京公网安备11010802038645号京ICP备20022436号-3京EDI证京B2-20220639区块链京网信备 1101082276223860002X号以下为卖家选择提供的数据验证报告：
数据描述
2010 New York State Hospital Inpatient Discharge Data
Detailed Characteristics, Diagnoses, Treatments and Payments
By Health Data New York [source]
About this dataset
> The Statewide Planning and Research Cooperative System (SPARCS) Inpatient De-identified dataset is a wealth of information, containing discharge level detail on various aspects of hospital inpatient discharges in New York State during the year 2010. From patient characteristics such as age group, gender, race and ethnicity to diagnoses, treatments, services and charges - all data elements excluding those consideredidentifiable have been made available within this dataset. This data does not contain any protected health information (PHI) under the Health Insurance Portability and Accountability Act (HIPAA). Understanding the plethora of details in this data can give individuals insights into many varying aspects related to hospital care. Before using or referencing any data from this dataset it is important to read and understand the Terms of Service which can be found at [link]. Dive into understanding more about what goes on behind closed doors at hospitals with the SPARCS Inpatient De-identified Dataset!
More Datasets
> For more datasets, click here.
Featured Notebooks
> - 🚨 Your notebook can be here! 🚨!
How to use the dataset
> > This guide is here to provide you with information on how to use this dataset efficiently and effectively. Here are some useful tips: > > - Familiarize Yourself With The Data: Before diving into the data itself it is important to understand what it is you will be working with. Take time to read through the columns that are included in the dataset as well as any other relevant documentation associated with this data so that you know exactly what it is you are looking at. > - Clean and Process The Data: When working with raw datasets such as this one it is important to ensure that all of the data provided has been properly cleaned and structured before being used for further analysis or machine learning models. Taking contamination for example; if not correctly diagnosed then these can affect your results later down the line when drawing conclusions from your analysis results. Additionally take care when handling missing values - weighing usage / exclusion of certain values and where applicable looking for patterns which may suggest underlying reasons leading up to them being absent from certain records etc... > - Explore Your Hypothesis/Goals Further: After understanding more about what this data has got behind offer explore any potential hypothesis/goals further by analysing different correlations between various factors across different dimensions (by taking various columns into consideration). Visualisation tools such s Tableau can be used here - however take great care when doing so; visualisations too easily dictate terms leaving a bias sometimes without particularly realising or consciously intending so when carrying out an analysis on a large dataset (which isn’t necessarily bad but something which needs close attention). > > > > 4 Lastly Utilise Actionable Insights Gathered From Your Findings: Once your initial exploration phase has been completed utilize any insights gathered within a productive manner - share your findings & collaborate closely with key stakeholders where applicable presenting any actionable insights gained from your analysis making use potential optimization strategies & aiming towards greater understanding of issues / opportunities affecting business practices
Research Ideas
> - Identifying health disparities in hospital inpatient discharges across New York State – This dataset can be used to understand the regional variations between communities across NY and diagnose which areas need more healthcare coverage for certain diagnosis codes or procedure codes. > - Knowing patient needs ahead of time based on demographics, diagnosis, and procedures – With this dataset, health professionals will be able to get an idea of what kind of treatments most patients look for when they come down with a particular illness or injury. This will allow them to better prepare the necessary equipment, medicine and resources needed beforehand so that they don't have to search while the patient is already at their facility waiting for treatment. > - Improving cost efficiency by looking at correlations between different payment sources – With this dataset, hospitals could identify any patterns or correlations between different payment sources (such as Medicaid and private insurance) that could be used toward improving cost efficiency during inpatient visits by optimizing resource allocation according to source of payments provided from patients' end
Acknowledgements
> If you use this dataset in your research, please credit the original authors. > Data Source > >
License
> > > See the dataset description for more information.
Columns
File: hospital-inpatient-discharges-sparcs-de-identified-2010-1.csv
| Column name | Description |
|---|---|
| Health Service Area | Geographic region of the hospital. (String) |
| Hospital County | County in which the hospital is located. (String) |
| Operating Certificate Number | Unique identifier for hospitals. (Integer) |
| Facility Name | Name of the hospital. (String) |
| Age Group | Age group of the patient. (String) |
| Zip Code - 3 digits | First three digits of the patient's zip code. (Integer) |
| **Zip Code ** | First three digits of the patient's zip code. (Integer) |
| Gender | Gender of the patient. (String) |
| Race | Race of the patient. (String) |
| Ethnicity | Ethnicity of the patient. (String) |
| Length of Stay | Length of stay for the patient. (Integer) |
| Type of Admission | Type of admission for the patient. (String) |
| Patient Disposition | Disposition of the patient. (String) |
| Discharge Year | Year of the patient's discharge. (Integer) |
| CCS Diagnosis Code | Clinical Classification Software (CCS) diagnosis code for the patient. (Integer) |
| CCS Diagnosis Description | CCS Diagnosis Description. (String) |
| CCS Procedure Code | CCS procedure code for the patient. (Integer) |
| CCS Procedure Description | CCS Procedure Description. (String) |
| APR DRG Code | All Patient Refined Diagnosis Related Group APR DRG Code. (Integer) |
| APR DRG Description | APR DRG Description. (String) |
| APR MDC Code | All Patient Refined Major Diagnostic Category APR MDC Code. (Integer) |
| APR MDC Description | APR MDC Description. (String) |
| APR Severity of Illness Code | APR Severity of Illness Code. (Integer) |
| APR Severity of Illness Description | APR Severity of Illness Description. (String) |
| APR Risk of Mortality | APR Risk of Mortality. (Integer) |
| APR Medical Surgical Description | APR Medical Surgical Description. (String) |
| Source of Payment 1 | Source of Payment 1. (String) |
| Source of Payment 2 | Source of Payment 2 |
Acknowledgements
> If you use this dataset in your research, please credit the original authors. > If you use this dataset in your research, please credit Health Data New York.
New York State Hospital Inpatient Discharge
983.53MB
申请报告