Healthcare
24 columns
200 rows
8 formats

Patient Readmission Risk Predictor

This dataset provides a comprehensive record of hospital admissions, including patient demographics, diagnoses, procedures, length of stay, and AI-generated readmission risk scores. It enables predictive modeling and targeted interventions to reduce hospital readmissions, improve patient outcomes, and optimize healthcare resource allocation.

last updated 29 Jul 2025
by GoMask

The brief that made it

Predicting patient risk of hospital readmission for targeted care management

Sample rows

preview · 8 of 200 rows · all 24 columns

patient_idstring	insurance_typestring	risk_scorefloat	readmitted_within_30_daysboolean	race_ethnicitystring	admission_idstring	admission_datedate	discharge_datedate	ageinteger	genderstring	primary_diagnosis_codestring	secondary_diagnosis_codesstring	procedure_codesstring	comorbiditiesstring	length_of_stayinteger	readmission_datedate	readmission_reason_codestring	discharge_dispositionstring	attending_physician_idstring	admission_typestring	admission_sourcestring	intervention_flagboolean	intervention_typestring	zip_codestring
P1001	Medicare	0.88	true	White	A2001	2021-01-10	2021-01-13	74	female	I10	E11.9	30233N1	Hypertension,Diabetes	4	2021-02-06	J44.1	skilled nursing facility	PHY3101	emergency	emergency room	true	care coordination	60641
P1002	Medicaid	0.17	false	Hispanic	A2002	2021-04-15	2021-04-17	4	male	J45.909	blank	blank	Asthma	3	blank	blank	home	PHY3122	emergency	clinic	false	blank	75212
P1003	Private	0.26	false	Black	A2003	2021-02-09	2021-02-11	27	other	F32.9	blank	blank	Depression	3	blank	blank	home	PHY3145	urgent	clinic	false	blank	94117
P1004	Medicare	0.91	true	Asian	A2004	2021-03-12	2021-03-18	81	male	I50.9	E78.5,E11.9	5A1955Z	Heart Failure,Diabetes,Hyperlipidemia	7	2021-04-09	I50.9	skilled nursing facility	PHY3172	emergency	physician referral	true	home visit	92123
P1005	Medicaid	0.11	false	Native American	A2005	2021-06-21	2021-06-23	0	unknown	Z38.00	blank	blank	blank	3	blank	blank	home	PHY3199	newborn	clinic	false	blank	68104
P1006	Private	0.19	false	White	A2006	2021-09-01	2021-09-04	46	female	K21.9	E66.9	blank	Obesity	4	blank	blank	home	PHY3120	elective	physician referral	false	blank	32244
P1007	Medicare	0.7	false	Black	A2007	2021-08-29	2021-09-03	87	female	N18.9	I10,E11.9	3E0A3MZ	CKD,Hypertension,Diabetes	6	blank	blank	skilled nursing facility	PHY3184	emergency	transfer	true	care coordination	70119
P1008	Private	0.12	false	Pacific Islander	A2008	2021-05-19	2021-05-21	17	male	S06.0X0A	blank	00B70ZZ	blank	3	blank	blank	home	PHY3138	trauma	emergency room	false	blank	96817
P1009	Private	0.08	false	Asian	A2009	2021-07-28	2021-07-30	34	female	O80	blank	10D00Z0	blank	3	blank	blank	home	PHY3105	elective	clinic	false	blank	94086
P1010	Medicare	0.97	true	White	A2010	2021-11-12	2021-11-26	92	male	J18.9	I10,E11.9,J44.1	5A1945Z	COPD,Hypertension,Diabetes	15	2021-12-14	J44.1	deceased	blank	emergency	emergency room	true	care coordination	10002
P1011	Self-pay	0.18	false	Multiracial	A2011	2021-10-05	2021-10-07	23	male	S82.101A	blank	blank	blank	3	blank	blank	home	PHY3180	trauma	emergency room	false	blank	30329
P1012	Medicare	0.64	false	Black	A2012	2021-12-01	2021-12-06	77	female	G30.9	I10,E11.9	blank	Dementia,Diabetes,Hypertension	6	blank	blank	skilled nursing facility	PHY3133	urgent	transfer	true	follow-up call	48221
P1013	Private	0.29	false	White	A2013	2021-07-02	2021-07-05	55	male	E11.9	blank	blank	Diabetes	4	blank	blank	home	PHY3167	elective	physician referral	false	blank	85032
P1014	Medicare	0.56	false	White	A2014	2021-05-25	2021-05-29	68	female	I25.10	E78.5	027034Z	Coronary Artery Disease,Hyperlipidemia,Hypertension	5	blank	blank	home	PHY3107	urgent	physician referral	true	follow-up call	60620
P1015	Medicaid	0.14	false	White	A2015	2021-04-03	2021-04-10	0	female	Z38.01	blank	blank	blank	8	blank	blank	home	PHY3197	newborn	clinic	false	blank	44118
P1016	Medicaid	0.21	false	Native Hawaiian	A2016	2021-03-22	2021-03-24	12	male	J45.909	blank	blank	Asthma	3	blank	blank	home	PHY3186	emergency	clinic	false	blank	96816
P1017	Self-pay	0.22	false	White	A2017	2021-07-10	2021-07-12	28	female	F41.9	blank	blank	Anxiety	3	blank	blank	home	PHY3116	elective	clinic	false	blank	35243
P1018	Medicaid	0.15	false	Asian	A2018	2021-02-18	2021-02-20	7	other	E10.9	blank	blank	Type 1 Diabetes	3	blank	blank	home	PHY3127	emergency	clinic	false	blank	94112
P1019	Medicare	0.81	false	White	A2019	2021-06-09	2021-06-21	94	female	G30.9	I10,E11.9	blank	Dementia,Diabetes,Hypertension	13	blank	blank	skilled nursing facility	PHY3173	urgent	residential care	true	care coordination	75227
P1020	Private	0.71	true	Black	A2020	2021-08-08	2021-08-13	61	male	I63.9	blank	03CG0ZZ	Hypertension,Hyperlipidemia	6	2021-09-04	I63.9	home	PHY3146	emergency	emergency room	true	follow-up call	63136

