Healthcare
23 columns
200 rows
8 formats

Patient Health Record Summaries

This dataset provides anonymized, longitudinal summaries of patient health records, including detailed information on encounters, diagnoses, laboratory results, and medications. Designed for cohort analysis and predictive healthcare modeling, it enables researchers and analysts to track patient journeys, identify trends, and develop clinical insights while maintaining strict privacy standards.

last updated 21 Jul 2025
by GoMask

The brief that made it

Cohort analysis for chronic disease management and outcomes research

Sample rows

preview · 8 of 200 rows · all 23 columns

patient_idstring	encounter_typestring	length_of_stay_daysfloat	readmission_within_30_daysboolean	race_ethnicitystring	encounter_idstring	encounter_datedate	age_at_encounterinteger	sexstring	diagnosis_codestring	secondary_diagnosis_codesstring	procedure_codestring	procedure_descriptionstring	lab_test_codestring	lab_test_namestring	lab_result_valuefloat	lab_result_unitstring	lab_result_flagstring	medication_namestring	medication_dosestring	medication_routestring	discharge_dispositionstring	diagnosis_descriptionstring
P0001	inpatient	5.2	false	White	ENC0000001	2022-01-17	85	female	I10	E11.9,E78.5	93000	Electrocardiogram, routine ECG	2345-7	Glucose [Mass/volume] in Blood	225.4	mg/dL	abnormal	Lisinopril	10 mg	oral	home	Essential (primary) hypertension
P0002	outpatient	0	false	Black/African American	ENC0000002	2022-02-11	22	male	F32.1	blank	blank	blank	blank	blank	blank	blank	blank	Sertraline	50 mg	oral	blank	Major depressive disorder, moderate
P0003	emergency	0.8	false	Hispanic/Latino	ENC0000003	2022-03-09	1	female	J21.0	blank	36415	Collection of venous blood	718-7	Hemoglobin [Mass/volume] in Blood	8.5	g/dL	critical	blank	blank	blank	home	Acute bronchiolitis due to RSV
P0004	inpatient	8.6	true	White	ENC0000004	2022-03-18	93	female	N39.0	E11.9	81001	Urinalysis, automated, with microscopy	5804-0	Leukocytes [#/volume] in Urine	130	/uL	abnormal	Nitrofurantoin	100 mg	oral	transferred	Urinary tract infection, site not specified
P0005	outpatient	0	false	Asian	ENC0000005	2022-04-05	29	other	M54.5	blank	blank	blank	blank	blank	blank	blank	blank	blank	blank	blank	blank	Low back pain
P0006	emergency	3.7	false	White	ENC0000006	2022-05-10	44	female	I21.4	E78.5	92928	Percutaneous coronary intervention	777-3	Troponin I [Mass/volume] in Serum	16.8	ng/mL	critical	Aspirin	325 mg	oral	expired	Acute subendocardial myocardial infarction
P0001	inpatient	6	true	White	ENC0000007	2022-06-16	86	female	J18.9	I10,E11.9	71045	Chest X-ray	20565-8	C-reactive protein [Mass/volume] in Serum	180	mg/L	critical	Azithromycin	500 mg	oral	home	Pneumonia, unspecified organism
P0007	outpatient	0	false	Pacific Islander	ENC0000008	2022-07-01	36	female	F41.1	blank	blank	blank	blank	blank	blank	blank	blank	Escitalopram	10 mg	oral	blank	Generalized anxiety disorder
P0008	emergency	0.6	false	Black/African American	ENC0000009	2022-07-17	2	male	S06.0X0A	blank	70450	CT head without contrast	blank	blank	blank	blank	blank	blank	blank	blank	home	Concussion without loss of consciousness, initial encounter
P0009	telehealth	0	false	Native American	ENC0000010	2022-08-04	25	male	Z23	blank	90471	Immunization administration	blank	blank	blank	blank	blank	blank	blank	blank	blank	Encounter for immunization
P0010	inpatient	13.5	false	White	ENC0000011	2022-08-22	102	female	I69.3	I10,E11.9,N39.0	96372	Therapeutic injection	6690-2	Leukocytes [#/volume] in Blood by Automated count	25	10^9/L	critical	Vancomycin	1000 mg	IV	expired	Sequelae of cerebral infarction
P0011	outpatient	0	false	Asian	ENC0000012	2022-09-15	27	female	M25.561	blank	blank	blank	blank	blank	blank	blank	blank	Ibuprofen	400 mg	oral	blank	Pain in right knee
P0002	emergency	0.4	false	Black/African American	ENC0000013	2022-09-30	23	male	S93.401A	blank	29515	Application of short leg splint	blank	blank	blank	blank	blank	Acetaminophen	650 mg	oral	home	Sprain of unspecified ligament of right ankle, initial encounter
P0012	inpatient	5.6	false	White	ENC0000014	2022-10-18	77	male	E11.9	I10	82947	Glucose; quantitative, blood	2345-7	Glucose [Mass/volume] in Blood	195	mg/dL	abnormal	Metformin	1000 mg	oral	home	Type 2 diabetes mellitus without complications
P0013	outpatient	0	false	Middle Eastern	ENC0000015	2022-11-05	49	male	E78.5	blank	blank	blank	2093-3	Cholesterol, total [Mass/volume] in Serum	249	mg/dL	abnormal	Atorvastatin	20 mg	oral	blank	Hyperlipidemia, unspecified
P0014	emergency	4.9	true	White	ENC0000016	2022-11-30	68	male	A41.9	I10,E11.9	96372	Therapeutic injection	6690-2	Leukocytes [#/volume] in Blood by Automated count	33.7	10^9/L	critical	Vancomycin	1500 mg	IV	transferred	Sepsis, unspecified organism
P0015	inpatient	3.2	false	Black/African American	ENC0000017	2023-01-08	81	male	R55	I10	93000	Electrocardiogram, routine ECG	blank	blank	blank	blank	blank	Amlodipine	5 mg	oral	home	Syncope and collapse
P0016	telehealth	0	false	blank	ENC0000018	2023-01-19	20	unknown	Z71.9	blank	blank	blank	blank	blank	blank	blank	blank	blank	blank	blank	blank	Counseling, unspecified
P0017	inpatient	4.3	false	Other	ENC0000019	2023-02-03	91	female	W19	I10,E11.9	73564	Radiologic examination, knee	blank	blank	blank	blank	blank	blank	blank	blank	home	Unspecified fall
P0018	emergency	3.1	true	Native Hawaiian	ENC0000020	2023-02-15	55	male	S06.5X0A	blank	70450	CT head without contrast	718-7	Hemoglobin [Mass/volume] in Blood	7.2	g/dL	critical	blank	blank	blank	transferred	Traumatic subdural hemorrhage without loss of consciousness, initial encounter

