Structured Health Records v3

Synthetic dataset with transparent data card and QA.

Records
5,000
Modalities
Tabular
Annotations
Diagnosis, Outcome

Age Percentiles

Percentiles normalized across min–max

min 00.00%
p1015.29%
p2529.41%
p50 (median)51.76%
p7576.47%
p9090.59%
max 85100.00%

Top Diagnoses

Most frequent diagnoses in the dataset

Healthy24.60%
Common Cold12.00%
Hypertension10.68%
Influenza7.84%
Diabetes7.62%
Depression6.86%
Heart Disease6.32%
Pneumonia5.02%
Asthma4.66%
Cancer4.14%

Visit Types

Proportion of visit types

Primary Care60.74%
Specialist20.08%
Emergency14.48%
Urgent Care4.70%

Gender Distribution

Proportion by gender

Female49.76%
Male48.24%
Non-binary2.00%

Insurance Types

Proportion by insurance type

Private45.78%
Medicare25.42%
Medicaid19.48%
Self-Pay7.56%
Other1.76%

Outcomes

Outcome distribution

Recovered57.74%
Ongoing Treatment39.72%
Deteriorated2.18%
Deceased0.36%

Top Medications

Most frequent medications

None61.14%
Lisinopril1.10%
Calcium0.96%
Multivitamin0.96%
Amlodipine0.84%
Vitamin D0.80%
Hydrochlorothiazide0.78%
Bupropion0.72%
Glipizide0.72%
Insulin0.64%

Top Symptoms

Most frequent symptoms

None24.60%
runny_nose;sore_throat;cough;headache;fatigue3.98%
headache;dizziness;chest_pain;fatigue3.94%
fatigue;headache3.44%
fever;cough;fatigue;muscle_pain;headache2.42%
fatigue;loss_of_interest;sleep_disturbances;mood_changes2.36%
fatigue;frequent_urination;increased_thirst;blurred_vision2.24%
chest_pain;shortness_of_breath;fatigue;dizziness2.06%
fever;cough;shortness_of_breath;chest_pain;fatigue1.80%
shortness_of_breath;cough;wheezing;chest_tightness1.54%

Sample Preview

No sample preview available.