New York State Hospital Inpatient Discharges For 2020

2020 data from the Statewide Planning and Research Cooperative System (SPARCS) provides de-identified inpatient discharge records. It includes patient characteristics, diagnoses, procedures, and financial details like Total Charges and Total Costs. The data is published by health.data.ny.gov.

Use Cases

• Analyze the relationship between APR Severity of Illness Code and Total Costs to model hospital expenditure drivers.
• Predict Patient Disposition (e.g., routine discharge) using features like Age Group, APR DRG Code, and CCSR Diagnosis Code.
• Investigate disparities in Hospital Service Area or Race for specific CCSR Procedure Description categories.
• Assess the correlation between Payment Typology categories and metrics like Total Charges or Length of Stay (if inferred).

Strengths

• Contains over 30 specific columns detailing clinical and financial aspects of care.
• Data is de-identified to HIPAA standards, removing protected health information for research use.

Limitations

• Limited to a single year (2020), restricting longitudinal analysis.
• Geographic scope is confined to New York State hospitals, limiting generalizability.
• Specific row count and sample size are unknown, affecting statistical power assessment.

Provenance

Source

health.data.ny.gov via the Statewide Planning and Research Cooperative System (SPARCS).

Collection Method

Administrative discharge data collected from hospitals.

Time Range

2020

Freshness

Data is from 2020, with metadata updated in April 2025.

Geography

New York State, United States.