HEALTHCARE COST & UTILIZATION PROJECT

User Support

Do Your own analysis
Explore Expert Research & Limited Datasets

Introduction to the HCUP National Inpatient Sample (NIS), 2019

HEALTHCARE COST AND UTLIZATION PROJECT – HCUP
A FEDERAL-STATE-INDUSTRY PARTNERSHIP IN HEALTH DATA

Sponsored by the Agency for Healthcare Research and Quality

 

 

INTRODUCTION TO

THE HCUP NATIONAL INPATIENT SAMPLE (NIS)

2019

 

 

Please read all documentation carefully.

BEGINNING WITH DATA YEAR 2016, THE NIS CONTAINS A FULL YEAR OF ICD-10-CM/PCS CODES.
Beginning with data year 2016, the NIS includes a full calendar year of data with diagnosis and procedure codes reported using the ICD-10-CM/PCS1 coding system. The file structure is similar to the file structure of the NIS in data years prior to 2015.

THE 2015 NIS CONTAINS ICD-9-CM AND ICD-10-CM/PCS CODES
On October 1, 2015, hospital administrative data began using ICD-10-CM/PCS, so the first nine months of 2015 contain ICD-9-CM codes and the last three months contain ICD-10-CM/PCS codes. Data elements and data structure for the 2015 NIS are different. Trends based on diagnoses or procedures will be affected.

Data elements derived from AHRQ software tools are not available for ICD-10-CM/PCS data on the 2016-2017 NIS.

THE NIS WAS REDESIGNED BEGINNING WITH 2012
Starting in data year 2012, the NIS is a sample of discharges from all hospitals participating in HCUP. For prior years, the NIS was a sample of hospitals. For details, see the 2012 NIS Redesign Report.

 

Issued September 2021

Agency for Healthcare Research and Quality
Healthcare Cost and Utilization Project (HCUP)
Phone: (866) 290-HCUP (4287)
Email: hcup@ahrq.gov
Website: www.hcup-us.ahrq.gov

 

NIS Data and Documentation Distributed by:
HCUP Central Distributor
Phone: (866) 290-HCUP (4287) (toll-free)
Email: HCUP@ahrq.gov



Table of Contents



HCUP NATIONAL INPATIENT SAMPLE (NIS) SUMMARY OF DATA USE RESTRICTIONS

***** REMINDER *****


All users of the NIS must take the online HCUP Data Use Agreement (DUA) training course, and read and sign a Data Use Agreement. Details and links may be found on the following page.

Authorized users of HCUP data agree to the following restrictions:a

  • Will not use the data for any purpose other than research, analysis, and aggregate statistical reporting.

  • Will not re-release any data to unauthorized users.

  • Will not redistribute HCUP data by posting on any website or publishing in any other publicly accessible online repository. If a journal or publication requests access to data or analytic files, will cite restrictions on data sharing in the Data Use Agreement and direct them to AHRQ HCUP (www.hcup-us.ahrq.gov) for more information on accessing HCUP data.

  • Will not identify or attempt to identify any individual, including by the use of vulnerability analysis or penetration testing. Methods that could be used to identify individuals directly or indirectly shall not be disclosed or published.

  • Will not report any statistics where the number of observations (i.e., individual discharge records) in any given cell of tabulated data is less than or equal to 10 (< 10).

  • Will not publish information that could identify individual establishments (e.g., hospitals) and will not contact establishments.

  • Will not use the data concerning individual establishments for commercial or competitive purposes affecting establishments, or to determine rights, benefits, or privileges of establishments.

  • Will not use the data for criminal and civil litigation, including expert witness testimony or for law enforcement activities.

  • Will not use data elements from the proprietary severity adjustment software packages (e.g., 3M™ APR-DRGs) for any commercial purpose or to disassemble, decompile, or otherwise reverse engineer the proprietary software.

  • Will acknowledge in reports that data from the "Healthcare Cost and Utilization Project (HCUP)" were used, including names of the specific databases used for analysis.b

Any violation of the limitations in the Data Use Agreement is punishable under Federal law by a fine, up to five years in prison, or both. Violations may also be subject to penalties under State statutes.

a This is a summary of key terms of the Data Use Agreement for Nationwide Databases; please refer to the DUA for full terms and conditions.
b Suggested citations for the HCUP databases are provided in the Requirements for Publishing with HCUP Data available at www.hcup-us.ahrq.gov/db/publishing.jsp.


Return to Introduction



HCUP DATA USE AGREEMENT REQUIREMENTS

All HCUP data users, including data purchasers and collaborators, must complete the online HCUP Data Use Agreement (DUA) Training Tool, and read and sign the HCUP Data Use Agreement. Proof of training completion and signed Data Use Agreements must be submitted to the HCUP-US Central Distributor.

Data purchasers will be required to provide their DUA training completion code and will execute their DUAs electronically as a part of the online ordering process. The DUAs and training certificates for collaborators and others with access to HCUP data should be submitted directly to the HCUP Central Distributor using the contact information below.

The online DUA training course is available at: www.hcup-us.ahrq.gov/tech_assist/dua.jsp.

The HCUP Data Use Agreement for the NIS is available on the HCUP User Support (HCUP-US) website at: www.hcup-us.ahrq.gov/team/NationwideDUA.jsp

Return to Contents

HCUP CONTACT INFORMATION

HCUP Central Distributor and HCUP User Support

Information about the content of the HCUP databases is available on the HCUP User Support (HCUP-US) website (www.hcup-us.ahrq.gov).

If you have questions, please review the HCUP Frequently Asked Questions located at www.hcup-us.ahrq.gov/tech_assist/faq.jsp.

If you need further technical assistance, please contact the HCUP Central Distributor and User Support team at:

Phone: 866-290-4287 (toll free)
Email: HCUP@AHRQ.gov

Mailing address:
HCUP Central Distributor
IBM Watson Health
5425 Hollister Ave, Suite 140
Santa Barbara, CA 93111

We would like to receive your feedback on the HCUP data products.

Please send user feedback to hcup@ahrq.gov.

Return to Contents

WHAT'S NEW IN THE 2019 NATIONAL INPATIENT SAMPLE (NIS)?

  • Beginning with data year 2019, data elements derived from the Elixhauser Comorbidity Software Refined for ICD-10-CM, the CCSR for ICD-10-PCS procedures, and Procedure Classes Refined for ICD-10-CM are available in the NIS Diagnosis and Procedure Groups file.
  • Beginning with data year 2019, New Hampshire data is again included in the NIS.

UNDERSTANDING THE NIS

  • This document, Introduction to the NIS, 2019, summarizes the content of the NIS and describes the development of the NIS sample and weights.

  • In addition, the HCUP-US website has a section on ICD-10-CM/PCS Resources that summarizes key issues for researchers using HCUP and other administrative databases that include ICD-10-CM/PCS coding. The web page provides general guidance and forewarning to users analyzing outcomes that may be affected by the transition to the ICD-10-CM/PCS coding system and lists other related web resources.

  • Important considerations for data analysis are provided along with references to detailed reports.

  • In-depth documentation for the NIS is available on the HCUP User Support (HCUP-US) website (www.hcup-us.ahrq.gov/db/nation/nis/nisdbdocumentation.jsp). Please refer to detailed documentation before using the data.

Return to Introduction



HEALTHCARE COST AND UTILIZATION PROJECT — HCUP
A FEDERAL-STATE-INDUSTRY PARTNERSHIP IN HEALTH DATA

Sponsored by the Agency for Healthcare Research and Quality

The Agency for Healthcare Research and Quality and
the staff of the Healthcare Cost and Utilization Project (HCUP) thank users for
purchasing the HCUP National Inpatient Sample (NIS).



HCUP National Inpatient Sample (NIS)

ABSTRACT

The National Inpatient Sample (NIS) is part of the Healthcare Cost and Utilization Project (HCUP), sponsored by the Agency for Healthcare Research and Quality (AHRQ).

The NIS is a database of hospital inpatient stays derived from billing data submitted by hospitals to statewide data organizations across the U.S. These inpatient data include clinical and resource use information typically available from discharge abstracts. Researchers and policymakers use the NIS to make national estimates of healthcare utilization, cost, quality, and outcomes.

The NIS contains information on all hospital stays, regardless of expected payer for the hospital stay. For Medicare, the NIS includes Medicare Advantage patients, a population that is often missing from Medicare claims data but that comprises as much as 30 percent of Medicare beneficiaries.1 The NIS' large sample size enables analyses of rare conditions, uncommon treatments, and special patient populations.

The NIS is sampled from the State Inpatient Databases (SID), which include all inpatient data that are currently contributed to HCUP. The 2019 NIS sampling frame includes data from 49 statewide data organizations (48 States plus the District of Columbia), covering 98 percent of the U.S. population in Appendix I, Figure 1 and including 97 percent of discharges from U.S. community hospitals Appendix I, Table 4. A list of the 49 statewide data organizations participating in the NIS and a summary of NIS States, hospitals, and discharges by year are provided in Appendix 1 (Table 2 and Table 3). The NIS includes weights for calculating national estimates.