What the 200 rows show

from the 200-row sample

Inpatient (encounter type) stands out: mean length_of_stay_days is 7.5, against 0.92 for the rest.

20%readmission_within_30_days = true
0.75median length_of_stay_days
3lab result flags
4sexes
4medication routes
5discharge dispositions

Mean length_of_stay_days by encounter_type200 rows

length_of_stay_days200 rows, in bands of 2

Median 0.75, from 0.0 to 13.6.

race_ethnicity187 rows with a value · 13 left blank

White56
Black/African American34
Other17
Native Hawaiian16
Asian14
Pacific Islander14
Hispanic/Latino13
Native American12
Middle Eastern11

23 columns by typefrom the column list below

string 18
integer 1
float 2
date 1
boolean 1

Columns

23 columns in four groups

blueprint · 23 columns
column	type	description	example
Text 18 columns
`patient_id`	string	Anonymized unique identifier for each patient	P0001
`encounter_id`	string	Unique identifier for each patient encounter or visitunique	ENC0000001
`encounter_type`	string	Type of encounter (e.g., inpatient, outpatient, emergency)inpatient · outpatient · emergency · telehealth · other	inpatient
`sex`	string	Patient's recorded sex at birthmale · female · other · unknown	female
`race_ethnicity`	string	Patient's self-reported race or ethnicity9 ethnicities · optional	White
`diagnosis_code`	string	Primary diagnosis code (e.g., ICD-10) for the encounter	I10
`diagnosis_description`	string	Text description of the primary diagnosisoptional	Low back pain
`secondary_diagnosis_codes`	string	Comma-separated list of secondary diagnosis codes for the encounter12 codeses · optional	E11.9,E78.5
`procedure_code`	string	Primary procedure code (e.g., CPT) performed during the encounter, if anyoptional	93000
`procedure_description`	string	Text description of the primary procedure performedoptional	Chest X-ray
`lab_test_code`	string	Code for the primary laboratory test performed during the encounteroptional	2345-7
`lab_test_name`	string	Name of the primary laboratory test performedoptional	Glucose, Serum
`lab_result_unit`	string	Unit of measurement for the laboratory result value12 units · optional	mg/dL
`lab_result_flag`	string	Flag indicating if the lab result is normal, abnormal, or criticalnormal · abnormal · critical · unknown · optional	abnormal
`medication_name`	string	Name of the primary medication prescribed during the encounteroptional	Lisinopril
`medication_dose`	string	Dosage of the medication prescribedoptional	10 mg
`medication_route`	string	Route of administration for the medication (e.g., oral, IV)4 routes · optional	oral
`discharge_disposition`	string	Disposition of the patient at discharge (e.g., home, transferred, expired)5 values · optional	home
Numbers 3 columns
`age_at_encounter`	integer	Patient's age (in years) at the time of the encounter0 to 120	85
`lab_result_value`	float	Numeric value of the primary laboratory test resultoptional	225.4
`length_of_stay_days`	float	Length of stay for the encounter in days0 or more · optional	5.2
Dates and times 1 column
`encounter_date`	date	Date of the patient encounter	2022-01-17
True or false 1 column
`readmission_within_30_days`	boolean	Indicates if the patient was readmitted within 30 days of dischargeoptional	false

Use it for

A healthcare dashboard
The readmission_within_30_days rate, length_of_stay_days by encounter_type and a breakdown of race_ethnicity. Excel, Power BI or Tableau.
Why do the 66 inpatient rows have a mean length_of_stay_days of 7.5?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Patients200
P00015.2inpatient
P00048.6inpatient
P00016inpatient
A software demo
Believable patients with encounter_id, encounter_date and encounter_type to fill a screen in front of a buyer.

This dataset200 rows23 columns

Yours1,000 rows23 columns

blueprint · patient-health-record-summaries

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 23 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

Unique patient IDs per longitudinal record
Each record includes diagnoses, meds, labs
Encounter types (inpatient, outpatient, ER) flagged
Dates of care and provider anonymized
Outcome measures (readmission, mortality) included

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: patient-health-record-summaries

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?