MedicalClaimsSynthetic1M
Medical claims synthetic 1M sample
@kaggle.drscarlat_medicalclaimssynthetic1m
Medical claims synthetic 1M sample
@kaggle.drscarlat_medicalclaimssynthetic1m
From the multiple tables offered by Medicare, each with millions of rows - I've created ONE table with 1M rows and the following columns by joining the claims with the beneficiaries table:
['BENE_BIRTH_DT', 'BENE_DEATH_DT', 'BENE_SEX_IDENT_CD', 'BENE_RACE_CD',
'BENE_ESRD_IND', 'SP_STATE_CODE', 'BENE_COUNTY_CD',
'BENE_HI_CVRAGE_TOT_MONS', 'BENE_SMI_CVRAGE_TOT_MONS',
'BENE_HMO_CVRAGE_TOT_MONS', 'PLAN_CVRG_MOS_NUM', 'SP_ALZHDMTA',
'SP_CHF', 'SP_CHRNKIDN', 'SP_CNCR', 'SP_COPD', 'SP_DEPRESSN',
'SP_DIABETES', 'SP_ISCHMCHT', 'SP_OSTEOPRS', 'SP_RA_OA', 'SP_STRKETIA',
'MEDREIMB_IP', 'BENRES_IP', 'MEDREIMB_OP', 'BENRES_OP', 'PPPYMT_OP',
'MEDREIMB_CAR', 'BENRES_CAR', 'PPPYMT_CAR', 'CLM_FROM_DT',
'CLM_THRU_DT', 'ICD9_DGNS_CD_1', 'HCPCS_CD_1', 'LINE_NCH_PMT_AMT_1',
'LINE_BENE_PTB_DDCTBL_AMT_1', 'LINE_COINSRNC_AMT_1',
'LINE_PRCSG_IND_CD_1', 'LINE_ICD9_DGNS_CD_1']
https://www.cms.gov/Research-Statistics-Data-and-Systems/Downloadable-Public-Use-Files/SynPUFs
https://www.cms.gov/Research-Statistics-Data-and-Systems/Downloadable-Public-Use-Files/SynPUFs/Downloads/SynPUF_DUG.pdf
CREATE TABLE medicalclaimssynthetic1m (
"desynpuf_id" VARCHAR,
"bene_birth_dt" BIGINT,
"bene_death_dt" BIGINT,
"bene_sex_ident_cd" BIGINT,
"bene_race_cd" BIGINT,
"bene_esrd_ind" VARCHAR,
"sp_state_code" BIGINT,
"bene_county_cd" BIGINT,
"bene_hi_cvrage_tot_mons" BIGINT,
"bene_smi_cvrage_tot_mons" BIGINT,
"bene_hmo_cvrage_tot_mons" BIGINT,
"plan_cvrg_mos_num" BIGINT,
"sp_alzhdmta" BIGINT,
"sp_chf" BIGINT,
"sp_chrnkidn" BIGINT,
"sp_cncr" BIGINT,
"sp_copd" BIGINT,
"sp_depressn" BIGINT,
"sp_diabetes" BIGINT,
"sp_ischmcht" BIGINT,
"sp_osteoprs" BIGINT,
"sp_ra_oa" BIGINT,
"sp_strketia" BIGINT,
"medreimb_ip" DOUBLE,
"benres_ip" DOUBLE,
"pppymt_ip" DOUBLE,
"medreimb_op" DOUBLE,
"benres_op" DOUBLE,
"pppymt_op" DOUBLE,
"medreimb_car" DOUBLE,
"benres_car" DOUBLE,
"pppymt_car" DOUBLE,
"clm_id" BIGINT,
"clm_from_dt" BIGINT,
"clm_thru_dt" BIGINT,
"icd9_dgns_cd_1" VARCHAR,
"prf_physn_npi_1" DOUBLE,
"hcpcs_cd_1" BIGINT,
"line_nch_pmt_amt_1" DOUBLE,
"line_bene_ptb_ddctbl_amt_1" DOUBLE,
"line_coinsrnc_amt_1" DOUBLE,
"line_prcsg_ind_cd_1" VARCHAR,
"line_icd9_dgns_cd_1" VARCHAR
);Anyone who has the link will be able to view this.