The 2012 National Inpatient Sample (NIS) was redesigned to improve national estimates. To highlight the design change, beginning with 2012 data, AHRQ renamed the NIS from the "Nationwide Inpatient Sample" to the "National Inpatient Sample." The redesign incorporates three major types of changes:

The new sampling strategy produces more precise estimates than the previous NIS design by reducing sampling error. For many estimates, confidence intervals under the new design are about half the length of confidence intervals under the previous design.

Key features of the most recent NIS (2019) include:

Changes to the NIS may impact some types of analyses. For example, the elimination of hospital identifiers means that hospital linkages can no longer be done with the NIS, and the sampling of discharges means that analyses relying on a census of discharges from sampled hospitals (e.g. hospital volume analysis) can no longer be performed. Because inpatient data are available for many individual States through the HCUP Central Distributor, State inpatient data can be used for those analyses that require a census of discharges from individual hospitals, local market areas, and States.

A summary of design changes is provided in Table 1 in Appendix I, The National Inpatient Sample (NIS) Design Changes. For a detailed description of the NIS redesign, please see the 2012 NIS Redesign Report available on the HCUP-US website.

The NIS is available yearly, beginning with 1988, allowing analysis of trends over time. Analyses of time trends using the HCUP NIS are recommended from 1993 forward because earlier samples were drawn from only 8 to 11 States, covering less than 50 percent of the hospital discharge population. For trends analysis using NIS data 2011 and earlier, revised weights should be used to make estimates comparable to the new 2012 design. Users should refer to 1993-2011 NIS Trend Weights Files and the report, Using the HCUP National Inpatient Sample to Estimate Trends, available on the HCUP-US website, for details.

Because ICD-10-CM/PCS was introduced October 1, 2015, trends that rely on diagnosis and procedures may be interrupted. Analyses that do not rely on diagnosis and procedure coding should not be affected. HCUP has developed recommendations for reporting statistics (e.g., counts, rates, averages) that are based on HCUP data with a mixture of ICD-9-CM and ICD-10-CM/PCS codes. These recommendations apply to calendar year 2015 data (which includes both ICD-9-CM and ICD-10-CM/PCS codes), as well as reporting trends that span the October 1, 2015 transition date (before and after the introduction of ICD10-CM/PCS). In addition, the HCUP-US website has a section on ICD-10-CM/PCS Resources that summarizes key issues for researchers using HCUP and other administrative databases that include ICD-9-CM and ICD-10-CM/PCS coding.

Appendix III provides a summary of data elements and when they are effective. The data elements included in the NIS can vary across data years.

Access to the NIS is open to users who sign Data Use Agreements. Uses are limited to research and aggregate statistical reporting.

For more information on the NIS, please visit the AHRQ-sponsored HCUP-US website at www.hcup-us.ahrq.gov/db/nation/nis/nisdbdocumentation.jsp.

Return to Introduction



INTRODUCTION TO THE HCUP NATIONAL INPATIENT SAMPLE (NIS)

Overview of NIS Data

The National Inpatient Sample (NIS) contains all-payer data on hospital inpatient stays from States participating in the Healthcare Cost and Utilization Project (HCUP). Each year of the NIS includes over 7 million inpatient stays.

The NIS contains clinical and resource use information included in a typical discharge abstract. The NIS is a database of hospital inpatient stays derived from billing data submitted by hospitals to statewide data organizations across the U.S.

NIS 2012 Redesign

The 2012 National Inpatient Sample (NIS) was redesigned to improve national estimates. To highlight the design change, beginning with 2012 data, AHRQ renamed the NIS from the "Nationwide Inpatient Sample" to the "National Inpatient Sample." The redesign incorporates three major types of changes.

Impact of New Design on Estimates

The new NIS is now stratified by nine Census Divisions rather than four Census Regions, which will allow more refined analyses of geographic variation in U.S. hospitalizations. The new sampling strategy produces more precise estimates than the previous NIS design by reducing sampling error. For national-level estimates, the 2012 NIS systematic design reduces the margin of error by 42 to 48 percent over the previous NIS design for the outcomes studied (total discharges, average length-of-stay, average charges, and mortality rates); thus the new NIS design generates estimates that are about twice as precise as those from the old design. The margin of error is commonly used by the popular press to describe the reliability of sample statistics. Technically, it is the half-width of a confidence interval around a sample statistic, such as a rate or a mean. The systematic design also consistently reduced the margin of error for estimates at the DRG level.

Because of the changes implemented in the 2012 redesign, users should expect one-time disruptions to historical trends for counts, rates, and means estimated from the NIS, beginning with data year 2012. For 2012 it is expected to see overall trends in discharge counts to decline by about 4.3 percent, overall trends in average length-of-stay to decline by about 1.5 percent, overall trends in total charges to decline by about 0.5 percent, and overall trends in hospital mortality to decline by about 2.0 percent. New weights for prior years of the NIS to make prior year estimates comparable to the new design implemented in 2012 are available for download under 1993-2011 NIS Trend Weights Files from the NIS Database Documentation page on the HCUP-US website.

A summary of design changes is provided in Table 1 in Appendix I, The National Inpatient Sample (NIS) Design Changes. For a detailed description of the NIS redesign and the effects on sample estimates, please see the 2012 NIS Redesign Report available on the HCUP-US website.

The NIS sampling and weighting strategy was also revised in 1998. A detailed report describing this revision, Changes in NIS Sampling and Weighting Strategy for 1998, is available on the HCUP-US website at HCUP-US website www.hcup-us.ahrq.gov.

Types of Hospitals Included in the NIS

The NIS is a sample of discharges from U.S. community hospitals, defined as "all non-Federal, short-term, general, and other specialty hospitals, excluding hospital units of institutions."2 Included among community hospitals are specialty hospitals such as obstetrics-gynecology, ear-nose-throat, orthopedic, and pediatric institutions. Also included are public hospitals and academic medical centers.

Starting in 2005, the AHA included long term acute care facilities with average lengths-of-stay less than 30 days in the definition of community hospitals, and such facilities were included in the NIS sampling frame. However, because long-term acute care hospital data was not uniformly available from all States participating in HCUP, and their average length of stay (ALOS) was over 25 days (unlike other community hospitals with an ALOS of about 4.5 days), long-term acute care hospitals were excluded in the 2012 NIS redesign. Exclusion of long-term acute care hospitals mainly affects statistics related to the elderly—estimates of discharge counts, ALOS, charges, and mortality are reduced for the older age groups because of the demographics of patients in long-term acute care hospitals.

Return to Introduction

Sample Design for the NIS

This universe of U.S. community hospitals is divided into strata using five hospital characteristics: ownership/control, bed size, teaching status, urban/rural location, and the nine U.S. census divisions (the four census regions were used prior to the 2012 NIS).

The systematic sample starting in 2012 is a self-weighted sample design similar to simple random sampling, but it is more efficient. It ensures that the sample is representative of the population on the following critical factors:

Weighted Estimates

To facilitate the production of national estimates, discharge weights are provided, along with information necessary to calculate the variance of estimates. More information on using the discharge weights for generating national estimates and studying trends is provided under How to Use the NIS for Data Analysis. Also, refer to the Checklist for Working with the NIS (www.hcup-us.ahrq.gov/db/nation/nis/nischecklist.jsp) to verify adherence to data use, methodology, and reporting requirements.

Detailed information on the design of the NIS prior to 2006 is available in the year-specific reports on Design of the Nationwide Inpatient Sample found on the NIS Related Reports page on the HCUP-US website. Detailed information on the design of the NIS from 2006-2012 is available in the NIS Introduction for each year on the NIS Database Documentation - Archive page on the HCUP-US website.

ICD-10-CM/PCS Started October 1, 2015, at the Beginning of Fiscal Year 2016

On October 1, 2015, the United States transitioned from using ICD-9-CM to ICD-10-CM/PCS code sets for reporting medical diagnoses and inpatient procedures.3 ICD-10-CM/PCS consists of two parts:

The HCUP-US website has a section on ICD-10-CM/PCS Resources that summarizes key issues for researchers using HCUP and other administrative databases that include ICD-10-CM/PCS coding. The web page provides general guidance and forewarning to users analyzing outcomes that may be affected by the transition to the ICD-10-CM/PCS coding system and lists other related web resources.

NIS Data Sources, Hospitals, and Inpatient Stays

The NIS is sampled from the State Inpatient Databases (SID), which include all inpatient data that are currently contributiing to HCUP. The 2019 NIS sampling frame includes data from 49 statewide data organizations (48 states plus the District of Columbia), covering 98 percent of the U.S. population (Appendix I, Figure 1) and including 97 percent of discharges from U.S. community hospitals (Appendix I, Table 4). A list of the 49 HCUP Partner organizations participating in the NIS and a summary of NIS States, hospitals, and discharges by year are provided in Appendix 1 (Table 2 and Table 3). The NIS includes weights for calculating national estimates.

Partner Restrictions

Some HCUP Partners that contributed data to the NIS imposed restrictions on the release of certain data elements or on the number and types of hospitals that could be included in the database. Because of confidentiality laws, some data sources were prohibited from providing HCUP with discharge records that indicated specific medical conditions and procedures, specifically HIV/AIDS, behavioral health, and abortion. Detailed information on these State-specific restrictions is available in Appendix II.

