date of the CT scan is random, so the FVC series should be shift invariant up to a degree
", "votes": null, "replies": [ { "id": 958467, "author_name": "miklgr500", "author_url": "", "post_date": "08/05/2020 02:25:45", "content": "\n\n\nIn the dataset, you are provided with a baseline chest CT scan and associated clinical information for a set of patients. A patient has an image acquired at time Week = 0 and has numerous follow up visits over the course of approximately 1-2 years, at which time their FVC is measured.
\n \nIn the training set, you are provided with an anonymized, baseline CT scan and the entire history of FVC measurements.\n In the test set, you are provided with a baseline CT scan and only the initial FVC measurement. You are asked to predict the final three FVC measurements for each patient, as well as a confidence value in your prediction.\n Since this is real medical data, you will notice the relative timing of FVC measurements varies widely. The timing of the initial measurement relative to the CT scan and the duration to the forecasted time points may be different for each patient.
\n
I recommend you reread it carefully.
", "votes": null, "replies": [] }, { "id": 958833, "author_name": "abiolatti", "author_url": "", "post_date": "08/05/2020 06:54:30", "content": "What I mean is that there is a degree of randomness in the date of the CT scan, for example for one patient it could be theee months after the first symptoms, while for another one it could be six months (not sure if these numbers make sense), so the zero week is not the same for everybody
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "956450": "None of the training data contains participants with true FVC measurements for a range from week -12 to 133. The longest range is 61 weeks, less than half of the requested range. \n\nHave you been extrapolating this data then training or are you training your model to predict a trend line for a participant?", "957506": "I think that the date of the CT scan is random, so the FVC series should be shift invariant up to a degree", "958467": "> In the dataset, you are provided with a baseline chest CT scan and associated clinical information for a set of patients. A patient has an image acquired at time Week = 0 and has numerous follow up visits over the course of approximately 1-2 years, at which time their FVC is measured.\n\n> In the training set, you are provided with an anonymized, baseline CT scan and the entire history of FVC measurements.\nIn the test set, you are provided with a baseline CT scan and only the initial FVC measurement. You are asked to predict the final three FVC measurements for each patient, as well as a confidence value in your prediction.\n> Since this is real medical data, you will notice the relative timing of FVC measurements varies widely. The timing of the initial measurement relative to the CT scan and the duration to the forecasted time points may be different for each patient.\n\nI recommend you reread it carefully.", "958833": "What I mean is that there is a degree of randomness in the date of the CT scan, for example for one patient it could be theee months after the first symptoms, while for another one it could be six months (not sure if these numbers make sense), so the zero week is not the same for everybody" }, "source": "meta" }