Health Reference tableQC clean AI-training-safe

US Hospital Prices

What US hospitals actually charge - gross, discounted-cash AND payer-negotiated rates - for each billing code, in one tidy cross-hospital table. Since CMS's July-2024 mandate every hospital must publish a standardized machine-readable file (MRF) of its standard charges, but the files are a nightmare to use: 68 MB to 480 MB+ each, three CMS template variants (CSV 'tall', CSV 'wide', JSON), per-hospital column drift, prices as strings, and negotiated rates buried in nested payer arrays. We stream-parse a curated set of large hospitals that publish the CMS-conformant CSV-tall or JSON template and normalise everything to one schema: hospital, state, payer, plan, code type & code, item description, care setting, and the gross, discounted-cash, negotiated-dollar, min and max charges. Cleaning IS the product. Factual price data published under a federal mandate - freely reusable; shipped as a cleaned/derived aggregate, not the official files.

264K
rows
15
columns
15.1 MB
download
Source
HOSPITALPRICES
Licence
Redistributable open data
Quality
QC clean · 0 failures
Format
Apache Parquet + dictionary

Safe to train on

Built only from a named, redistributable official source under a documented open licence - not scraped web data. No copyright grey zone, no personal data. Ships machine-readable Croissant metadata (ML Commons - loads in Hugging Face / Kaggle / Google), an AI training-licence manifest documenting source, licence and provenance for your model's data governance, and a machine-readable data dictionary (drop it into an agent / RAG prompt so the model knows every column) - all inspectable before you buy.

What's included

  • Gross, discounted-cash AND payer-negotiated dollar rates per billing code - one clean table
  • 8 large US hospitals across 6 states (CA, NC, WI, AZ, ME, OH); CSV-tall + JSON MRF variants
  • Payer × plan × code (CPT/HCPCS/DRG/NDC/RC/CDM) × setting - the join nobody wants to do by hand
  • Prices parsed from strings to real USD; nested-JSON payer arrays flattened; min/max carried
  • The tedious part done: 68-480 MB MRFs in three CMS templates → one tidy Parquet
  • Payer/plan/price data only - no patients, no PII
  • Published to satisfy the CMS Hospital Price Transparency federal mandate (45 CFR 180); factual data, freely reusable - shipped as a cleaned/derived aggregate
  • Source: individual hospitals' machine-readable files (CMS Hospital Price Transparency rule)

Schema

ColumnTypeDescriptionFilledDistinct
hospital_id str Short hospital slug (registry id) 100.0% 8
hospital_name str Hospital name 100.0% 8
state str US state (2-letter) 100.0% 6
payer_name str Payer / insurer name (null for gross/cash-only rows) 97.7% 36
plan_name str Health plan name (null where not applicable) 97.7% 76
code_type str Billing code system (CPT, HCPCS, MS-DRG, APR-DRG, NDC, RC, CDM, LOCAL) 100.0% 8
code str Billing code for the item/service 100.0% 37,501
description str Item / service description 100.0% 112,213
setting str Care setting (inpatient, outpatient, both) 100.0% 5
billing_class str Billing class (facility / professional), where reported 64.1% 2
standard_charge_gross float Gross charge (chargemaster / list price), USD 81.0% 27,516
standard_charge_discounted_cash float Discounted cash price (self-pay), USD 81.8% 30,209
standard_charge_negotiated_dollar float Payer-specific negotiated charge, USD 95.0% 71,855
standard_charge_min float Minimum negotiated charge across payers, USD 97.5% 41,935
standard_charge_max float Maximum negotiated charge across payers, USD 97.5% 42,194

Sample & preview

Every purchase ships as Apache Parquet with a data dictionary and the full QC report. A free sample (first rows + schema) is downloadable here - confirm fit before you buy. Source: HOSPITALPRICES (redistributable open data; attribution passes through - see our Licence).

Don't trust screenshots - drop the sample into your notebook right now.

import pandas as pd
df = pd.read_parquet("us-hospital-prices_sample.parquet")
df.info()   # typed columns, gap-aware, ready to join
⬇ Download free Parquet sample or CSV for Excel