Return to Introduction

File Structure of the NIS

Each release of the NIS includes:

The NIS Database is distributed as fixed-width ASCII-formatted data files delivered via secure digital download from the Online HCUP Central Distributor. The files are compressed and encrypted with SecureZIP® from PKWARE. Users will need the password provided by the HCUP Central Distributor.

The NIS product is downloaded in a single zipped file for each year which contains several data-related compressed files and accompanying documentation. There are three discharge-level files and one hospital-level file:

Discharge-level files

Hospital-level files

On the HCUP-US website, NIS users can access complete file documentation, including data element notes, file layouts, summary statistics, and related technical reports. Similarly, users can also download SAS, SPSS, and Stata load programs from this website. Available online documentation and supporting files are detailed in Appendix I, Table 5.

File structures can differ for a given year from the general structure described above. See below for specifics.

Return to Introduction

File Structure of the NIS Beginning with 2016 Data

Beginning with data year 2016, the NIS is a calendar year file that includes diagnoses and procedures coded using only ICD-10-CM/PCS. The file structure is similar to the file structure of the NIS prior to 2015.

Return to Introduction

File Structure of the 2015 NIS

For the 2015 data, because of the transition to ICD-10-CM/PCS on October 1, 2015, data elements related to diagnoses and procedures are included in files that are split into two files. Nine months of the 2015 data with ICD-9-CM codes (discharges from January 1, 2015 - September 30, 2015) are in one set of files labeled Q1-Q3. Three months of 2015 data with ICD-10-CM/PCS codes (discharges from October 1, 2015 - December 31, 2015) are in a separate set of files labeled Q4. More information about the changes to the HCUP databases for ICD-10-CM/PCS and use of data across the two coding systems may be found on the HCUP-US website under ICD-10-CM/PCS Resources.

Return to Introduction

File Structure of the NIS Prior to 2015

The NIS databases prior to 2015 are annual, calendar year files based on discharge date that include ICD-9-CM coding only. The Inpatient Core File and the Hospital File are available all data years. The Disease Severity File is available starting in data year 2002, and the Diagnosis and Procedure Groups File is available starting in data year 2005.

Return to Introduction

NIS Data Elements

All releases of the NIS contain two types of data: inpatient stay records and hospital information with weights to calculate national estimates. Appendix III identifies the data elements in each NIS file:

Not all data elements in the NIS are uniformly coded or available across all States. The tables in Appendix III are not complete documentation for the data. Please refer to the NIS documentation located on the HCUP-US website (www.hcup-us.ahrq.gov) for comprehensive information about data elements and the files.

Users interested in applying AHRQ software tools to the NIS for data years including ICD-10-CM/PCS-coded data to produce data elements currently unavailable in the database files may do so by downloading the respective tool(s) from the Research Tools section of the HCUP User Support (HCUP-US) website. Additionally, users may wish to review the HCUP Software Tools Tutorial, which provides instructions on how to apply the AHRQ software tools to HCUP or other administrative databases.

Getting Started

Computer Specifications Required for Using the NIS

To load and analyze the NIS data on a computer, users will need the following:

Decompressing the NIS Files

To extract the data files from the compressed download file, follow these steps:

  1. Create a directory for the NIS on your hard drive.
  2. Unzip the compressed NIS product file into the new directory using a third-party zip utility. This will create four compressed, encrypted data-related files in the new directory. You will be prompted to enter the encryption password (sent separately by email) to decrypt the file.

    Please note that attempts to unzip encrypted files using the built-in zip utility in Windows® (Windows Explorer) or Macintosh® (Archive Utility) will produce an error message warning of incorrect password and/or file or folder errors. The solution is to use a third-party zip utility.

    Third-party zip utilities are available from the following reputable vendors on their official websites.

    • ZIP Reader (Windows) (free download offered by the PKWARE corporation)
    • SecureZIP® for Mac or Windows (free evaluation and licensed/fee software offered by the PKWARE corporation)
    • WinZip (Windows) (evaluation and fee versions offered by the WinZip corporation)
    • Stuffit Expander® (Mac) (free evaluation and licensed/fee software offered by Smith Micro corporation)

  3. Unzip each of the compressed, encrypted data-related files using the same password and third-party zip utility method. This will place the data-related ASCII files in this same directory by default.

Return to Introduction

Downloading and Running the Load Programs

Programs to load the data into SAS, SPSS, or Stata, are available on the HCUP User Support website (HCUP-US). The SAS and SPSS programs are available beginning with 1998. The Stata programs begin with 2004. To download and run the load programs, follow these steps:

  1. Go to the NIS Database Documentation page on HCUP-US at www.hcup-us.ahrq.gov/db/nation/nis/nisdbdocumentation.jsp.
  2. Go to the "File Specifications and Load Programs" section on this page.
  3. Click on "Nationwide SAS Load Programs", "Nationwide SPSS Load Programs", or "Nationwide Stata Load Programs" to go to the corresponding Load Programs page.
  4. Select the data year and the database ("NIS") from the drop down lists on this page. Or you may select "NIS Load All Years" to obtain a zipped file with all load programs for multiple years at once.
  5. Select and save the load programs you need. The load programs are specific to the data year. For example, the load program for the 2019 NIS Core File is found under the link "SAS NIS 2019 Core File" in the list generated by selecting "2019" and "NIS." Save the load programs into the same directory as the NIS ASCII files on your computer.
  6. Edit and run the load programs as appropriate for your computing environment to create the analysis files. For example, modify the directory paths to point to the location of your input and output files.

NIS Documentation

Year-specific NIS documentation files on the HCUP-US website (www.hcup-us.ahrq.gov) provide important resources for the user. Refer to these resources to understand the structure and content of the NIS and to aid in using the database.

Table 5 in Appendix I details both the NIS related reports and the comprehensive NIS database documentation available on HCUP-US.

Return to Introduction

HCUP Online Tutorials

For additional assistance, AHRQ has created the HCUP Online Tutorial Series, a series of free, interactive courses which provide training on technical methods for conducting research with HCUP data. Topics include an HCUP Overview Course and these tutorials:

New tutorials are added periodically and existing tutorials are updated when necessary. The Online Tutorial Series is located on the HCUP-US website at www.hcup-us.ahrq.gov/tech_assist/tutorials.jsp.

Return to Introduction

HOW TO USE THE NIS FOR DATA ANALYSIS

This section provides a brief synopsis of special considerations when using the NIS. Before reporting findings using the NIS, you should refer to the Checklist for Working with the NIS (www.hcup-us.ahrq.gov/db/nation/nis/nischecklist.jsp) to verify adherence to data use, methodology, and reporting requirements.

Return to Introduction

Data Use Agreement

If anyone other than the original purchaser uses the NIS data, be sure to have them read and sign a Data Use Agreement, after viewing the online Data Use Agreement Training Tool available on the HCUP-US website (www.hcup-us.ahrq.gov). A copy of the signed Data Use Agreements must be sent to the HCUP Central Distributor. See page 2 for the mailing address.

Return to Introduction

Choosing Data Elements for Analysis

Return to Introduction

Diagnosis-Related Groups

Missing Values

Return to Introduction

Hospital-Level Data Elements

Return to Introduction

Longitudinal Hospital Analyses

Return to Introduction

Hospital Volume Estimates

Return to Introduction

Calculating National Estimates

Return to Introduction

Studying Trends

Return to Introduction

Studying Readmissions

Return to Introduction

Variance Calculations

Return to Introduction

Computer Software for Variance Calculations

Return to Introduction

SAMPLING PROCEDURE

The NIS Hospital Universe

Each year, the AHA's Health Forum administers the AHA Annual Survey of Hospitals. The purpose of the survey is to collect utilization, financial, service, and personnel information on each of the nation's hospitals. The survey's overall response rate averages approximately 85 percent each year, which is high for a voluntary survey given its length and the size of the universe (about 6,000 hospitals). For hospitals that do not respond, the AHA imputes items based on prior-year information, so that data are available for all hospitals in the universe.

The hospital universe is defined by all hospitals that were open during any part of the calendar year and were designated as community hospitals in the AHA Annual Survey. For purposes of the NIS, the definition of a community hospital is that used by the AHA: "all nonfederal short-term general and other specialty hospitals, excluding hospital units of institutions." Consequently, Veterans Affairs hospitals and other Federal hospitals are excluded. Beginning with the 1998 redesign, rehabilitation hospitals are excluded. Beginning with the 2012 redesign, long-term acute care hospitals are also excluded.

Long-term acute care hospitals are classified as community hospitals by the AHA if they have an average length-of-stay (ALOS) less than 30 days. However, long-term acute care hospital data was not uniformly available from all States participating in HCUP, and ALOS data from these facilities was over 25 days (unlike other community hospitals with an ALOS of about 4.5 days). Thus, long term acute care facilities were eliminated from the 2012 NIS.

Prior to the 2012 NIS, NIS sample weights were calculated by dividing the number of universe discharges by the number of sampled discharges within each hospital stratum. The number of universe discharges had been estimated using data from the AHA annual hospital survey. The total number of discharges in the universe was estimated by the sum of births and admissions contained in the AHA annual survey for all hospitals in the universe.

