This dataset contains the statewide number and (unadjusted) rate for all-cause, unplanned, 30-day inpatient readmissions in California hospitals. Data are categorized by age, sex, race/ethnicity, expected payer and county.

In 2019, the 30-day acute-care hospital readmission rate was around ** percent for breast cancer in the United States. This statistic illustrates rates of 30-day acute-care hospital readmission in the United States in 2019, by disease.

Dataset Description: Healthcare Readmission Prediction

This dataset is designed for predicting patient readmissions within 30 days of discharge. It includes synthetic patient records with a variety of medical features such as age, diagnosis, number of procedures, and discharge destination. The goal is to develop machine learning models that can predict whether a patient will be readmitted within 30 days, which can help hospitals improve patient care and reduce costs.

Files:

train.csv - This file contains the training data with a target label (readmitted) indicating whether a patient was readmitted within 30 days.

test.csv - This file contains the test data, which omits the target variable. The task is to predict whether each patient in this dataset will be readmitted.

sample_submission.csv - This file shows the expected format for your submission, with two columns: Patient_ID and readmitted.

The Healthcare Cost and Utilization Project (HCUP) Nationwide Readmissions Database (NRD) is a unique and powerful database designed to support various types of analyses of national readmission rates for all payers and the uninsured. The NRD includes discharges for patients with and without repeat hospital visits in a year and those who have died in the hospital. Repeat stays may or may not be related. The criteria to determine the relationship between hospital admissions is left to the analyst using the NRD. This database addresses a large gap in health care data - the lack of nationally representative information on hospital readmissions for all ages. Outcomes of interest include national readmission rates, reasons for returning to the hospital for care, and the hospital costs for discharges with and without readmissions. Unweighted, the NRD contains data from approximately 18 million discharges each year. Weighted, it estimates roughly 35 million discharges. Developed through a Federal-State-Industry partnership sponsored by the Agency for Healthcare Research and Quality, HCUP data inform decision making at the national, State, and community levels. The NRD is drawn from HCUP State Inpatient Databases (SID) containing verified patient linkage numbers that can be used to track a person across hospitals within a State, while adhering to strict privacy guidelines. The NRD is not designed to support regional, State-, or hospital-specific readmission analyses. The NRD contains more than 100 clinical and non-clinical data elements provided in a hospital discharge abstract. Data elements include but are not limited to: diagnoses, procedures, patient demographics (e.g., sex, age), expected source of payer, regardless of expected payer, including but not limited to Medicare, Medicaid, private insurance, self-pay, or those billed as ‘no charge, discharge month, quarter, and year, total charges, length of stay, and data elements essential to readmission analyses. The NIS excludes data elements that could directly or indirectly identify individuals. Restricted access data files are available with a data use agreement and brief online security training.

Percentage of emergency admissions to any hospital in England occurring within 30 days of the last, previous discharge from hospital after admission: indirectly standardised by age, sex, method of admission and diagnosis/procedure. The indicator is broken down into the following demographic groups for reporting: ● All years and female only, male only and both male and female (persons). ● <16 years and female only, male only and both male and female (persons). ● 16+ years and female only, male only and both male and female (persons) ● 16-74 years and female only, male only and both male and female (persons) ● 75+ years and female only, male only and both male and female (persons) Results for each of these groups are also split by the following geographical and demographic breakdowns: ● Local authority of residence. ● Region. ● Area classification. ● NHS and private providers. ● NHS England regions. ● Deprivation (Index of Multiple Deprivation (IMD) Quintiles, 2019). ● Sustainability and Transformation Partnerships (STP) & Integrated Care Boards (ICB) from 2016/17. ● Clinical Commissioning Groups (CCG) & sub-Integrated Care Boards (sub-ICB). All annual trends are indirectly standardised against 2013/14.

This statistic displays the rate of 30-day acute-care hospital readmissions in the United States from 2015 to 2017, by disease. In 2017, some **** percent of those with heart failure were readmitted to the hospital in the United States within ** days.

This statistic displays the percentage of inpatient 30-day readmissions that occurred within the first 7 days after discharge among the top 20 diagnoses with the highest 7-day readmission rates in 2014, by diagnosis. According to the data, among cases with intestinal obstruction without hernia that were readmitted within 30 days, 43.6 percent were readmitted within the first 7 days following discharge from the hospital.

