Healthcare
22 columns
200 rows
8 formats

Hospital Readmission Prediction

This dataset provides detailed, labeled records of hospital admissions, including patient demographics, diagnoses, procedures, and outcomes related to readmission. It is designed to support predictive modeling for hospital readmissions, enabling health systems to identify risk factors, optimize care transitions, and reduce costs. The comprehensive schema facilitates advanced analytics and machine learning applications in healthcare quality improvement.

opened 5 times
last updated 20 Aug 2025
by GoMask

The brief that made it

Predicting patient risk of hospital readmission

Sample rows

preview · 8 of 200 rows · all 22 columns

patient_idstring	insurance_typestring	ageinteger	readmittedboolean	ethnicitystring	admission_idstring	admission_datedate	discharge_datedate	readmission_datedate	genderstring	primary_diagnosis_codestring	secondary_diagnosis_codesstring	procedure_codesstring	length_of_stayinteger	admission_typestring	discharge_dispositionstring	comorbiditiesstring	hospital_idstring	hospital_citystring	hospital_statestring	hospital_postal_codestring	hospital_countrystring
PAT-0001	private	32	false	white	ADM-00001	2023-01-10	2023-01-15	blank	female	I10	E11,K21	CPT99214	5	elective	home	hypertension	HOSP-0001	New York	NY	10001	USA
PAT-0002	medicare	71	true	black	ADM-00002	2023-02-03	2023-02-08	2023-02-20	male	I50	E11,I10	CPT93010	5	emergency	home	heart failure, diabetes, hypertension	HOSP-0002	Chicago	IL	60601	USA
PAT-0003	medicare	85	false	asian	ADM-00003	2023-03-12	2023-03-12	blank	female	J18	blank	blank	0	emergency	deceased	cardiac arrest, sepsis	HOSP-0003	San Francisco	CA	94103	USA
PAT-0004	medicaid	8	false	hispanic	ADM-00004	2022-10-21	2022-10-23	blank	male	J45	blank	CPT94010	2	emergency	home	asthma	HOSP-0004	Houston	TX	77002	USA
PAT-0005	medicare	62	true	white	ADM-00005	2022-12-01	2022-12-09	2022-12-20	female	E11	I10,E78	CPT80053,CPT99213	8	urgent	home	diabetes, hypertension, hyperlipidemia	HOSP-0005	Boston	MA	02108	USA
PAT-0006	private	27	false	asian	ADM-00006	2023-03-20	2023-03-22	blank	male	S72	blank	CPT27130	2	elective	home	blank	HOSP-0006	Los Angeles	CA	90001	USA
PAT-0007	private	35	false	hispanic	ADM-00007	2023-01-19	2023-01-20	blank	female	N39	blank	blank	1	emergency	home	blank	HOSP-0007	Miami	FL	33101	USA
PAT-0008	medicare	67	true	white	ADM-00008	2022-09-07	2022-09-12	2022-09-25	male	I25	blank	CPT92928	5	emergency	transferred	ischemic heart disease, hypertension	HOSP-0008	Philadelphia	PA	19103	USA
PAT-0009	private	45	false	asian	ADM-00009	2023-02-28	2023-03-10	blank	female	K21	blank	CPT43235	10	elective	home	GERD	HOSP-0009	Seattle	WA	98101	USA
PAT-0010	other	90	false	other	ADM-00010	2023-04-02	2023-04-02	blank	male	I21	I50	blank	0	emergency	deceased	myocardial infarction, heart failure	HOSP-0010	San Diego	CA	92101	USA
PAT-0011	medicaid	16	false	hispanic	ADM-00011	2022-11-15	2022-11-17	blank	female	J20	blank	CPT94010	2	emergency	home	bronchitis	HOSP-0011	Atlanta	GA	30303	USA
PAT-0012	medicare	77	true	black	ADM-00012	2023-05-18	2023-05-25	2023-06-10	female	N18	I10,E11	CPT90935	7	urgent	transferred	chronic kidney disease, diabetes, hypertension	HOSP-0012	Dallas	TX	75201	USA
PAT-0013	private	41	false	white	ADM-00013	2023-01-28	2023-02-05	blank	male	K35	blank	CPT44970	8	elective	home	blank	HOSP-0013	Denver	CO	80202	USA
PAT-0014	other	110	false	blank	ADM-00014	2022-08-10	2022-08-10	blank	unknown	A41	blank	blank	0	emergency	deceased	sepsis	HOSP-0014	Phoenix	AZ	85001	USA
PAT-0015	private	59	true	asian	ADM-00015	2023-06-03	2023-06-09	2023-06-25	female	E78	I10	CPT80061	6	urgent	home	hyperlipidemia, hypertension	HOSP-0015	Las Vegas	NV	89101	USA
PAT-0016	medicaid	4	false	other	ADM-00016	2022-07-22	2022-07-23	blank	male	P07	blank	blank	1	emergency	home	prematurity	HOSP-0016	Detroit	MI	48201	USA
PAT-0017	medicare	78	true	white	ADM-00017	2023-05-08	2023-05-13	2023-05-25	male	I10	E11	CPT99214	5	urgent	transferred	hypertension, diabetes	HOSP-0017	San Antonio	TX	78205	USA
PAT-0018	private	29	false	white	ADM-00018	2023-02-16	2023-02-19	blank	female	M54	blank	CPT72148	3	elective	home	blank	HOSP-0018	Portland	OR	97201	USA
PAT-0019	private	53	false	black	ADM-00019	2022-11-29	2022-12-02	blank	male	E11	I10	CPT80053	3	urgent	home	diabetes, hypertension	HOSP-0019	Baltimore	MD	21201	USA
PAT-0020	medicare	68	true	white	ADM-00020	2023-03-05	2023-03-11	2023-03-26	female	J44	I10,E11	CPT94010	6	emergency	home	COPD, diabetes, hypertension	HOSP-0020	Cleveland	OH	44101	USA