Given that HCUP Partners supply more than 95 percent of discharges nationwide, beginning with the 2012 NIS, the universe count of discharges within each stratum is estimated using the actual count of discharges contained in HCUP data. The AHA counts are used only for hospitals in the universe that do not appear in HCUP data coming from the statewide data organizations.

This option was not considered for the previous 1998 redesign because HCUP data included a much smaller percentage of discharges in the United States, and the differences between HCUP counts and AHA counts would tend to adversely affect trends as the mix of HCUP Partners changed from year to year. In 2011, for hospitals in both the AHA and the SID, in 43 of 46 States, the AHA survey data estimated State discharge totals that were between 1 percent and 17 percent higher than the observed SID discharge totals. Overall, the AHA survey estimated about a 4 percent higher count of discharges than the observed SID count.

In the 2012 redesign, a logical corollary of switching from AHA discharge estimates to SID discharge counts was to distinguish unique hospitals using the SID hospital identifiers rather than the AHA hospital identifiers. For most hospitals, the SID hospital identifiers are in one-to-one correspondence with the AHA hospital identifiers. However, about 10 percent of the AHA identifiers correspond to two or more hospitals in the SID that have common ownership within a hospital system. For these "combined" AHA identifiers, the number of estimated discharges and the number of hospital beds in the AHA data reflect the sum of estimated discharges and the sum of beds, respectively, from the constituent hospitals. As a result, these combined hospitals could have been allocated to the wrong bed size stratum in the sample design. Also, the between-hospital variance was combined with the within-hospital variance for these combined hospitals. Therefore, use of the SID hospital identifiers in the 2012 NIS disaggregates the previously combined hospitals in many States, which is likely to improve the classification of hospitals and improve variance estimates.

For more information on how hospitals in the data set were mapped to hospitals as defined by the AHA, refer to the special report, HCUP Hospital Identifiers.7 For a list of all data sources, refer to Table 2 in Appendix I.

Return to Introduction

Stratification Data Elements

Given the increase in the number of contributing HCUP Partner organizations, AHRQ evaluated and revised the sampling and weighting strategy for the 1998 NIS and subsequent data years to best represent the U.S. This included changes to the definitions of the strata data elements, the exclusion of rehabilitation hospitals from the NIS hospital universe, and a change to the calculation of hospital universe discharges for the weights. A full description of this process is available in the special report on Changes in NIS Sampling and Weighting Strategy for 1998, available on the HCUP-US website. (A description of the sampling procedures and definitions of strata data elements used from 1988 through 1997 can be found in the special report: Design of the HCUP Nationwide Inpatient Sample, 1997. This report is also available on the HCUP-US website.)

Again for the 2012 NIS and subsequent data years, AHRQ evaluated and revised the sampling strategy to best represent the U.S. See Table 1 in Appendix I, The National Inpatient Sample (NIS) Design Changes, for a summary of design changes. For a detailed description of the NIS redesign, please see the 2012 NIS Redesign Report available on the HCUP-US website.

Prior to 2012, the NIS sampling strata were defined based on five hospital characteristics contained in the AHA hospital files. Beginning with the 2012 NIS, the only hospital-level stratification factor that changes is census division rather than census region8; and the stratification data elements were defined as follows:

Census Division — New England, Middle Atlantic, East North Central, West North Central, South Atlantic, South Central, Mountain, and Pacific. This is an important stratification data element because practice patterns have been shown to vary substantially by region. For example, lengths of stay tend to be longer in East Coast hospitals than in West Coast hospitals. The NIS States by census division are shown in Figure 2 of Appendix I.

  1. Control — government non-Federal (public), private not-for-profit (voluntary), and private investor-owned (proprietary). Depending on their control, hospitals tend to have different missions and different responses to government regulations and policies. Hospitals are stratified as public, voluntary, and proprietary. When necessary, strata are combined so that a minimum of two hospitals are included in each stratum.

  2. Location — urban or rural. Government payment policies for hospital services often differ according to this designation. Also, rural hospitals are generally smaller and offer fewer services than urban hospitals. Hospitals with a CBSA type of Metropolitan are categorized as urban, while hospitals with a CBSA type of Micropolitan or Rural are designated as rural.

  3. Teaching Status — teaching or non-teaching. The missions of teaching hospitals differ from non-teaching hospitals. In addition, financial considerations differ between these two hospital groups. Currently, the Medicare Diagnosis Related Group (DRG) payments are uniformly higher to teaching hospitals. A hospital is considered to be a teaching hospital if it met any one of the following three criteria: (See Appendix IV for details.)
    • Residency training approval by the Accreditation Council for Graduate Medical Education (ACGME)
    • Membership in the Council of Teaching Hospitals (COTH)
    • A ratio of full-time equivalent interns and residents to beds of .25 or higher

  4. Bed Size — small, medium, and large. Bed size categories were based on the number of hospital beds and were specific to the hospital's region, location, and teaching status, as shown in Table 6 in Appendix I. The bed size cutoff points were chosen so that approximately one-third of the hospitals in each region, location, and teaching status combination would fall within each bed size category (small, medium, or large). Different cutoff points were used for rural, urban non-teaching, and urban teaching hospitals because hospitals in those categories tend to be small, medium, and large, respectively. For example, a medium-sized teaching hospital would be considered a rather large rural hospital. Further, the size distribution is different among regions for each of the urban/teaching categories. For example, teaching hospitals tend to be smaller in the West than they are in the South. Using differing cutoff points in this manner avoids strata containing small numbers of hospitals.

No distinction was made by teaching status among rural hospitals, because rural teaching hospitals were rare. For example, in 2019, rural teaching hospitals comprised less than 5 percent of the total hospital universe. Bed size categories were defined within location and teaching status because they would otherwise have been redundant. Rural hospitals tend to be small; urban non-teaching hospitals tend to be medium-sized; and urban teaching hospitals tend to be large. Yet it was important to recognize gradations of size within these types of hospitals. For example, in serving rural discharges, the role of "large" rural hospitals (particularly rural referral centers) often differs from the role of "small" rural hospitals.

To further ensure geographic representativeness of the sample, implicit stratification data elements included de-identified hospital number, Diagnosis Related Group (DRG) and admission month. The discharges were sorted according to these data elements prior to systematic random sampling.

Return to Introduction

Design Considerations

Prior to 2012, the NIS was a stratified probability sample of hospitals in the frame, with sampling probabilities proportional to the number of U.S. community hospitals in each stratum: sampling probabilities were calculated to select 20 percent of the universe of U.S. community, non-rehabilitation hospitals contained in each stratum. This sample size was determined by AHRQ based on their experience with similar research databases. The overall design objective was to select a sample of hospitals that accurately represented the target universe, which included hospitals outside the frame (i.e., having zero probability of selection). Moreover, this sample was to be geographically dispersed, yet drawn only from data supplied by HCUP Partners.

Starting with the 2012 NIS, a systematic sampling design is used to construct the database. Rather than first drawing a sample of hospitals and then keeping all discharges from that sample, in the 2012 NIS redesign a sample of discharges was drawn from all hospitals in the hospital frame. Both designs selected approximately 20 percent of the target universe of discharges from United States community hospitals, excluding rehabilitation and long-term acute care hospitals.

The new systematic sample is a self-weighted sample design similar to simple random sampling, but it is more efficient. It ensures that the sample is representative of the population on the following critical factors: hospital factors (de-identified hospital number, census division, ownership, urban-rural location, teaching status, number of beds) and patient factors (diagnosis-related group, admission month). Within each stratum all discharges are sorted in the following order on patient-level "control" variables: encrypted hospital ID, DRG, admission month, and a random number.

It should be possible, for example, to estimate DRG-specific average lengths of stay across all U.S. hospitals using weighted average lengths of stay, based on averages or regression coefficients calculated from the NIS. Ideally, relationships among outcomes and their correlates estimated from the NIS should accurately represent all U.S. hospitals. It is advisable to verify your estimates against other data sources, especially for specific patient populations (e.g. organ transplant recipients).

The 2012 NIS Redesign Report assessed the accuracy of NIS estimates and considered alternative stratified sampling allocation schemes. However, systematic sampling design was preferred for several reasons:

Return to Introduction

Overview of the Sampling Procedure

The strata for the 2012 and later NIS systematic sampling design are the same as those for the previous NIS sample design except that the four census regions are replaced by the nine census divisions—New England, Middle Atlantic, East North Central, West North Central, South Atlantic, South Central, Mountain, and Pacific. Within each stratum, dischargers are sorted by re-identified hospital number. Then, within each hospital, discharges are sorted by their DRG and their admission month. This sorting ensures that the NIS sample will be representative on these factors.

Next, within each stratum, a number of discharges proportionate to the number of discharges in the universe are selected systematically from the sorted list. For example, if the sampling frame was equal to the universe and 20 percent of the universe was required, then every fifth discharge would be selected from the sorted list of discharges, beginning with a randomly selected start at discharge number 1, 2, 3, 4, or 5 on the list.

To ensure a self-weighted sample that has 20 percent of the universe within each stratum represented, sampling rates would vary for each stratum, depending on the proportion of the population of discharges covered by the discharges in the sampling frame. Thus, the sampling rate would not always be 20 percent for each stratum. For strata that were missing more discharges, the sampling rate would be higher to ensure that the number of sampled discharges would equal 20 percent of the universe.