This statistic displays the rate of all-cause 7 and 30-day readmission rates for U.S. hospitals in 2014, by expected payer. According to the data, among those using Medicare to pay for hospital expenses, those that were readmitted within 7 days had a readmission rate of 6.1 and those that were readmitted after 7 days had a readmission rate of 17.3.

Background The environment in which a patient lives influences their health outcomes. However, the degree to which community factors are associated with readmissions is uncertain. Objective To estimate the influence of community factors on the Centers for Medicare & Medicaid Services risk-standardized hospital-wide readmission measure (HWR). Research Design We assessed 71 community factors in 6 domains related to health outcomes: clinical care; health behaviors; social and economic factors; the physical environment; demographics; and social capital. Subjects Medicare fee-for-service patients eligible for the HWR measure between July 2014-June 2015 (n= 6,790,723). Patients were linked to community factors using their 5-digit zip code of residence. Methods We used a random forest algorithm to rank factors for their importance in predicting hospital HWR scores. Factors were entered into 6 domain-specific multivariable regression models in order of decreasing importance. Factors with with P-values <0.10 were retained for a final model, after eliminating any that were collinear. Results Among 71 community factors, 19 were retained in the 6 domain models and the final model. Domains which explained the most to least variance in HWR were: physical environment (R2=15%); clinical care (12%); demographics (11%); social and economic environment (7%); health behaviors (9%); and social capital (8%). In the final model, the 19 factors explained more than a quarter of the variance in readmission rate (R2=27%). Conclusions Readmissions for a wide range of clinical conditions are influenced by factors relating to the communities in which patients reside. These findings can be used to target efforts to keep patients out of the hospital.

This statistic displays the National hospital readmission rate under Medicare from 2005 to 2014, by initial hospitalization diagnosis. In period July 2011-June 2014, the readmission rate for hospitalizations with an initial diagnosis of heart attack was 17 percent.

Content

The hospital readmission rate PUF presents nation-wide information about inpatient hospital stays that occurred within 30 days of a previous inpatient hospital stay (readmissions) for Medicare fee-for-service beneficiaries. The readmission rate equals the number of inpatient hospital stays classified as readmissions divided by the number of index stays for a given month. Index stays include all inpatient hospital stays except those where the primary diagnosis was cancer treatment or rehabilitation. Readmissions include stays where a beneficiary was admitted as an inpatient within 30 days of the discharge date following a previous index stay, except cases where a stay is considered always planned or potentially planned. Planned readmissions include admissions for organ transplant surgery, maintenance chemotherapy/immunotherapy, and rehabilitation.

This dataset has several limitations. Readmissions rates are unadjusted for age, health status or other factors. In addition, this dataset reports data for some months where claims are not yet final. Data published for the most recent six months is preliminary and subject to change. Final data will be published as they become available, although the difference between preliminary and final readmission rates for a given month is likely to be less than 0.1 percentage point.

Data Source: The primary data source for these data is the CMS Chronic Condition Data Warehouse (CCW), a database with 100% of Medicare enrollment and fee-for-service claims data. For complete information regarding data in the CCW, visit http://ccwdata.org/index.php. Study Population: Medicare fee-for-service beneficiaries with inpatient hospital stays.

Context

This is a dataset hosted by the Centers for Medicare & Medicaid Services (CMS). The organization has an open data platform found here and they update their information according the amount of data that is brought in. Explore CMS's Data using Kaggle and all of the data sources available through the CMS organization page!

• Update Frequency: This dataset is updated daily.

Acknowledgements

This dataset is maintained using Socrata's API and Kaggle's API. Socrata has assisted countless organizations with hosting their open data and has been an integral part of the process of bringing more data to the public.

Cover photo by Justyn Warner on Unsplash
Unsplash Images are distributed under a unique Unsplash License.

This dataset is distributed under NA

This dataset tracks the updates made on the dataset "All-Cause Unplanned 30-Day Hospital Readmission Rate, California (LGHC Indicator)" as a repository for previous versions of the data and metadata.

