Healthcare
21 columns
200 rows
8 formats

Healthcare Clinical Trial Simulation

This synthetic clinical trial dataset provides detailed, patient-level records for multi-arm studies, including demographics, treatment assignments, protocol compliance, outcomes, and adverse event tracking. It is ideal for modeling trial efficacy, safety profiles, and protocol adherence in simulated or methodological research. The flat structure ensures compatibility with statistical and machine learning tools for rapid analysis and simulation.

opened 5 times
last updated 21 Jul 2025
by GoMask

The brief that made it

Modeling and simulation of clinical trial outcomes

Sample rows

preview · 8 of 200 rows · all 21 columns

patient_idstring	primary_outcomestring	protocol_compliancefloat	dropoutboolean	ethnicitystring	trial_idstring	arm_idstring	arm_descriptionstring	enrollment_datedate	ageinteger	sexstring	baseline_conditionstring	comorbiditiesstring	secondary_outcomestring	adverse_event_occurredboolean	adverse_event_typestring	adverse_event_severitystring	adverse_event_onset_datedate	adverse_event_outcomestring	dropout_reasonstring	completion_datedate
P000001	improved	97	false	Caucasian	T1	A-T1-01	Placebo	2020-03-15	5	male	Congenital Heart Disease	blank	surgical outcome good	false	blank	blank	blank	blank	blank	2021-03-16
P000002	responder	92.6	false	Asian	T1	A-T1-02	Drug A 50mg	2020-03-17	42	female	Type 2 Diabetes	Hypertension,Obesity	HbA1c improved	false	blank	blank	blank	blank	blank	2021-03-20
P000003	non-responder	89.2	false	African American	T1	A-T1-03	Drug B 10mg	2020-03-20	55	female	Hypertension	Hyperlipidemia	BP unchanged	true	Dizziness	mild	2020-05-10	resolved	blank	2021-03-20
P000004	unchanged	94.7	false	Hispanic	T1	A-T1-01	Placebo	2020-03-22	60	male	Type 2 Diabetes	Obesity	HbA1c unchanged	false	blank	blank	blank	blank	blank	2021-03-22
P000005	unchanged	78.5	false	Caucasian	T2	A-T2-01	Device X	2021-09-18	77	female	Alzheimer's Disease	Hypertension,Osteoporosis	minor cognitive improvement	true	Headache	moderate	2021-11-01	resolved	blank	2022-09-18
P000006	unchanged	88	false	Native American	T2	A-T2-02	Placebo	2021-09-20	80	female	Chronic Pain	blank	joint pain unchanged	false	blank	blank	blank	blank	blank	2022-09-22
P000007	improved	81.9	false	Other	T2	A-T2-03	Device X	2021-09-22	75	male	Rheumatoid Arthritis	Osteoporosis	joint pain reduced	true	Nausea	moderate	2021-11-30	resolved	blank	2022-09-23
P000008	unchanged	68.2	true	Caucasian	T2	A-T2-02	Placebo	2021-09-24	72	female	Alzheimer's Disease	Arthritis	minor cognitive improvement	false	blank	blank	blank	blank	Lost to follow-up	2022-01-30
P000009	improved	95.5	false	Hispanic	T3	A-T3-01	Surgery A	2022-04-10	4	female	Rare Genetic Disorder	blank	good surgical outcome	true	Surgical Complication	severe	2022-04-18	resolved	blank	2023-04-10
P000010	responder	98.8	false	Other	T3	A-T3-02	Surgery B	2022-04-15	3	male	Congenital Heart Disease	blank	surgical outcome good	false	blank	blank	blank	blank	blank	2023-04-15
P000011	improved	92.1	false	Asian	T3	A-T3-03	Placebo	2022-04-17	2	female	Congenital Heart Disease	blank	blank	false	blank	blank	blank	blank	blank	2023-04-17
P000012	responder	80.2	false	Middle Eastern	T4	A-T4-01	Drug X 200mg	2021-11-10	38	female	Melanoma	Asthma	tumor size reduced	true	Neutropenia	life-threatening	2021-11-17	resolved	blank	2022-11-10
P000013	non-responder	88.7	false	Pacific Islander	T4	A-T4-02	Placebo	2021-11-12	41	male	Melanoma	blank	tumor size unchanged	false	blank	blank	blank	blank	blank	2022-11-12
P000014	improved	96.4	false	Black	T4	A-T4-01	Drug X 200mg	2021-11-14	35	female	COVID-19	blank	hospitalization avoided	true	Fever	mild	2021-11-20	resolved	blank	2022-11-15
P000015	responder	87.4	false	blank	T5	A-T5-01	Drug Q 400mg	2023-01-02	50	male	Hypertension	Hyperlipidemia,Obesity	BP reduced	false	blank	blank	blank	blank	blank	2024-01-02
P000016	non-responder	94.2	false	Caucasian	T5	A-T5-02	Placebo	2023-01-03	58	male	Hypertension	blank	BP unchanged	false	blank	blank	blank	blank	blank	2024-01-04
P000017	improved	74.9	false	African American	T5	A-T5-01	Drug Q 400mg	2023-01-05	45	female	Type 2 Diabetes	CKD	HbA1c improved	true	Hypoglycemia	moderate	2023-02-01	resolved	blank	2024-01-05
P000018	responder	96	false	Hispanic	T6	A-T6-01	Drug S 20mg	2023-02-10	16	other	Epilepsy	Obesity	seizure frequency decreased	false	blank	blank	blank	blank	blank	2024-02-10
P000019	improved	99.1	false	Caucasian	T6	A-T6-02	Surgery	2023-02-12	25	female	Epilepsy	blank	surgical outcome good	true	Infection	moderate	2023-02-22	resolved	blank	2024-02-12
P000020	responder	97.6	false	Other	T6	A-T6-01	Drug S 20mg	2023-02-15	40	male	Congenital Heart Disease	blank	blank	false	blank	blank	blank	blank	blank	2024-02-15

