Hospital encounters, diagnoses and claims
Patients, providers, encounters, ICD-10 diagnoses, prescriptions, labs and insurance claims that reconcile from billed to paid.
A hospital network's 1,500 patients: providers, encounters (outpatient, emergency, inpatient), ICD-10 diagnoses, prescriptions, lab results and the insurance claims that follow, from billed through allowed to paid, with denials and their reasons.
39,946 rows across 7 tables, 736 KB zipped. Public domain (CC0), no signup, no attribution required.
What is in it
patient_id, full_name, sex, date_of_birth, insurance, city, region, country, street_address, postal_code, phone, registered_at, encounter_count
provider_id, provider_name, specialty, npi, facility
encounter_id, patient_id, provider_id, patient_sex, insurance, admit_at, encounter_type, los_hours, discharge_at, diagnosis_count, total_billed
diagnosis_id, encounter_id, patient_id, patient_sex, diagnosed_at, icd10_code, description, category
claim_id, encounter_id, patient_id, payer, encounter_type, submitted_at, billed_amount, allowed_ratio, allowed_amount, status, paid_at, denied_at, paid_amount, patient_responsibility, denial_reason
prescription_id, diagnosis_id, encounter_id, patient_id, category, prescribed_at, drug, dose, dose_unit, frequency, days_supply
lab_id, encounter_id, patient_id, collected_at, analyte, unit, value, ref_low, ref_high, flag
What holds, and how it was checked
Each line was measured against these exact files rather than asserted. The same checks ship inside the zip as INTEGRITY.txt, so you can re-run them yourself.
- 11 foreign-key relationships checked, 0 orphaned rows
- No row is dated before the row it belongs to
- 9.0% of 4,737 claims are denied, and every denied claim carries a reason
- Money walks down correctly: paid is at most allowed and allowed at most billed in 100% of 4,737 claims
- 100% of encounters are discharged after they are admitted; median stay is emergency 4 h, inpatient 4.1 days, outpatient 1 h
- 41 distinct ICD-10 codes across 8,427 diagnoses
Questions it can answer
- Which payers deny the most claims, and for what reasons?
- What is the average length of stay by diagnosis category?
- How much of billed revenue is finally paid?
- Which lab flags cluster around which diagnoses?
Generate a custom version
Make your own version in StudioThis dataset was built by Misata Studio's engine and is fixed. RECIPE.json in the zip records the archetype, the sizes and the seed. In Studio you can start from the same kind of data, change the sizes, the rates or the period, and get a new dataset with its own certificate.
Other datasets
- Retail star schema
A dimensional model you can actually practise joins on: one fact table, four dimensions, 63,170 rows, and every join resolving.
- Machine degradation
100 machines monitored from commissioning to failure, with an exact remaining-useful-life label on every one of 23,118 readings.
- Ecommerce storefront
A year of orders across five joined tables, with a real Q4 peak and totals that reconcile to the cent.
- B2B SaaS subscription analytics
Accounts, seats, MRR, churn and support load, where company size actually drives the plan.
- Credit risk portfolio
3,000 borrowers and 4,200 commercial loans, where a credit rating actually predicts whether the loan defaults, at the rate S&P's own data says it should.
- Network intrusion / netflow
500 hosts and 20,000 labeled flows, where a port scan, a DDoS flood, and a brute-force attempt each carry the real statistical signature their MITRE ATT&CK technique actually leaves in traffic.
- Contact center queueing (Erlang C)
4 queues, 2,400 half-hour intervals over a full business month, where agents_staffed is what Erlang C (1917) says is actually required to clear each queue's own SLA target, not a plausible-looking number.
- Manufacturing SPC (Cpk / Xbar-R)
5 processes, 450 subgroups, 2,250 measurements, where process capability and out-of-control detection come from a real Xbar-R control chart -- including one process with an engineered tool-wear drift that actually trips Western Electric rules where it happens.
- Anti-money-laundering transactions with ground truth
A bank's customers, accounts and transactions, with the laundering typologies labelled, the rule-based alerts raised, and the cases and SARs that followed.
- Clinical trial: sites, patients, visits and adverse events
Two trials across nine sites: enrolment, scheduled visits, dosing, lab biomarkers and graded adverse events, all in the right order.
- Factory sensors with failure labels
A year of hourly sensor readings from six machines, with the degradation stage, remaining useful life, and the failures and work orders they lead to.