Healthcare
24 columns
200 rows
8 formats

Hospital Readmission Prediction Dataset

This dataset provides comprehensive, visit-level hospital data for predicting patient readmission risk, including demographics, diagnoses, treatments, medications, and outcomes. It enables advanced analytics and machine learning for care management, resource allocation, and quality improvement in healthcare settings. The dataset is ideal for developing predictive models, benchmarking hospital performance, and supporting population health initiatives.

opened 18 times
last updated 12 Jul 2025
by GoMask

The brief that made it

Building machine learning models to predict hospital readmission risk

Sample rows

preview · 8 of 200 rows · all 24 columns

patient_idstring	discharge_dispositionstring	num_medicationsinteger	readmitted_within_30_daysboolean	secondary_diagnosis_codestring	visit_idstring	admission_datedate	discharge_datedate	ageinteger	genderstring	racestring	primary_diagnosis_codestring	comorbiditiesstring	procedure_codestring	length_of_stay_daysinteger	insurance_typestring	num_prior_admissionsinteger	attending_physician_idstring	hospital_idstring	admission_typestring	admission_sourcestring	vital_signs_on_admissionstring	lab_results_on_admissionstring	medication_liststring
P0001	skilled nursing facility	9	false	blank	V100001	2023-01-07	2023-01-10	74	female	white	I10	hypertension,diabetes	99213	3	Medicare	4	DR101	H001	emergency	emergency room	BP:144/82,HR:92,O2:96%	WBC:9.2,HGB:13.1,CRE:1.1	lisinopril,metformin,atorvastatin,aspirin,insulin,amlodipine,omeprazole,metoprolol,simvastatin
P0002	home	1	false	blank	V100002	2023-01-08	2023-01-09	2	male	black	J21.9	blank	blank	1	Medicaid	0	DR102	H002	newborn	physician referral	BP:94/58,HR:108,O2:99%	WBC:7.5,HGB:11.7,CRE:0.3	albuterol
P0003	rehab	13	true	I25.10	V100003	2023-01-12	2023-01-17	81	female	other	E11.9	hypertension,diabetes,hyperlipidemia,osteoporosis	99214	5	Medicare	8	DR103	H003	emergency	emergency room	BP:156/90,HR:88,O2:94%	WBC:7.9,HGB:12.8,CRE:1.5	metformin,atorvastatin,aspirin,insulin,omeprazole,amlodipine,simvastatin,losartan,levothyroxine,clopidogrel,hydrochlorothiazide,alprazolam,glipizide
P0004	home	2	false	blank	V100004	2023-01-20	2023-01-21	5	female	asian	J45.909	blank	94010	1	Medicaid	0	DR104	H002	emergency	emergency room	BP:98/54,HR:116,O2:97%	WBC:6.8,HGB:12.1,CRE:0.4	albuterol,fluticasone
P0005	home	3	false	blank	V100005	2023-02-01	2023-02-08	54	male	hispanic	M54.5	hypertension	20552	7	Private	2	DR105	H004	elective	physician referral	BP:129/76,HR:84,O2:99%	WBC:7.2,HGB:14.2,CRE:1.0	acetaminophen,ibuprofen,lisinopril
P0006	home	2	false	blank	V100006	2023-02-02	2023-02-05	42	male	asian	S06.0X0A	blank	99285	3	Private	1	blank	H005	trauma	transfer	BP:122/72,HR:102,O2:97%	WBC:8.3,HGB:15.0,CRE:0.9	acetaminophen,ondansetron
P0007	home	2	false	blank	V100007	2023-02-06	2023-02-08	33	female	white	F32.1	depression	90834	2	Private	0	DR106	H003	elective	physician referral	BP:124/78,HR:76,O2:100%	WBC:6.5,HGB:13.6,CRE:0.9	sertraline,lorazepam
P0008	home	1	false	blank	V100008	2023-02-10	2023-02-13	24	male	pacific islander	S82.101A	blank	27786	3	Self-pay	0	blank	H006	trauma	emergency room	BP:120/72,HR:98,O2:99%	WBC:8.7,HGB:14.8,CRE:1.0	acetaminophen