What the 200 rows show

from the 200-row sample

Medicare (insurance type) stands out: mean risk_score is 0.78, against 0.17 for the rest.

18%readmitted_within_30_days = true
0.23median risk_score
3discharge dispositions
3intervention types
4genders
5admission sources

Mean risk_score by insurance_type200 rows

risk_score200 rows, in bands of 0.1

Median 0.23, from 0.05 to 0.99.

race_ethnicity196 rows with a value · 4 left blank

White75
Black38
Asian27
Hispanic17
Native American12
Pacific Islander10
Multiracial9
Native Hawaiian8

24 columns by typefrom the column list below

string 16
integer 2
float 1
date 3
boolean 2

Columns

24 columns in four groups

blueprint · 24 columns
column	type	description	example
Text 16 columns
`patient_id`	string	Unique identifier for each patientunique	P1001
`admission_id`	string	Unique identifier for each hospital admission eventunique	A2001
`gender`	string	Gender of the patientmale · female · other · unknown	female
`race_ethnicity`	string	Race or ethnicity of the patient8 ethnicities · optional	White
`primary_diagnosis_code`	string	Primary diagnosis code (ICD-10 or similar) for the admission	I10
`secondary_diagnosis_codes`	string	Comma-separated list of secondary diagnosis codes for the admissionoptional	E11.9
`procedure_codes`	string	Comma-separated list of procedure codes performed during the admissionoptional	30233N1
`comorbidities`	string	Comma-separated list of patient comorbidities (chronic conditions)optional	Hypertension,Diabetes
`readmission_reason_code`	string	Diagnosis code for the reason of readmission, if applicable12 codes · optional	J44.1
`insurance_type`	string	Type of insurance coverage (e.g., Medicare, Medicaid, Private, Self-pay)4 types · optional	Medicare
`discharge_disposition`	string	Disposition at discharge (e.g., home, skilled nursing facility, deceased)3 dispositions · optional	skilled nursing facility
`attending_physician_id`	string	Identifier for the attending physician during the admissionoptional	PHY3101
`admission_type`	string	Type of admission (e.g., emergency, elective, urgent)6 values	emergency
`admission_source`	string	Source of admission (e.g., physician referral, clinic, transfer)5 sources · optional	emergency room
`intervention_type`	string	Type of intervention recommended (e.g., follow-up call, home visit, care coordination)3 types · optional	care coordination
`zip_code`	string	Patient's residential zip or postal codeoptional	60641
Numbers 3 columns
`age`	integer	Age of the patient at time of admission0 or more	74
`length_of_stay`	integer	Total number of days patient stayed in the hospital during this admission1 or more	4
`risk_score`	float	Predicted risk score (0-1) for likelihood of readmission, generated by AI model0 to 1	0.88
Dates and times 3 columns
`admission_date`	date	Date of patient admission to the hospital	2021-01-10
`discharge_date`	date	Date of patient discharge from the hospital	2021-01-13
`readmission_date`	date	Date of readmission if readmitted within 30 days; null otherwiseoptional	2021-02-06
True or false 2 columns
`readmitted_within_30_days`	boolean	Indicates if the patient was readmitted to the hospital within 30 days of discharge	true
`intervention_flag`	boolean	Indicates if an intervention was recommended based on risk scoreoptional	true

Use it for

A healthcare dashboard
The readmitted_within_30_days rate, risk_score by insurance_type and a breakdown of race_ethnicity. Excel, Power BI or Tableau.
Why do the 74 Medicare rows have a mean risk_score of 0.78?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Patients200
P10010.88Medicare
P10020.17Medicaid
P10040.91Medicare
A software demo
Believable patients with admission_id, admission_date and discharge_date to fill a screen in front of a buyer.

This dataset200 rows24 columns

Yours1,000 rows24 columnszip_code: UK only

blueprint · patient-readmission-risk-predictor

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

Include age, gender, and diagnosis codes
Lab results and prior admissions required
Flag high-risk patients
Exclude pediatric readmissions

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-readmission-risk-predictor

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?