What the 200 rows show

from the 200-row sample

Medicaid (insurance type) stands out: mean age is 8.4, against 56.2 for the rest.

16%readmitted = true
45median age
3admission types
4genders
4discharge dispositions
39hospital states

Mean age by insurance_type200 rows

age200 rows, in bands of 20

Median 45, from 0 to 120.

ethnicity182 rows with a value · 18 left blank

White36
white34
asian22
Asian17
hispanic15
Other13
other12
Black12
Hispanic11
black10

22 columns by typefrom the column list below

string 16
integer 2
date 3
boolean 1

Columns

22 columns in four groups

blueprint · 22 columns
column	type	description	example
Text 16 columns
`patient_id`	string	Unique identifier for each patient in the datasetunique	PAT-0001
`admission_id`	string	Unique identifier for each hospital admission eventunique	ADM-00001
`gender`	string	Gender of the patientmale · female · other · unknown	female
`ethnicity`	string	Ethnicity of the patient10 ethnicities · optional	white
`primary_diagnosis_code`	string	ICD code for the primary diagnosis at admission	I10
`secondary_diagnosis_codes`	string	Comma-separated ICD codes for secondary diagnoses at admissionoptional	E11,K21
`procedure_codes`	string	Comma-separated codes for procedures performed during admissionoptional	CPT99214
`admission_type`	string	Type of hospital admission (e.g., emergency, elective, urgent)emergency · elective · urgent · other	elective
`discharge_disposition`	string	Disposition of the patient at discharge (e.g., home, transferred, deceased)home · transferred · deceased · other	home
`comorbidities`	string	Comma-separated list of comorbid conditions present at admissionoptional	hypertension
`insurance_type`	string	Type of insurance coverage for the patientprivate · medicare · medicaid · self-pay · other · optional	private
`hospital_id`	string	Unique identifier for the hospital where the admission occurred	HOSP-0001
`hospital_city`	string	City where the hospital is locatedoptional	New York
`hospital_state`	string	State where the hospital is locatedoptional	NY
`hospital_postal_code`	string	Postal code of the hospital locationoptional	10001
`hospital_country`	string	Country where the hospital is locatedoptional	USA
Numbers 2 columns
`age`	integer	Age of the patient at the time of admission0 to 120	32
`length_of_stay`	integer	Number of days the patient stayed in the hospital during this admission1 or more	5
Dates and times 3 columns
`admission_date`	date	Date when the patient was admitted to the hospital	2023-01-10
`discharge_date`	date	Date when the patient was discharged from the hospital	2023-01-15
`readmission_date`	date	Date of readmission, if applicable (null if not readmitted)optional	2023-02-20
True or false 1 column
`readmitted`	boolean	Indicates whether the patient was readmitted within the prediction window (e.g., 30 days post-discharge)	false

Use it for

A healthcare dashboard
The readmitted rate, age by insurance_type and a breakdown of ethnicity. Excel, Power BI or Tableau.
Why do the 32 medicaid rows have a mean age of 8.4?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Patients200
PAT-000132private
PAT-000271medicare
PAT-000562medicare
A software demo
Believable patients with admission_id, admission_date and discharge_date to fill a screen in front of a buyer.

This dataset200 rows22 columns

Yours1,000 rows22 columnshospital_city: UK only

blueprint · hospital-readmission-prediction

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 22 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

Patient demographics and diagnosis
Discharge and readmission dates captured
Readmission window: 30/60/90 days
Synthetic data for privacy compliance

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: hospital-readmission-prediction

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?