Return to Introduction

WEIGHTS

To obtain nationwide estimates, discharge weights were developed to extrapolate NIS sample discharges to the discharge universe. NIS discharge weights are calculated by dividing the number of universe discharges by the number of sampled discharges within each NIS stratum. Historically, the number of universe discharges had been estimated using data from the AHA annual hospital survey. The total number of discharges in the universe was estimated by the sum of births and admissions contained in the AHA annual survey for all hospitals in the universe.

Given that HCUP Partners supply more than 95 percent of discharges nationwide, beginning with the 2012 NIS, the universe count of discharges was estimated within each stratum using the actual count of discharges contained in HCUP data. The only exceptions are for strata with HCUP hospitals that, according to the AHA files, were open for the entire year but contributed less than a full year of data to HCUP. For those hospitals, the number of observed discharges was adjusted by a factor of 12 ÷ M, where M is the number of months for which the hospital contributed discharges to HCUP. For example, when a hospital contributed only six months of discharge data to HCUP, the adjusted number of discharges is double the observed number.

For non-HCUP hospitals in the universe, adjusted AHA discharge estimates were calculated by multiplying the AHA admissions plus births volume by the overall ratio of HCUP discharges to AHA volumes for HCUP hospitals in the census division.

The discharge weights are constant for all discharges within a stratum, where the stratum is defined by hospital characteristics: census division, rural/urban location, bed size, teaching status, and ownership. The previous design provided discharge weights that reflected the universe of discharges in each of the four census regions. The 2012 NIS design provides discharge weights that reflect the universe of discharges in each of the nine census divisions.

Each discharge weight is essentially equal to the number of target universe discharges that each sampled discharge represents in its stratum. Discharge weights to the universe were calculated as follows: Within stratum s, each NIS sample discharge's universe weight was calculated as:

DWs(universe) = DNs(universe) ÷ DNs(sample)

where DWs(universe) was the discharge weight; DNs(universe) represented the number of discharges from community hospitals in the universe within stratum s; and DNs(sample) was the number of discharges selected for the NIS. Thus, each discharge's weight (DISCWT) is equal to the number of universe discharges it represents in stratum s during that year.9 Because 20 percent of the universe discharges in each stratum were sampled, the discharge weights are near five.

Prior to the 2012 NIS redesign, the NIS included weights to project NIS hospitals to the number of hospital in the target universe. However, with the 2012 NIS redesign the hospital weights are discontinued because the NIS is now a sample of discharges from all available HCUP SID community hospitals, excluding rehabilitation and long-term acute care hospitals.

Return to Introduction



Appendix I: Tables and Figures

Table 1: National Inpatient Sample (NIS) Design Changes Beginning in 2012
Feature Previous Design (1998-2011) New 2012 and Later Design
Universe Included long-term acute care hospitals Removed long-term acute care hospitals
Discharge estimates based on AHA admissions plus births Discharge estimates based on SID discharges when available (for about 90 percent of all hospitals); otherwise, based on adjusted AHA counts
Hospitals defined based on AHA IDs Hospitals defined based on State-supplied hospital identifiers for HCUP states
Sample design Sample hospitals and then retain all discharges from each sampled hospital Systematic sample of discharges from all frame hospitals
Stratified by:
  • hospital census region,a
  • ownership
  • urban/rural location,
  • teaching status, and
  • number of beds (bed size categories)
Stratified by:
  • hospital census division,b
  • ownership
  • urban/rural location,
  • teaching status, and
  • number of beds (bed size categories)
Sorted by three-digit hospital ZIP Code within strata before sampling Sorted by hospital and by DRG and admission month within strata before sampling
Sample without self-weighting requires weights for all estimates Self-weighting sample requires weights for estimating totals, but not for means and rates
Data elements Includes State and hospital identifiers and data elements with State-specific coding
  • Drops State identifiers and data elements that were not available uniformly across the States, such as hospital identifiers, secondary payer, and data elements with State-specific coding
  • Drop hospital weights
  • Retain certain high value State-specific data elements (See Appendix B)
  • AGES (AGE) over 89 are aggregated into a single category of 90 years or older in the HCUP nationwide databases starting in data year 2012.

Abbreviations: AHA, American Hospital Association; DRG, diagnosis-related group; ID, identification numbers; SID, State Inpatient Databases
a Census region: Northeast, Midwest, South, West.
b Census division: New England, Middle Atlantic, East North Central, West North Central, South Atlantic, East South Central, West South Central, Mountain, Pacific.

Return to Introduction



Table 2: States Participating in 2019 NIS



State Data Organization
AK Alaska Department of Health and Social Services
AR Arkansas Department of Health
AZ Arizona Department of Health Services
CA California Office of Statewide Health Planning & Development
CO Colorado Hospital Association
CT Connecticut Hospital Association
DC District of Columbia Hospital Association
DE Delaware Division of Public Health
FL Florida Agency for Health Care Administration
GA Georgia Hospital Association
HI Hawaii Laulima Data Alliance
IA Iowa Hospital Association
IL Illinois Department of Public Health
IN Indiana Hospital Association
KS Kansas Hospital Association
KY Kentucky Cabinet for Health and Family Services
LA Louisiana Department of Health
MA Massachusetts Center for Health Information and Analysis
MD Maryland Health Services Cost Review Commission
ME Maine Health Data Organization
MI Michigan Health & Hospital Association
MN Minnesota Hospital Association
MO Missouri Hospital Industry Data Institute
MS Mississippi Department of Health
MT Montana Hospital Association
NC North Carolina Department of Health and Human Services
ND North Dakota (data provided by the Minnesota Hospital Association)
NE Nebraska Hospital Association
NH New Hampshire Department of Health & Human Services
NJ New Jersey Department of Health
NM New Mexico Department of Health
NV Nevada Department of Health & Human Services
NY New York State Department of Health
OH Ohio Hospital Association
OK Oklahoma State Department of Health
OR Oregon Association of Hospitals and Health Systems
PA Pennsylvania Healthcare Cost Containment Council
RI Rhode Island Department of Health
SC South Carolina Revenue and Fiscal Affairs Office
SD South Dakota Association of Healthcare Organizations
TN Tennessee Hospital Association
TX Texas Department of State Health Services
UT Utah Department of Health
VT Vermont Association of Hospitals and Health Systems
VA Virginia Health Information
WA Washington State Department of Health
WI Wisconsin Department of Health Services
WV West Virginia Health Care Authority
WY Wyoming Hospital Association

