# Help with Hemolysis — Data

来源：https://www.kaggle.com/competitions/aacc-2023-helpwithhemolysis/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The dataset is a real, de-identified clinical dataset consisting of results of all hemolysis measurements produced at a large, academic, tertiary care center over one month. Additional features include the collector ID, basic patient demographics, metadata related to the care setting, the time of day, and the day of the month.  

The training data contains the collector ID and relevance scores for a random subset of the collectors. The relevance scores were determined as the expected cost savings to be realized over the following year resulting from targeting each collector for hemolysis prevention training. Additional details related to the calculation of collector relevance can be found in the evaluation description under the overview tab.

The test data contains a randomly ordered list of the remaining collectors' collector IDs. Your task is to order this list of collector IDs from most to least relevant as a target for hemolysis prevention training.

The use of the de-identified data set for this competition has been reviewed and deemed as non-human research by the Human Research Protections Office at Washington University in St. Louis (IRB ID #202301172). 

## Files

*   **hemolysis_index_results.csv** - the de-identified clinical dataset of all hemolysis index results over one month
*   **redraw_thresholds.csv** - orderables and hemolysis index redraw thresholds
*   **redraw_costs.csv** - encounter types and costs (USD) of sample redraw
*   **train.csv** - the training set of collector IDs with labels of collector relevance
*   **test.csv** - the test set of collector IDs to be ranked by the competitors
*   **sample_submission.csv** - a sample submission file in the correct format

## Columns

###### hemolysis_index_results.csv
*   `ORDER_ID` - code uniquely identifying a single order
*   `ORDERABLE` - laboratory orderable
*   `PATIENT_ID` - code uniquely identifying the patient providing the sample
*   `PATIENT_AGE` - patient age in years at the time of draw
*   `PATIENT_SEX` - patient sex
*   `PATIENT_RACE` - patient race
*   `NURSING_UNIT` - code uniquely identifying the nursing unit where the sample was drawn
*   `ENCOUNTER_TYPE` - patient care setting where the sample was drawn
*   `MEDICAL_SERVICE` - medical service caring for the patient at the time of draw
*   `SPECIMEN_ID` - code uniquely identifying a single specimen
*   `SPECIMEN_TYPE` - specimen type
*   `COLLECTOR_ID` - code uniquely identifying a single specimen collector
*   `DRAW_SITE` - anatomic site of specimen collection
*   `COLLECTION_DAY` - day of the month the sample was drawn on
*   `COLLECTION_TIME` - time of day the sample was drawn
*   `HEMOLYSIS_INDEX` - hemolysis index (a quantitative measure of sample hemolysis)

###### redraw_thresholds.csv
*   `ORDERABLE` - laboratory orderable
*   `HI_REDRAW_THRESHOLD` - the threshold for hemolysis index above which results are suppressed for at least one of the ordered analytes and redraw is required

###### redraw_costs.csv
*   `ENCOUNTER_TYPE` - patient care setting where the sample was drawn
*   `REDRAW_COST` - costs (USD) assigned to sample redraw

###### train.csv
*   `SPLIT` - indicates that each row is related to the training dataset. 
*   `COLLECTOR_ID` - code uniquely identifying a single specimen collector
*   `RELEVANCE` - expected total preventable hemolysis costs (in thousands of USD) over the next year 

###### test.csv
*   `SPLIT` - indicates that each row is related to the test dataset. 
*   `COLLECTOR_ID` - code uniquely identifying a single specimen collector

###### sample_submission.csv
*   `SPLIT` - indicates that each row is related to the test dataset. **Leave all values as "TEST" in your submission**
*   `COLLECTOR_ID` - code identifying a single specimen collector in the test set. **Your job is to order these by relevance (greatest to least)!**