P0009	home health	6	false	E78.5	V100009	2023-02-13	2023-02-16	66	male	white	I50.9	hypertension,hyperlipidemia	92950	3	Medicare	3	DR107	H001	emergency	emergency room	BP:134/82,HR:78,O2:95%	WBC:8.6,HGB:13.3,CRE:1.3	furosemide,atorvastatin,aspirin,carvedilol,metoprolol,clopidogrel
P0010	skilled nursing facility	15	false	blank	V100010	2023-02-14	2023-02-21	92	female	black	G30.9	dementia,osteoporosis,hypertension,diabetes	99215	7	Medicare	14	DR108	H001	emergency	emergency room	BP:136/72,HR:66,O2:91%	WBC:8.1,HGB:13.0,CRE:1.6	donepezil,memantine,metformin,atorvastatin,aspirin,insulin,amlodipine,omeprazole,simvastatin,losartan,levothyroxine,clopidogrel,hydrochlorothiazide,alprazolam,glipizide
P0011	home	2	false	blank	V100011	2023-02-16	2023-02-20	48	male	white	K52.9	blank	43239	4	Private	1	blank	H003	emergency	emergency room	BP:131/77,HR:80,O2:99%	WBC:9.0,HGB:13.9,CRE:1.0	pantoprazole,loperamide
P0012	home	4	false	blank	V100012	2023-02-21	2023-02-25	72	female	white	I25.9	hypertension,hyperlipidemia	99213	4	Medicare	2	DR109	H004	elective	physician referral	BP:128/66,HR:72,O2:98%	WBC:7.7,HGB:13.7,CRE:1.2	atorvastatin,amlodipine,aspirin,clopidogrel
P0013	home	1	false	blank	V100013	2023-02-22	2023-02-23	0	female	native american	Z38.00	blank	59400	1	Medicaid	0	DR110	H002	newborn	physician referral	BP:62/38,HR:142,O2:99%	WBC:10.1,HGB:16.3,CRE:0.2	vitamin k
P0014	home	3	false	E11.9	V100014	2023-02-24	2023-03-01	57	other	asian	I42.9	hypertension,hyperlipidemia	blank	5	Private	1	blank	H005	elective	physician referral	BP:129/84,HR:91,O2:97%	WBC:8.5,HGB:14.9,CRE:1.0	atorvastatin,amlodipine,aspirin
P0015	home	2	false	blank	V100015	2023-03-01	2023-03-04	31	male	white	S52.501A	blank	24505	3	Other	0	DR111	H006	trauma	emergency room	BP:121/73,HR:80,O2:100%	WBC:7.8,HGB:15.1,CRE:0.9	acetaminophen,ibuprofen
P0016	home	2	false	blank	V100016	2023-03-05	2023-03-06	3	male	white	J18.9	blank	blank	1	Private	0	DR112	H003	emergency	physician referral	BP:95/52,HR:122,O2:97%	WBC:8.1,HGB:12.7,CRE:0.3	amoxicillin,acetaminophen
P0017	home	1	false	blank	V100017	2023-03-08	2023-03-09	22	female	black	F41.1	anxiety	99213	1	Private	1	DR106	H001	elective	physician referral	BP:118/78,HR:72,O2:99%	WBC:7.4,HGB:13.2,CRE:0.8	alprazolam
P0018	home	4	false	blank	V100018	2023-03-10	2023-03-15	59	male	asian	I10	hypertension	99214	5	Medicare	2	DR113	H004	elective	physician referral	BP:139/81,HR:70,O2:97%	WBC:7.3,HGB:14.0,CRE:1.1	lisinopril,atorvastatin,aspirin,metoprolol
P0019	home	2	false	blank	V100019	2023-03-11	2023-03-15	45	female	hispanic	N39.0	blank	51701	4	Private	0	blank	H005	emergency	emergency room	BP:126/76,HR:86,O2:100%	WBC:10.2,HGB:13.9,CRE:0.8	ciprofloxacin,acetaminophen
P0020	skilled nursing facility	14	true	E11.9	V100020	2023-03-14	2023-03-22	88	female	white	I63.9	hypertension,diabetes,hyperlipidemia,osteoporosis,dementia	99215	8	Medicare	11	DR114	H001	emergency	transfer	BP:142/88,HR:84,O2:92%	WBC:9.8,HGB:12.2,CRE:1.5	lisinopril,atorvastatin,metformin,aspirin,insulin,amlodipine,omeprazole,metoprolol,simvastatin,losartan,levothyroxine,clopidogrel,hydrochlorothiazide,glipizide