Return to Introduction



Table 3: Summary of NIS States, Hospitals, and Inpatient Stays, 1988-2019



Year Data Sources Number of States Number of Hospitals Number of Discharges in the NIS, Unweighted Number of Discharges in the NIS, Weighted Number of Discharges in the NIS, Weighted with Trend Weight
1988 CA CO FL IA IL MA NJ WA 8 759 5,265,756 35,171,448 --
1989 AZ CA CO FL IA IL MA NJ PA WA WI 11 882 6,110,064 35,104,645 --
1990 AZ CA CO FL IA IL MA NJ PA WA WI 11 871 6,268,515 35,215,397 --
1991 AZ CA CO FL IA IL MA NJ PA WA WI 11 859 6,156,188 35,036,492 --
1992 AZ CA CO FL IA IL MA NJ PA WA WI 11 856 6,195,744 35,011,385 --
1993 AZ CA CO CT FL IA IL KS MA MD NJ NY OR PA SC WA WI 17 913 6,538,976 34,715,985 33,736,753
1994 AZ CA CO CT FL IA IL KS MA MD NJ NY OR PA SC WA WI 17 904 6,385,011 34,622,203 33,149,768
1995 AZ CA CO CT FL IA IL KS MA MD MO NJ NY OR PA SC TN WA WI 19 938 6,714,935 34,791,998 33,647,121
1996 AZ CA CO CT FL IA IL KS MA MD MO NJ NY OR PA SC TN WA WI 19 906 6,542,069 34,874,386 33,386,097
1997 AZ CA CO CT FL GA HI IA IL KS MA MD MO NJ NY OR PA SC TN UT WA WI 22 1,012 7,148,420 35,408,207 33,232,257
1998 AZ CA CO CT FL GA HI IA IL KS MA MD MO NJ NY OR PA SC TN UT WA WI 22 984 6,827,350 34,874,001 33,923,632
1999 AZ CA CO CT FL GA HI IA IL KS MA MD ME MO NJ NY OR PA SC TN UT VA WA WI 24 984 7,198,929 35,467,673 34,440,994
2000 AZ CA CO CT FL GA HI IA IL KS KY MA MD ME MO NC NJ NY OR PA SC TN TX UT VA WA WI WV 28 994 7,450,992 36,417,565 35,300,425
2001 AZ CA CO CT FL GA HI IA IL KS KY MA MD ME MI MN MO NC NE NJ NY OR PA RI SC TN TX UT VA VT WA WI WV 33 986 7,452,727 37,187,641 36,093,550
2002 CA CO CT FL GA HI IA IL KS KY MA MD ME MI MN MO NC NE NJ NV NY OH OR PA RI SC SD TN TX UT VA VT WA WI WV 35 995 7,853,982 37,804,021 36,523,831
2003 AZ CA CO CT FL GA HI IA IL IN KS KY MA MD MI MN MO NC NE NH NJ NV NY OH OR PA RI SC SD TN TX UT VA VT WA WI WV 37 994 7,977,728 38,220,659 37,074,605
2004 AR AZ CA CO CT FL GA HI IA IL IN KS KY MA MD MI MN MO NC NE NH NJ NV NY OH OR RI SC SD TN TX UT VA VT WA WI WV 37 1,004 8,004,571 38,661,786 37,496,978
2005 AR AZ CA CO CT FL GA HI IA IL IN KS KY MA MD MI MN MO NC NE NH NJ NV NY OH OK OR RI SC SD TN TX UT VT WA WI WV 37 1,054 7,995,048 39,163,834 37,843,039
2006 AR AZ CA CO CT FL GA HI IA IL IN KS KY MA MD MI MN MO NC NE NH NJ NV NY OH OK OR RI SC SD TN TX UT VA VT WA WI WV 38 1,045 8,074,825 39,450,216 38,076,556
2007 AR AZ CA CO CT FL GA HI IA IL IN KS KY MA MD ME MI MN MO NC NE NH NJ NV NY OH OK OR RI SC SD TN TX UT VA VT WA WI WV WY 40 1,044 8,043,415 39,541,948 38,155,908
2008 AR AZ CA CO CT FL GA HI IA IL IN KS KY LA MA MD ME MI MN MO NC NE NH NJ NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 42 1,056 8,158,381 39,885,120 38,210,889
2009 AR AZ CA CO CT FL GA HI IA IL IN KS KY LA MA MD ME MI MN MO MT NC NE NH NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 44 1,050 7,810,762 39,434,956 37,734,584
2010 AK AR AZ CA CO CT FL GA HI IA IL IN KS KY LA MA MD ME MI MN MO MS MT NC NE NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 45 1,051 7,800,441 39,008,298 37,352,013
2011 AK AR AZ CA CO CT FL GA HI IA IL IN KS KY LA MA MD ME MI MN MO MS MT NC ND NE NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 46 1,049 8,023,590 38,590,733 36,962,415
2012 AK AR AZ CA CO CT FL GA HI IA IL IN KS KY LA MA MD MI MN MO MT NC ND NE NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 44 4,378 7,296,968 36,484,846  
2013 AR AZ CA CO CT DC FL GA HI IA IL IN KS KY LA MA MD MI MN MO MT NC ND NE NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 44 4,363 7,119,563 35,597,792  
2014 AR AZ CA CO CT DC FL GA HI IA IL IN KS KY LA MA MD ME MI MN MO MT NC ND NE NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 45 4,411 7,071,762 35,358,818  
2015 AK AR AZ CA CO CT DC FL GA HI IA IL IN KS KY LA MA MD ME MI MN MO MS MT NC ND NE NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 47 4,573 7,153,989 35,769,942  
2016 AK AR AZ CA CO CT DC FL GA HI IA IL IN KS KY LA MA MD ME MI MN MO MS MT NC ND NE NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 47 4,575 7,135,090 35,675,421  
2017 AK AR AZ CA CO CT DC DE FL GA HI IA IL IN KS KY LA MA MD ME MI MN MO MS MT NC ND NE NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 48 4,584 7,159,694 35,798,453  
2018 AK AR AZ CA CO CT DC DE FL GA HI IA IL IN KS KY LA MA MD ME MI MN MO MS MT NC ND NE NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 48 4,550 7,105,498 35,527,481  
2019 AK AR AZ CA CO CT DC DE FL GA HI IA IL IN KS KY LA MA MD ME MI MN MO MS MT NC ND NE NH NJ NM NV NY OH OK OR PA RI SC SD TN TX UT VA VT WA WI WV WY 49 4,568 7,083,805 35,419,023  

Return to Introduction



Table 4: Number of Hospitals and Discharges in 2019 Universe, Frame, and NIS, by Census Division

Number of Hospitals and Discharges in 2019 Universe, Frame, and NIS, by Census Division
  Universe Frame NIS
Census Region Census Division Hospitals Discharges Hospitals Discharges Hospitals Discharges Weighted Discharges
Northeast New England 180 1,647,139 177 1,638,649 176 329,427 1,647,139
Northeast Middle Atlantic 437 4,760,268 426 4,661,922 426 952,052 4,760,268
Northeast Subtotal 617 6,407,407 603 6,300,571 602 1,281,479 6,407,407
Midwest East North Central 749 5,349,401 738 5,331,167 737 1,069,880 5,349,401
Midwest West North Central 669 2,491,091 626 2,465,925 625 498,220 2,491,091
Midwest Subtotal 1,418 7,840,492 1,364 7,797,092 1,362 1,568,100 7,840,492
South South Atlantic 710 7,389,157 703 7,373,652 703 1,477,831 7,389,157
South East South Central 392 2,419,527 293 1,726,445 293 483,907 2,419,527
South West South Central 787 4,267,800 745 4,236,552 743 853,560 4,267,800
South Subtotal 1,889 14,076,484 1,741 13,336,649 1,739 2,815,298 14,076,484
West Mountain 403 2,271,313 341 2,107,737 340 454,262 2,271,313
West Pacific 530 4,823,327 525 4,799,619 525 964,666 4,823,327
West Subtotal 933 7,094,640 866 6,907,356 865 1,418,928 7,094,640
Total Total 4,857 35,419,023 4,574 34,341,668 4,568 7,083,805 35,419,023

Return to Introduction



Table 5: NIS Related Reports and Database Documentation Available on HCUP-US



Description of the NIS Database
  • NIS Overview
    • HCUP Partners in the NIS
  • Introduction to the NIS, 2019 - this document
  • NIS Related Reports
    Links to HCUP-US page with various NIS related reports such as the following:
    • Design of the Nationwide Inpatient Sample for 1988 to 2005.
    • Changes in NIS Sampling and Weighting Strategy for 1998
    • Updated NIS Variance Reports
    • NIS Trends Report
    • Missing Data Methods Report
    • 2012 NIS Redesign Report
    • NIS Comparison Reports (available for years in which the NIS sample changed)
    • HCUP Data Quality Reports for 1988-2019
    • HCUP E-Code Evaluation Report
Restrictions on the Use
  • Data Use Agreement Training
  • Data Use Agreement for the NIS
  • Requirements for Publishing with HCUP data
File Specifications and Load Programs
  • NIS File Specifications
  • Nationwide SAS Load Programs
  • Nationwide SPSS Load Programs
  • Nationwide Stata Load Programs
Data Elements
  • NIS Description of Data Elements - details uniform coding and State-specific idiosyncrasies
  • NIS Summary Statistics - lists means and frequencies on nearly all data elements
  • Prior to Data Year 2012
    • Availability of AHA Hospital Identifiers
    • Why the NIS should not be used to make State-level estimates
Additional Resources for Data Elements
  • NIS Severity Measures - provides detailed documentation on the different types of measures
  • HCUP Quality Control Procedures - describes procedures used to assess data quality
  • HCUP Coding Practices - describes how HCUP data elements are coded
  • HCUP Hospital Identifiers - explains data elements that characterize individual hospitals
ICD-10-CM/PCS Data Included in the NIS Starting With 2015
  • NIS Changes Beginning Data Year 2016
  • Caution: 2015 NIS includes ICD-9-CM and ICD-10-CM/PCS
    • 2015 NIS Revised File Structure and New Data Elements
  • Additional ICD-10-CM/PCS Resources
  • HCUP Software Tools Tutorial
Information on the Redesign of the NIS in 2012
  • 2012 NIS Redesign Report
  • Trend Weights for the 1993-2011 NIS for Consistent Estimates with the Redesigned NIS
Known Data Issues
  • Why the NIS should not be used to make State-level estimates
  • Information on corrections to the NIS data sets
NIS Supplemental Files
  • Cost-to-Charge Ratio files
  • Hospital Market Structure (HMS) files
  • 1993-2011 NIS Supplemental Discharge-Level Files
  • NIS Ownership Files
HCUP Tools: Labels and Formats
  • Overview of Clinical Classifications Software (CCS), a categorization scheme that groups ICD-9-CM diagnosis and procedure codes into mutually exclusive categories
  • Format Programs
    • Labels file for multiple versions of Diagnosis Related Groups (DRGs) and Major Diagnostic Categories (MDCs)
    • NIS SAS format library program to create value labels
    • HCUP Diagnosis and Procedure Groups Formats Program - formats to label DX_PR_Groups including CCS data elements
    • NIS ICD-9-CM formats to label ICD-9-CM diagnoses and procedures
    • NIS ICD-10-CM formats to label ICD-10-CM diagnoses and procedures
    • NIS Severity formats to label severity data elements
Obtaining HCUP Data
  • Purchase HCUP data from the HCUP Central Distributor


Return to Introduction

Table 6: Hospital Size Categories (in Number of Beds), by Region

Location and Teaching Status Hospital Bed Size
Small Medium Large
NORTHEAST
Rural 1 - 49 50 - 99 100+
Urban, non-teaching 1 - 124 125 - 199 200+
Urban, teaching 1 - 249 250 - 424 425+
MIDWEST
Rural 1 - 29 30 - 49 50+
Urban, non-teaching 1 - 74 75 - 174 175+
Urban, teaching 1 - 249 250 - 374 375+
SOUTH
Rural 1 - 39 40 - 74 75+
Urban, non-teaching 1 - 99 100 - 199 200+
Urban, teaching 1 - 249 250 - 449 450+
WEST
Rural 1 - 24 25 - 44 45+
Urban, non-teaching 1 - 99 100 - 174 175+
Urban, teaching 1 - 199 200 - 324 325+

Return to Introduction



Figure 1: Percentage of U.S. Population Covered in the 2019 NIS by Census Division and Region, Calculated using the Estimated U.S. Population on July 1, 2019

text version

Figure 1 is a bar chart illustrating the percentage of U.S. Population Covered in the 2019 NIS by Census Division, Population of NIS (millions), U.S. Population (millions).

