Synthetic Patient Health Trajectories

This dataset provides comprehensive, longitudinal synthetic patient records simulating chronic disease progression, including demographics, clinical encounters, vital signs, laboratory results, medications, and outcomes. Designed for safe AI/ML experimentation, it enables time-series modeling, predictive analytics, and healthcare research without patient privacy risks.

  • last updated 22 Jul 2025
  • by GoMask
The brief that made it

Developing and validating AI/ML models for chronic disease progression and risk prediction

Sample rows

preview · 8 of 200 rows · all 27 columns
patient_idstringencounter_typestringvital_sign_oxygen_saturationfloatracestringgenderstringbirth_datedateethnicitystringchronic_conditionstringdiagnosis_datedateencounter_idstringencounter_datedatetimeprovider_idstringvisit_reasonstringvital_sign_heart_ratefloatvital_sign_systolic_bpfloatvital_sign_diastolic_bpfloatvital_sign_temperaturefloatvital_sign_respiratory_ratefloatlab_test_namestringlab_test_valuefloatlab_test_unitstringmedication_namestringmedication_dosestringmedication_routestringoutcome_eventstringoutcome_datedatenotesstring
H4Q7T9ZCoutpatient97Whitefemale1950-04-13Not Hispanic or LatinoAlzheimer's disease2013-11-22ENCOUNTER10012023-03-14T09:34:00PROV1023Memory loss evaluation711227436.516Hemoglobin A1c5.4%Donepezil10 mgoralblankblankPatient presented with ongoing memory decline, stable on current medication, no acute events.
BD2W8R3Loutpatient98Black or African Americanmale1996-07-22blankType 1 diabetes mellitus2005-09-01ENCOUNTER10022023-01-31T13:12:00PROV1040Routine diabetes follow-up831187536.718Blood glucose116mg/dLInsulin glargine22 unitssubcutaneousblankblankBlood glucose levels well controlled. No episodes of hypoglycemia. Continues on insulin therapy.
QZ8TM4KNinpatient96blankfemale2009-02-18blankCongenital heart defect2009-03-10ENCOUNTER10032023-02-08T10:44:00blankSurgical follow-up104935636.424BNP220pg/mLFurosemide20 mgIVhospitalization2023-02-10Post-surgical monitoring for congenital heart defect repair, stable hemodynamics, on diuretic therapy.
LJ3Y5TUNemergency80Asianmale1947-11-04Hispanic or LatinoChronic obstructive pulmonary disease2008-05-15ENCOUNTER10042023-03-18T15:27:00PROV1005Acute respiratory distress1281438637.234Arterial blood gas7.25pHAlbuterol2 puffsinhaledhospitalization2023-03-20Patient admitted from ED for COPD exacerbation, started on nebulized bronchodilators and oxygen support.
V7K6ZQ1Boutpatient94blankmale2017-12-05blankAsthma (pediatric)2022-03-09ENCOUNTER10052023-04-02T11:11:00PROV1011Cough and wheezing11288503732Peak flow180L/minAlbuterol2 puffsinhaledblankblankPediatric patient with moderate asthma exacerbation, responded to inhaled albuterol, no acute complications.
F3S2N7RLoutpatient98Whitefemale1974-09-30Not Hispanic or LatinoHypertension2015-06-12ENCOUNTER10062023-04-11T14:34:00PROV1102Hypertension management851388936.617Serum creatinine1mg/dLLisinopril20 mgoralblankblankBlood pressure slightly elevated, advised medication adherence and lifestyle changes, no acute symptoms.
Z8P3C6YDoutpatient97Native Hawaiian or Other Pacific Islandermale1988-06-21blankChronic kidney disease stage 32016-05-18ENCOUNTER10072023-02-19T09:23:00PROV1098CKD routine monitoring781308036.818eGFR48mL/minLosartan50 mgoralblankblankCKD stage 3, kidney function stable, blood pressure well controlled, continue current regimen.
M2X5R4VLtelehealth98Whiteother2001-03-30Hispanic or LatinoRheumatoid arthritis2017-12-06ENCOUNTER10082023-05-05T15:01:00blankJoint pain check-in821177336.519blankblankblankMethotrexate15 mgoralblankblankTelehealth session for joint pain, no new flares, continues on DMARD therapy, tolerating medication.

What the 200 rows show

from the 200-row sample

Emergency (encounter type) stands out: mean vital_sign_oxygen_saturation is 84.4, against 95.5 for the rest.