What the 200 rows show

from the 200-row sample

Skilled nursing facility (discharge disposition) stands out: mean num_medications is 11.9, against 3.5 for the rest.

5%readmitted_within_30_days = true
2median num_medications
3genders
3admission sources
5insurance types
5admission types

Mean num_medications by discharge_disposition200 rows

num_medications200 rows, in bands of 2

Median 2, from 1 to 16.

secondary_diagnosis_code23 rows with a value · 177 left blank

I109
E78.57
E11.96
I25.101

24 columns by typefrom the column list below

string 17
integer 4
date 2
boolean 1

Columns

24 columns in four groups

blueprint · 24 columns
column	type	description	example
Text 17 columns
`patient_id`	string	Unique identifier for each patient in the dataset	P0001
`visit_id`	string	Unique identifier for each hospital visit or admissionunique	V100001
`gender`	string	Gender of the patientmale · female · other · unknown	female
`race`	string	Race or ethnicity of the patientoptional	white
`primary_diagnosis_code`	string	Primary diagnosis code (e.g., ICD-10) for the visit	I10
`secondary_diagnosis_code`	string	Secondary diagnosis code (if any) for the visit4 codes · optional	I25.10
`comorbidities`	string	Comma-separated list of comorbid conditions present during the visitoptional	hypertension,diabetes
`procedure_code`	string	Primary procedure code performed during the visit (e.g., CPT, ICD-10-PCS)optional	99213
`discharge_disposition`	string	Disposition at discharge (e.g., home, skilled nursing facility, deceased, rehab, etc.)4 dispositions	skilled nursing facility
`insurance_type`	string	Type of insurance coverage (e.g., Medicare, Medicaid, Private, Self-pay, Other)5 types · optional	Medicare
`medication_list`	string	Comma-separated list of medications prescribed during the visitoptional	albuterol
`attending_physician_id`	string	Identifier for the attending physician during the visitoptional	DR101
`hospital_id`	string	Identifier for the hospital where the visit occurred	H001
`admission_type`	string	Type of admission (e.g., emergency, elective, urgent, newborn, trauma)5 types	emergency
`admission_source`	string	Source of admission (e.g., physician referral, transfer, emergency room)3 sources · optional	emergency room
`vital_signs_on_admission`	string	Comma-separated key:value pairs of vital signs (e.g., BP:120/80, HR:72) on admissionoptional	BP:144/82,HR:92,O2:96%
`lab_results_on_admission`	string	Comma-separated key:value pairs of key lab results on admission (e.g., WBC:7.2, HGB:13.5)optional	WBC:9.2,HGB:13.1,CRE:1.1
Numbers 4 columns
`age`	integer	Age of the patient at the time of admission0 to 120	74
`length_of_stay_days`	integer	Number of days between admission and discharge1 or more	3
`num_prior_admissions`	integer	Number of prior hospital admissions for the patient0 or more · optional	4
`num_medications`	integer	Number of medications prescribed during the visit0 or more · optional	9
Dates and times 2 columns
`admission_date`	date	Date when the patient was admitted to the hospital	2023-01-07
`discharge_date`	date	Date when the patient was discharged from the hospital	2023-01-10
True or false 1 column
`readmitted_within_30_days`	boolean	Indicates if the patient was readmitted within 30 days of discharge (true/false)	false

15 SQL practice questions for the Hospital Readmission Prediction Dataset

Written for this data and checked against it: 12 SQL and 3 Power BI exercises from beginner to advanced. Try the first three free; the practice kit has all 15, a starter .sql file and an answer key with every expected result.

01BeginnerFreeSELECT · WHERE · ORDER BY
Long emergency stays
Return visit_id, patient_id and length_of_stay_days for emergency admissions (admission_type = 'emergency') with a length_of_stay_days of at least 10. Order the results by length_of_stay_days descending, then by visit_id ascending.
Tables: hospital_readmission_prediction_dataset · your result: 3 columns, 12 rows
02BeginnerFreeDISTINCT · ORDER BY
Distinct discharge dispositions
Return each distinct value of discharge_disposition once, as a single column named discharge_disposition, sorted alphabetically.
Tables: hospital_readmission_prediction_dataset · your result: 1 columns, 4 rows
03BeginnerFreeGROUP BY · COUNT
Visits per admission type
Return admission_type and the number of visits for each type as visit_count. Order by visit_count descending, then by admission_type ascending.
Tables: hospital_readmission_prediction_dataset · your result: 2 columns, 5 rows

04Average stay by insuranceBeginner
05Readmissions by hospital visualPower BI
06Diagnoses with high readmissionIntermediate
07Age band readmissionsIntermediate
08Hospitals above average stayIntermediate
09Monthly admissionsIntermediate
10Readmission rate card by genderPower BI
11Rank hospitals by readmission rateAdvanced
12Days since previous visitAdvanced
13Running total of monthly admissionsAdvanced
14Share of readmissions by dispositionAdvanced
15Stay length anomalies per hospitalPower BI

Get the practice kit: the full dataset, all 15 exercises, a starter .sql and the answer key. One-time $3.99.

Get the practice kit · $3.99

Use it for

A healthcare dashboard
The readmitted_within_30_days rate, num_medications by discharge_disposition and a breakdown of secondary_diagnosis_code. Excel, Power BI or Tableau.
Why do the 25 skilled nursing facility rows have a mean num_medications of 11.9?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Patients200
P00019skilled …
P000313rehab
P002014skilled …
A software demo
Believable patients with visit_id, admission_date and discharge_date to fill a screen in front of a buyer.

This dataset200 rows24 columns

Yours1,000 rows24 columns

blueprint · hospital-readmission-prediction-dataset

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 24 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

Readmission within 30 days flagged
Patients under 18 excluded
Diagnosis codes mapped to ICD-10
Only completed discharges 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: hospital-readmission-prediction-dataset

What should your data show?

No signup. No card.

Sample rows

What the 200 rows show

Columns

Long emergency stays

Distinct discharge dispositions

Visits per admission type

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?