Source: Table 1. Annual Estimates of the Population for the United States, Regions, States, and Puerto Rico: April 1, 2010 to July 1, 2020 (NST-EST2020-01). Source: U.S. Census Bureau, Population Division. Release Date: December 2020.

Return to Introduction



Figure 2: NIS States, by Census Division

text version

Figure 2 displays a U.S. map illustrating 2019 NIS States by Census Division and Census Region, as described in text below the figure.

All States, by U.S Census Bureau Region and Census Division

Notes: New Hampshire did not provide data in time for the 2010-2018 NIS.
Mississippi did not provide data in time for the 2012-2014 NIS.
Alaska did not provide data in time for the 2013-2014 NIS.
States and areas in italics do not participate in HCUP.
a Prior to June 1984, the Midwest Region was designated as the North Central Region.
Source: U.S. Census Bureau. Census Bureau Regions and Divisions with State FIPS Codes. www2.census.gov/geo/pdfs/maps-data/maps/reference/us_regdiv.pdf. Accessed August 3, 2020.

Return to Introduction



Figure 3: Number of Discharges (in Thousands, Unweighted) in 2019 NIS by Census Division and Census Region

text version

Figure 3 is a bar chart illustrating the number of discharges (in Thousands, Unweighted) in the 2019 NIS by Census Division and Census Region.

Return to Introduction



APPENDIX II: STATE-SPECIFIC RESTRICTIONS

The table below enumerates the types of restrictions applied to the National Inpatient Sample. Restrictions include the following types:



Confidentiality of Records — Restricted Release of Age in Years
  • Ages (AGE) over 89 are aggregated into a single category of 90 years or older in the HCUP nationwide databases starting in data year 2012.
  • At least one Partner required ages in years (AGE) to be set to the midpoints of age ranges.


Missing Discharges
  • At least one Partner prohibits the release of discharge records for patients with HIV diagnoses.
  • At least one Partner prohibits the release of Alternate Level of Care (SNF / Swing Bed Skilled) discharges.
  • At least one Partner prohibits the release of abortion discharges.
  • At least one Partner prohibits the release of medical misadventure or adverse reaction cause codes.

Return to Introduction



APPENDIX III: DATA ELEMENTS

Table 1: Data Elements in the 2019 NIS Inpatient Core Files

For prior years, refer to the NIS Description of Data Elements page on HCUP-US website or to previous versions of the NIS Introduction.

Type of Data Element HCUP Name Coding Notes
Admission information
Admission day AWEEKEND Admission on weekend: (0) admission on Monday-Friday, (1) admission on Saturday-Sunday
Admission month AMONTH Admission month coded from (1) January to (12) December
Transferred into hospital TRAN_IN Transfer In Indicator: (0) not a transfer, (1) transferred in from a different acute care hospital [ATYPE NE 4 & (ASOURCE=2 or POO=4)], (2) transferred in from another type of health facility [ATYPE NE 4 & (ASOURCE=3 or POO=5, 6, D, E, F)]
Indicator of emergency department service HCUP_ED Indicator that discharge record includes evidence of emergency department (ED) services: (0) Record does not meet any HCUP Emergency Department criteria, (1) Emergency Department revenue code on record, (2) Positive Emergency Department charge (when revenue center codes are not available), (3) Emergency Department CPT procedure code on record, (4) Admission source of ED, (5) State-defined ED record; no ED charges available
Admission type ELECTIVE Indicates elective admission: (1) elective, (0) non-elective admission
Patient demographic and location information
Age at admission AGE Age in years coded 0-124 years
AGE_NEONATE Neonatal age (first 28 days after birth) indicator: (0) non-neonatal age (1) neonatal age
Sex of patient FEMALE Indicates gender for NIS beginning in 1998: (0) male, (1) female
Race of patient RACE Race, uniform coding: (1) white, (2) black, (3) Hispanic, (4) Asian or Pacific Islander, (5) Native American, (6) other (For 2019, RACE contains missing values on over 3 percent of the records.)
Location of patient's residence PL_NCHS Patient Location: NCHS Urban-Rural Code. This is a six-category urban-rural classification scheme for U.S. counties: (1) "Central" counties of metro areas of >=1 million population, (2) "Fringe" counties of metro areas of >=1 million population, (3) Counties in metro areas of 250,000-999,999 population, (4) Counties in metro areas of 50,000-249,999 population, (5) Micropolitan counties, (6) Not metropolitan or micropolitan counties
Median household income for patient's ZIP Code ZIPINC_QRTL Median household income quartiles for patient's ZIP Code. For 2019, the median income quartiles are defined as: (1) $1 - $45,999; (2) $46,000 - $58,999; (3) $59,000 - 78,999; and (4) $79,000 or more.
Payer information
Primary expected payer PAY1 Expected primary payer, uniform: (1) Medicare, (2) Medicaid, (3) private including HMO, (4) self-pay, (5) no charge, (6) other
Diagnosis and procedure information
ICD-10-CM diagnoses I10_DX1 - I10_DX40 ICD-10-CM diagnoses, principal and secondary, with external cause of morbidity codes at the end of the array
I10_NDX Number of ICD-10-CM diagnoses coded on the record
ICD-10-PCS procedures I10_PR1 - I10_PR25 ICD-10-PCS procedures, principal and secondary
I10_NPR Number of ICD-10-PCS procedures coded on the record
PRDAY1 Number of days from admission to principal procedure
PRDAY2 - PRDAY25 Number of days from admission to secondary procedures
Indicators I10_BIRTH ICD-10-CM birth indicator
I10_DELIVERY ICD-10-CM delivery indicator
I10_INJURY Injury ICD-10-CM diagnosis reported on record
I10_MULTINJURY Multiple ICD-10-CM injuries reported on record
I10_SERVICELINE ICD-10-CM/PCS hospital service line indicator
PCLASS_ORPROC ICD-10-PCS major operating room procedure indicator
DRG information
Diagnosis Related Group (DRG) DRG DRG in use on discharge date (based on ICD-10-CM/PCS codes)
DRG_NoPOA DRG in use on discharge date, calculated without Present On Admission (POA) indicators (based on ICD-10-CM/PCS codes)
DRGVER Grouper version in use on discharge date
Major Diagnostic Category (MDC) MDC MDC in use on discharge date (based on ICD-10-CM/PCS codes)
MDC_NoPOA MDC in use on discharge date, calculated without Present on Admission (POA) indicators (based on ICD-10-CM/PCS codes)
Resource use information
Total charges TOTCHG Total charges, edited
Length of stay LOS Length of stay, edited
Discharge information
Discharge quarter DQTR Coded: (1) First quarter, Jan - Mar, (2) Second quarter, Apr - Jun, (3) Third quarter, Jul - Sep, (4) Fourth quarter, Oct - Dec
Discharge year YEAR Calendar year
Disposition of patient (discharge status) DIED Indicates in-hospital death: (0) did not die during hospitalization, (1) died during hospitalization
DISPUNIFORM Disposition of patient, uniform coding used beginning in 1998: (1) routine, (2) transfer to short-term hospital, (5) other transfers, including skilled nursing facility, intermediate care, and another type of facility, (6) home healthcare, (7) against medical advice, (20) died in hospital, (99) discharged alive, destination unknown
TRAN_OUT Transfer Out Indicator: (0) not a transfer, (1) transferred out to a different acute care hospital, (2) transferred out to another type of health facility
Weights (to calculate national estimates)
Discharge weights DISCWT Discharge weight on Core File and Hospital File for NIS beginning in 1998.
Hospital information
Hospital identifiers (encrypted) HOSP_NIS NIS hospital number (links to Hospital File; does not link to previous years)
Hospital location HOSP_DIVISION Census Division of hospital (STRATA): (1) New England, (2) Middle Atlantic, (3) East North Central, (4) West North Central, (5) South Atlantic, (6) East South Central, (7) West South Central, (8) Mountain, (9) Pacific
Hospital stratifier NIS_STRATUM Stratum used to sample hospitals, based on geographic region, control, location/teaching status, and bed size. Stratum information is also contained in the Hospital File.
Linkage Data Element
Record identifier, synthetic KEY_NIS Unique record number for file beginning in 2012 links the Core File to other discharge-level NIS files.