  • 97median vital_sign_oxygen_saturation
  • 2ethnicities
  • 2outcome events
  • 4genders
  • 6medication routes
  • 28lab test units
Mean vital_sign_oxygen_saturation by encounter_type200 rows
05010097.2outpat…128 rows89.0inpati…40 rows84.4emerge…16 rows98.2telehe…13 rows97.3other3 rows
vital_sign_oxygen_saturation200 rows, in bands of 10
0851700000000531164050100vital_sign_oxygen_saturation →

Median 97, from 78 to 99.

race155 rows with a value · 45 left blank
  1. White80
  2. Asian36
  3. Black or African American25
  4. Native Hawaiian or Other Pacific Islander6
  5. American Indian or Alaska Native4
  6. Other4
27 columns by typefrom the column list below
  • string 16
  • float 7
  • date 3
  • datetime 1

Columns

27 columns in three groups
blueprint · 27 columns
columntypedescriptionexample
Text 16 columns
patient_idstringUnique synthetic identifier for each patientuniqueH4Q7T9ZC
genderstringPatient's gender identitymale · female · other · unknownfemale
racestringPatient's self-identified race6 races · optionalWhite
ethnicitystringPatient's self-identified ethnicity2 ethnicities · optionalNot Hispanic or Latino
chronic_conditionstringPrimary chronic disease diagnosed for the patientAlzheimer's disease
encounter_idstringUnique identifier for each patient encounter/visituniqueENCOUNTER1001
encounter_typestringType of encounter (e.g., outpatient, inpatient, emergency, telehealth)outpatient · inpatient · emergency · telehealth · otheroutpatient
provider_idstringUnique identifier for the healthcare provider seen during the encounteroptionalPROV1023
visit_reasonstringChief complaint or reason for the visitoptionalMemory loss evaluation
lab_test_namestringName of the laboratory test performed during the encounteroptionalHemoglobin A1c
lab_test_unitstringUnit of measurement for the laboratory test resultoptional%
medication_namestringName of medication prescribed or administered during the encounteroptionalDonepezil
medication_dosestringDose and unit of the medication (e.g., 10 mg)optional10 mg
medication_routestringRoute of administration for the medication (e.g., oral, IV)6 routes · optionaloral
outcome_eventstringClinical outcome or event observed during or after the encounter (e.g., hospitalization, death, complication)2 events · optionalhospitalization
notesstringFree-text clinical notes or summary for the encounteroptionalPatient presented with on…
Numbers 7 columns
vital_sign_heart_ratefloatHeart rate measured during the encounter (beats per minute)20 to 250 · optional71
vital_sign_systolic_bpfloatSystolic blood pressure measured during the encounter (mmHg)50 to 300 · optional122
vital_sign_diastolic_bpfloatDiastolic blood pressure measured during the encounter (mmHg)30 to 200 · optional74
vital_sign_temperaturefloatBody temperature measured during the encounter (Celsius)30 to 45 · optional36.5
vital_sign_respiratory_ratefloatRespiratory rate measured during the encounter (breaths per minute)5 to 60 · optional16
vital_sign_oxygen_saturationfloatOxygen saturation measured during the encounter (percentage)50 to 100 · optional97
lab_test_valuefloatResult value of the laboratory testoptional5.4
Dates and times 4 columns
birth_datedatePatient's date of birth1950-04-13
diagnosis_datedateDate of initial chronic disease diagnosis2013-11-22
encounter_datedatetimeDate and time of the patient encounter2023-03-14T09:34:00
outcome_datedateDate of the outcome event, if applicableoptional2023-02-10

Use it for

  • median vital s…97200 rowsmean vital sign oxyge…97.2outp…89.0inpa…84.4emer…98.2tele…

    A healthcare dashboard

    Vital_sign_oxygen_saturation by encounter_type and a breakdown of race. Excel, Power BI or Tableau.

  • Why do the 16 emergency rows have a mean vital_sign_oxygen_saturation of 84.4?

    A root-cause class exercise

    Hand out the rows and one question. The answer is in the data, not in the brief.

  • A software demo

    Believable patients with gender, birth_date and race to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 27 columns, your size and your rules. See 20 rows before you pay.

Preview 20 rows free

1,000 rows: $1.99 · 10,000: $12.99One-time. No subscription. All prices

This dataset200 rows27 columns
Yours1,000 rows27 columns

blueprint · synthetic-patient-health-trajectories

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 27 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
  • Each patient has at least three chronic condition codes
  • Records span a minimum of 2 years per patient
  • Includes synthetic demographic, lab, and medication data
  • No patient identifier is reused
Rows
Open the blueprint in Data Factory

1 credit per row. New accounts start with 25 free credits.

Exports
CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence
yours to use, including commercially
API slug
synthetic-patient-health-trajectories

What should your data show?

Preview 20 rows free
No signup. No card.