# Disease Prediction — Data

来源：https://www.kaggle.com/competitions/eastwood-and-cleef-ml-disease/data

采集时间：2026-10-19T08:12:44Z

This page describes what files have been provided and the format of each. 

## Files

*   **admissions_data.csv** - contains information about hospital admissions for 2018-2019
*   **disease_data.csv** - contains information about ICD and HCC for 2018-2019
*   **labs_data.csv** - contains information about laboratory tests for 2018-2019
*   **patients_data.csv** - contains member data such as gender, age, etc. for 2018-2019
*   **prescriptions_data.csv** - contains drug prescriptions for 2018-2019
*   **train_labels.csv** - contains labels for 2019 (new diseases discovered that year)
*   **sample_submission.csv** - your prediction with HCCs for 2020

## Columns

*   `member_id` - patients' ID
*   `admission_date` - a date when hospital admission occurred
*   `discharge_date` -  date when member was discharge from the hospital
*   `admission_type` - a hospital admission type
*   `icd_code` - an ICD code (diagnosis) used for hospital admission
*   `is_readmission` - 1 if member was already in the hospital in last 30 days, otherwise 0
*   `er_to_inp_admission_transfer` - 1 if member had inpatient (INP) and ER (emergency) hospital admission same day, otherwise 0
*   `days_to_prev_admission` - a number of days since last admission
*   `year_of_service` - a year when ICD / HCC was detected by doctors
*   `icd_code` - an ICD code (disease)
*   `icd_chronic_or_acute` - a chronic / acute disease type
*   `hcc_code` - a HCC coding for ICD
*   `hcc_chronic_or_acute` - a chronic / acute HCC type
*   `date_of_service` - a date when some service was provided to patients
*   `loinc_code` - a laboratory test code
*   `performed_test_name ` - a laboratory test name
*   `abnormal_code` - a flag that tells about low (L) or high (H) lab results
*   `result_value` - a result value
*   `normal_low_value_numeric` - a lower bound for reference lab result
*   `normal_high_value_numeric` - an upper bound for reference lab result
*   `date_of_service` - a date when some service was provided to patients
*   `patient_age` - a patient's age
*   `patient_gender` - a patient's gender
*   `patient_age` - a patient's age
*   `dual_status` - a flag that tells about Medicaid / Medicate insurance programms
*   `patient_age` - a patient's age
*   `insurance_company` - a company providing medical insurance
*   `insurance_type` - an insurance type
*   `pbp_type` - a member's risk group
*   `county` - a member's county
*   `city` - a member's city
*   `date_filled` - a date when prescription was filled for the member
*   `ndc_number` - an unique drug ID 
*   `days_supply` - a number of days for which the prescription was filled
*   `drug_name` - a drug name
*   `metric_quantity` - a drug dosage
*   `new_or_refill` - 1 if a new drug was prescribed, otherwise 0
*   `hcc_9` - a flag that identifies that member has HCC 9. Similar logic should be used for other hcc_N columns