Return to Introduction

Table 2: Data Elements in the 2019 NIS Hospital Files

For prior years, refer to the NIS Description of Data Elements page on the HCUP-US website or to previous versions of the NIS Introduction.

Type of Data Element HCUP Name Coding Notes
Discharge counts N_DISC_U Number of universe discharges in the stratum
S_DISC_U Number of sampled discharges in the sampling stratum (NIS_STRATUM or STRATUM)
TOTAL_DISC Total number of discharges from this hospital in the NIS
Discharge weights DISCWT Discharge weight used in the NIS beginning in 1998.
Discharge Year YEAR Discharge year
N_HOSP_U Number of universe hospitals in the stratum
S_HOSP_U Number of sampled hospitals in the stratum (NIS_STRATUM or STRATUM)
Hospital identifiers HOSP_NIS NIS hospital number (links to Hospital File; does not link to previous years)
Hospital characteristics HOSP_BEDSIZE Bed size of hospital (STRATA): (1) small, (2) medium, (3) large
H_CONTRL Control/ownership of hospital: (1) government, nonfederal, (2) private, non-profit, (3) private, investor-own
HOSP_LOCTEACH Location/teaching status of hospital (STRATA): (1) rural, (2) urban non-teaching, (3) urban teaching
HOSP_REGION Region of hospital: (1) Northeast, (2) Midwest, (3) South, (4) West
HOSP_DIVISION Census Division of hospital (STRATA): (1) New England, (2) Middle Atlantic, (3) East North Central, (4) West North Central, (5) South Atlantic, (6) East South Central, (7) West South Central, (8) Mountain, (9) Pacific
NIS_STRATUM Stratum used to sample hospitals beginning in 1998; includes geographic region, control, location/teaching status, and bed size

Return to Introduction



Table 3: Data Elements in the 2019 NIS Disease Severity Measures Files

For prior years, refer to the refer to the NIS Description of Data Elements page on the HCUP-US website or to previous versions of the NIS Introduction.

Type of Data Element HCUP Name Coding Notes
All Patient Refined DRG (3M) APRDRG All Patient Refined DRG
APRDRG_Risk_Mortality Risk of Mortality Subclass: (0) No class specified, (1) Minor likelihood of dying, (2) Moderate likelihood of dying, (3) Major likelihood of dying, (4) Extreme likelihood of dying
APRDRG_Severity Severity of Illness Subclass: (0) No class specified, (1) Minor loss of function (includes cases with no comorbidity or complications), (2) Moderate loss of function, (3) Major loss of function, (4) Extreme loss of function
Linkage Data Elements HOSP_NIS NIS hospital number (links to Hospital File; does not link to previous years)
KEY_NIS Unique record number for file beginning in 2012

Return to Introduction



Table 4: Data Elements in the 2019 NIS Diagnosis and Procedure Groups Files

The Diagnosis and Procedure Groups file is available from 2005 to 2015; and is available again beginning with 2018 data, when data elements derived from the Clinical Classifications Software Refined (CCSR) for ICD-10-CM diagnoses are added. Beginning with data year 2019, data elements derived from the Elixhauser Comorbidity Software Refined for ICD-10-CM, the CCSR for ICD-10-PCS procedures, and Procedure Classes Refined for ICD-10-CM are also available in this file. This file is not available from 2016-2017 because the ICD-10-CM/PCS versions of the AHRQ tools were still under development.

For prior years, refer to the NIS Description of Data Elements page on the HCUP-US website or to previous versions of the NIS Introduction.

Type of Data Element HCUP Name Coding Notes
Comorbidity Measure Refined (CMR) CMR_aaab Comorbidity measures (aaa) identified by the AHRQ Elixhauser Comorbidity Software Refined for ICD-10-CM diagnosis codes
CMR_VERSION Version of the Elixhauser Comorbidity Measure Refined for ICD-10-CM
Clinical Classifications Software Refined (CCSR) Category DXCCSR_aaannn* Indication that at least one ICD-10-CM diagnosis on the record is included in CCSR aaannn
DXCCSR_DEFAULT_DX1 Default Clinical Classifications Software Refined (CCSR) for principal diagnosis
DXCCSR_VERSION Version of CCSR for ICD-10-CM diagnoses
PRCCSR_aaannnd Indication that at least one ICD-10-PCS procedure code on the record is included in CCSR aaannn
PRCCSR_VERSION Version of the CCSR for ICD-10-PCS procedures
Procedure Classes Refined PCLASSne Procedure Classes Refined for ICD-10-PCS procedures
PCLASS_VERSION Version of the Procedure Classes Refined for ICD-10-PCS procedures
Linkage Data Elements HOSP_NIS NIS hospital number (links to Hospital Weights file; does not link to previous years)
KEY_NIS Unique record number for file beginning in 2012
Abbreviations: AHRQ, Agency for Healthcare Research and Quality; CCSR, Clinical Classifications Software Refined; ICD-9-CM, International Classification of Diseases, Ninth Revision, Clinical Modification; ICD-10-CM/PCS, International Classification of Diseases, Tenth Revision, Clinical Modification/Procedure Coding System; NIS, National Inpatient Sample.
b Where aaa denotes the specific comorbidity measure.
c Where aaa denotes the body system and nnn denotes the CCSR number within the body system.
d Where aaa denotes the clinical domain and nnn denotes the CCSR number within the clinical domain.
e PCLASSn was also available on the NIS through quarter 3 of data year 2015 and was specific to the coding of ICD-9-CM procedures.

Return to Introduction



APPENDIX IV: TEACHING HOSPITAL INDICATOR ASSIGNMENT

The following data elements from the American Hospital Association Annual Survey Database (Health Forum, LLC © 2020) were used to assign the NIS Teaching Hospital Indicator:

AHA Data Element Name = Description [HCUP Data Element Name].

BDH = Number of short-term hospital beds [B001H].
BDTOT = Number of total facility beds [B001].
FTRES = Number of full-time employees: interns & residents (medical & dental) [E125].
PTRES = Number of part-time employees: interns & residents (medical & dental) [E225].
MAPP8 = Council of Teaching Hospitals (COTH) indicator [A101].
MAPP3 = Residency training approval by the Accreditation Council for Graduate Medical Education (ACGME) [A102].

Beginning with the 1998 NIS, we used the following SAS code was used to assign the teaching hospital status indicator, HOSP_TEACH:

/*******************************************************/
/* FIRST ESTABLISH SHORT-TERM BEDS DEFINITION */
/*******************************************************/
IF BDH NE . THEN BEDTEMP = BDH ;      /* SHORT TERM BEDS */
ELSE IF BDH =. THEN BEDTEMP = BDTOT ; /* TOTAL BEDS PROXY */
/*******************************************************/
/* ESTABLISH IRB NEEDED FOR TEACHING STATUS */
/* BASED ON F-T P-T RESIDENT INTERN STATUS */
/*******************************************************/
IRB = (FTRES + .5*PTRES) / BEDTEMP ;
/*******************************************************/
/* CREATE TEACHING STATUS DATA ELEMENT */
/*******************************************************/
IF (MAPP8 EQ 1) OR (MAPP3 EQ 1) THEN HOSP_TEACH = 1 ; 
ELSE IF (IRB GE 0.25) THEN HOSP_TEACH = 1 ;
ELSE HOSP_TEACH = 0 ;

Return to Introduction



1 Kaiser Family Foundation Medicare Advantage www.kff.org/medicare/fact-sheet/medicare-advantage/ Exit Disclaimer (Accessed 8/27/2017).

2 See the AHA "community hospital designation" at www.ahadataviewer.com/glossary.Exit Disclaimer

3 ICD-9-CM: International Classification of Diseases, Ninth Revision, Clinical Modification; ICD-10-CM/PCS: International Classification of Diseases, Tenth Revision, Clinical Modification/Procedure Coding System

4 See, for example, van Buuren, S. (2012). Flexible Imputation of Missing Data. CRC Press, Boca Raton, FL.

5 Prior to 1998, the discharge weight was named DISCWT_U. For 2000 only, use DISCWT to create national estimates for all analyses except those that involve total charges; and use DISCWTCHARGE to create national estimates of total charges.

6 Carlson BL, Johnson AE, Cohen SB. "An Evaluation of the Use of Personal Computers for Variance Estimation with Complex Survey Data." Journal of Official Statistics, vol. 9, no. 4, 1993: 795-814.

7 As of August 2019, this report had not been updated for the new NIS design; however, the methods described are still valid.

8 However, researchers can still make estimates for census regions by aggregating census divisions.

9 Although discharge characteristics (DRG and admission month) are implicit stratifiers for sampling, they do not play a role in weighting.

Return to Introduction


Internet Citation: 2019 Introduction to the NIS. Healthcare Cost and Utilization Project (HCUP). September 2021. Agency for Healthcare Research and Quality, Rockville, MD. www.hcup-us.ahrq.gov/db/nation/nis/NIS_Introduction_2019.jsp.
Are you having problems viewing or printing pages on this website?
If you have comments, suggestions, and/or questions, please contact hcup@ahrq.gov.
Privacy Notice, Viewers & Players
Last modified 9/13/21