Healthcare
18 columns
200 rows
8 formats

Healthcare Claims Diagnosis Patterns

This dataset provides anonymized, multi-table healthcare insurance claims data, including detailed ICD diagnosis codes, patient demographic profiles, claim amounts, and risk adjustment scores. It enables robust analysis of diagnosis trends, risk stratification, and healthcare utilization patterns for research, actuarial modeling, and quality improvement initiatives.

last updated 21 Jul 2025
by GoMask

The brief that made it

Diagnosis trend analysis and disease prevalence studies

Sample rows

preview · 8 of 200 rows · all 18 columns

patient_idstring	insurance_plan_typestring	risk_scorefloat	diagnosis_code_2string	claim_idstring	provider_idstring	service_datedate	claim_submission_datedate	diagnosis_code_1string	diagnosis_code_3string	procedure_codestring	claim_amountfloat	amount_paidfloat	claim_statusstring	patient_genderstring	patient_birth_datedate	patient_zip_codestring	patient_racestring
P1001	PPO	1.2	I10	C00001	PROV-A1	2023-04-12	2023-04-15	E11.9	blank	99214	175	140	approved	female	1987-08	10001	Hispanic
P1002	Commercial	0.8	blank	C00002	PROV-B3	2023-01-20	2023-01-22	F41.1	blank	99406	95.5	90	approved	male	1993-03	94110	Asian
P1003	Medicaid	0.5	blank	C00003	PROV-C2	2023-03-02	2023-03-03	J45.909	blank	99381	85	85	approved	female	2011-06	32828	Black
P1004	Medicare	18.5	E78.5	C00004	PROV-D5	2022-11-18	2022-11-20	I21.9	blank	92928	15750	14000	approved	male	1942-07	77005	White
P1005	HMO	1	blank	C00005	PROV-E9	2023-05-15	2023-05-16	R10.9	blank	70450	430	400	approved	female	1999-04	10001	White
P1006	Medicaid	0.2	blank	C00006	PROV-F4	2023-02-26	2023-02-27	Z23	blank	90471	42	42	approved	male	2015-10	75201	Hispanic
P1007	Medicare	14.9	E11.9	C00007	PROV-G6	2023-06-01	2023-06-05	N18.6	I12.0	90935	2850	2700	approved	male	1950-01	48197	Black
P1008	Medicaid	0.6	blank	C00008	PROV-H7	2023-03-15	2023-03-17	Z00.00	blank	99382	69	69	approved	female	2014-03	60616	Native American
P1009	PPO	1.3	blank	C00009	PROV-A1	2023-01-10	2023-01-11	E11.65	blank	99213	120	100	approved	female	1989-11	10001	Asian
P1010	Commercial	1.5	F41.1	C00010	PROV-B3	2023-02-04	2023-02-07	F33.1	blank	99407	130.5	100	approved	male	1996-05	94110	White
P1011	Medicare	23.1	blank	C00011	PROV-C2	2023-05-01	2023-05-03	C34.1	blank	32405	18500	18200	approved	female	1945-10	77005	Black
P1012	PPO	1.8	blank	C00012	PROV-D5	2022-12-11	2022-12-14	F41.9	blank	99214	190	150	approved	female	1986-02	10001	White
P1013	HMO	1	K21.9	C00013	PROV-E9	2023-03-27	2023-03-29	R10.9	blank	70450	410	390	approved	male	1998-09	94110	Asian
P1014	Commercial	1.1	blank	C00014	PROV-F4	2023-05-23	2023-05-24	M54.5	blank	97110	180	175	approved	female	1992-12	32828	Hispanic
P1015	Medicare	21.2	blank	C00015	PROV-G6	2023-06-10	2023-06-13	I50.9	blank	93306	3250	0	denied	female	1939-03	77005	Black
P1016	Medicaid	0.4	blank	C00016	PROV-H7	2023-01-08	2023-01-08	Z23	blank	90460	38	38	approved	female	2017-04	60616	Native American
P1017	PPO	1.6	blank	C00017	PROV-A1	2023-03-16	2023-03-19	E11.9	blank	99212	105	100	approved	male	1991-09	10001	Hispanic
P1018	HMO	1	blank	C00018	PROV-B3	2023-01-24	2023-01-28	I10	blank	99213	110	90	pending	female	1995-12	32828	Hispanic
P1019	Medicare	16.7	blank	C00019	PROV-C2	2022-10-10	2022-10-13	N18.6	blank	90935	2800	0	denied	male	1948-09	48197	White
P1020	Medicaid	0.3	blank	C00020	PROV-D5	2023-05-27	2023-05-27	Z00.00	blank	99383	70	70	approved	male	2012-08	75201	Hispanic

What the 200 rows show

from the 200-row sample

Medicare (insurance plan type) stands out: mean risk_score is 21.0, against 1.1 for the rest.