What the 200 rows show

from the 200-row sample

Unchanged (primary outcome) stands out: 17 of its 58 rows have dropout = true, against 5 of 142 for the rest.

11%dropout = true
91.2median protocol_compliance
2adverse event outcomes
4sexes
4adverse event severities
11baseline conditions

Dropout rate by primary_outcomedropout = true

protocol_compliance200 rows, in bands of 5

Median 91.2, from 59.0 to 100.0.

ethnicity183 rows with a value · 17 left blank

Caucasian54
Other49
Hispanic18
Asian14
African American14
Middle Eastern10
Pacific Islander10
Native American8
Black6

21 columns by typefrom the column list below

string 14
integer 1
float 1
date 3
boolean 2

Columns

21 columns in four groups

blueprint · 21 columns
column	type	description	example
Text 14 columns
`patient_id`	string	Unique identifier for each patient enrolled in the clinical trial.unique	P000001
`trial_id`	string	Unique identifier for the clinical trial.	T1
`arm_id`	string	Identifier for the treatment arm to which the patient is assigned.	A-T1-01
`arm_description`	string	Description of the treatment arm (e.g., placebo, drug A, drug B).	Placebo
`sex`	string	Sex of the patient.male · female · other · unknown	male
`ethnicity`	string	Ethnicity of the patient.9 ethnicities · optional	Caucasian
`baseline_condition`	string	Primary medical condition or diagnosis at baseline.11 conditions	Congenital Heart Disease
`comorbidities`	string	Comma-separated list of comorbid conditions at baseline.optional	Hypertension,Obesity
`primary_outcome`	string	Primary outcome result for the patient (e.g., responder, non-responder, improved, unchanged).4 outcomes	improved
`secondary_outcome`	string	Secondary outcome result for the patient, if applicable.optional	surgical outcome good
`adverse_event_type`	string	Type of the most serious adverse event experienced (if any).optional	Dizziness
`adverse_event_severity`	string	Severity of the most serious adverse event (e.g., mild, moderate, severe, life-threatening).mild · moderate · severe · life-threatening · none · optional	mild
`adverse_event_outcome`	string	Outcome of the most serious adverse event (e.g., resolved, ongoing, fatal).2 outcomes · optional	resolved
`dropout_reason`	string	Reason for dropout if applicable (e.g., adverse event, lost to follow-up, withdrawal of consent).9 reasons · optional	Lost to follow-up
Numbers 2 columns
`age`	integer	Age of the patient at the time of enrollment.0 to 120	5
`protocol_compliance`	float	Percentage of protocol compliance for the patient (0-100).0 to 100	97
Dates and times 3 columns
`enrollment_date`	date	Date when the patient was enrolled in the trial.	2020-03-15
`adverse_event_onset_date`	date	Date when the most serious adverse event began.optional	2020-05-10
`completion_date`	date	Date when the patient completed or exited the trial.optional	2021-03-16
True or false 2 columns
`adverse_event_occurred`	boolean	Indicates if the patient experienced any adverse event during the trial.	false
`dropout`	boolean	Indicates if the patient dropped out of the trial.	false

Use it for

A healthcare dashboard
The dropout rate, protocol_compliance by primary_outcome and a breakdown of ethnicity. Excel, Power BI or Tableau.
Why do 22 of 200 rows have dropout = true?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Patients200
P00000197improved
P00000868.2unchanged
P00002273unchanged
A software demo
Believable patients with trial_id, arm_id and arm_description to fill a screen in front of a buyer.

This dataset200 rows21 columns

Yours1,000 rows21 columns

blueprint · healthcare-clinical-trial-simulation

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 21 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

Patients assigned to active or control arms
Track dosages, visit dates, and outcome scores
Adverse events flagged per patient
Inclusion/exclusion criteria applied
Multiple trial sites simulated

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-clinical-trial-simulation

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?