1.2median risk_score
3claim statuses
3patient genders
6patient races
20diagnosis code 1s
20procedure codes

Mean risk_score by insurance_plan_type200 rows

risk_score200 rows, in bands of 5

Median 1.2, from 0.18 to 28.7.

diagnosis_code_249 rows with a value · 151 left blank

I1020
E11.98
E78.56
F41.14
Z234
E66.92
K21.91
R551
I50.91
R10.91

18 columns by typefrom the column list below

string 12
float 3
date 3

Columns

18 columns in three groups

blueprint · 18 columns
column	type	description	example
Text 12 columns
`patient_id`	string	Anonymized unique identifier for each patient	P1001
`claim_id`	string	Unique identifier for each insurance claimunique	C00001
`provider_id`	string	Unique identifier for the healthcare provider submitting the claim	PROV-A1
`diagnosis_code_1`	string	Primary ICD diagnosis code associated with the claim	E11.9
`diagnosis_code_2`	string	Secondary ICD diagnosis code (if applicable)11 2s · optional	I10
`diagnosis_code_3`	string	Tertiary ICD diagnosis code (if applicable)3 3s · optional	I12.0
`procedure_code`	string	CPT or HCPCS code for the procedure performedoptional	99214
`claim_status`	string	Status of the claim (e.g., submitted, approved, denied, pending)submitted · approved · denied · pending	approved
`patient_gender`	string	Anonymized gender of the patientmale · female · other · unknown · optional	female
`patient_zip_code`	string	Anonymized ZIP or postal code of the patient's residenceoptional	10001
`patient_race`	string	Self-reported or coded race/ethnicity of the patient (if available)6 races · optional	Hispanic
`insurance_plan_type`	string	Type of insurance plan (e.g., HMO, PPO, Medicare, Medicaid, Commercial)5 types · optional	PPO
Numbers 3 columns
`claim_amount`	float	Total amount claimed for the service0 or more	175
`amount_paid`	float	Amount paid by the insurer for the claim0 or more · optional	140
`risk_score`	float	Calculated risk adjustment score for the patient at the time of claim0 or more · optional	1.2
Dates and times 3 columns
`service_date`	date	Date when the healthcare service was provided	2023-04-12
`claim_submission_date`	date	Date when the claim was submitted to the insurer	2023-04-15
`patient_birth_date`	date	Birth date of the patient (anonymized or year only if required for privacy)optional	1987-08

Use it for

A healthcare dashboard
Risk_score by insurance_plan_type and a breakdown of diagnosis_code_2. Excel, Power BI or Tableau.
Why do the 34 Medicare rows have a mean risk_score of 21.0?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Patients200
P10011.2PPO
P10020.8Commerci…
P10030.5Medicaid
A software demo
Believable patients with claim_id, provider_id and service_date to fill a screen in front of a buyer.

This dataset200 rows18 columns

Yours1,000 rows18 columnspatient_zip_code: UK only

blueprint · healthcare-claims-diagnosis-patterns

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 18 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with

Claims linked to anonymized patient IDs
Multiple diagnosis codes per claim possible
Provider, location, and service dates included
Inpatient/outpatient status flagged
Claims marked as paid or denied

Rows1,000 rows10,000 rows100,000 rows1,000,000 rows

Open the blueprint in Data Factory

1 credit per row. Preview 20 rows free. Buy rows for the full run.

Exports: CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence: yours to use, including commercially
API slug: healthcare-claims-diagnosis-patterns

What should your data show?

No signup. No card.

Sample rows

What the 200 rows show

Columns

Use it for

A healthcare dashboard

A root-cause class exercise

A software demo

Make it yours.

Same schema. As many rows as you need.

More in Healthcare

What should your data show?