Reducing unplanned readmissions is a major focus of current hospital quality efforts. In order to avoid unfair penalization, administrators and policymakers use prediction models to adjust for the performance of hospitals from healthcare claims data. Regression-based models are a commonly utilized method for such risk-standardization across hospitals; however, these models often suffer in accuracy. In this study we, compare four prediction models for unplanned patient readmission for patients hospitalized with acute myocardial infarction (AMI), congestive health failure (HF), and pneumonia (PNA) within the Nationwide Readmissions Database in 2014. We evaluated hierarchical logistic regression and compared its performance with gradient boosting and two models that utilize artificial neural networks. We show that unsupervised Global Vector for Word Representations embedding representations of administrative claims data combined with artificial neural network classification models improves prediction of 30-day readmission. Our best models increased the AUC for prediction of 30-day readmissions from 0.68 to 0.72 for AMI, 0.60 to 0.64 for HF, and 0.63 to 0.68 for PNA compared to hierarchical logistic regression. Furthermore, risk-standardized hospital readmission rates calculated from our artificial neural network model that employed embeddings led to reclassification of approximately 10% of hospitals across categories of hospital performance. This finding suggests that prediction models that incorporate new methods classify hospitals differently than traditional regression-based approaches and that their role in assessing hospital performance warrants further investigation.

This data package contains information about hospital readmission and deaths as well as hospital excess readmission reduction program. It also includes data over hospital value based purchasing program for years 2017 and 2018. It comprises of datasets about readmission rates by age, gender, patient residence, payer, zip code and median income.

This statistic displays the Centre for Medicare and Medicaid Services' (CMS) estimates of total penalties on Medicare hospitals with high readmission rates in the U.S. from 2013 to 2017, in million U.S. dollars. In financial year 2013, CMS estimated about *** million U.S. dollars of total penalties whereas in FY 2017 penalties are estimated to increase to *** million U.S. dollars.

Data source: Declaration data of medical service points of insurance medical service organizationNumerator: Number of non-planned readmission cases within 14 days after discharge from denominator cases.Denominator: Number of inpatient cases for childbirth at the same hospital in the same season.Calculation formula: (Numerator / Denominator) x 100%

This dataset contains risk-adjusted 30-day mortality and 30-day readmission rates, quality ratings, and number of deaths / readmissions and cases for ischemic stroke treated in California hospitals. This dataset does not include ischemic stroke treated in outpatient settings.

The Nationwide Readmissions Database (NRD) is database under the Healthcare Cost and Utilization Project (HCUP) which contains nationally representative information on hospital readmissions for all ages, including all payers and the uninsured. The NRD contains data from approximately 18 million discharges per year (35 million weighted discharges) across most of the United States.

Data elements include:

• Discharge month, quarter, and year
• Verified patient linkage number
• Timing between admissions for a patient
• Length of inpatient stay (days)
• Transfers, same-day stays, and combined transfer records
• Identification of patient residency in the state in which he or she received hospital care
• International Classification of Diseases (ICD-9-CM) diagnosis, procedure, and external cause of injury codes (prior to October 1, 2015)
• ICD-10-CM/PCS diagnosis, procedures, and external cause of morbidity codes (beginning October 1, 2015)
• Patient demographics (e.g., sex, age, income quartile, rural/urban residency)
• Expected payment source (e.g., Medicare, Medicaid, private insurance, self-pay, those billed as 'no charge', and other insurance types)
• Total charges and hospital cost (calculated using the "Cost-to-Charge Ratio" file)

The NRD consists of four data files:

• Core File: Available for all years of the NRD and contains commonly used data elements (e.g., age, expected primary payer, discharge status, ICD-10-CM/PCS codes, total charges)
• Severity File: Available for all years of the NRD and contains additional data elements related to identifying health conditions at discharge.
• Diagnosis and Procedure Groups File: Contains additional information on ICD-10-CM/PCS; available beginning in 2018.
• Hospital File: Available for all years of the NRD and contains additional information on participating hospital characteristics.

Abstract Background Heart failure (HF) is worldwide known as a public health issue with high morbimortality. One of the issues related to the evolution of HF is the high rate of hospital readmission caused by decompensation of the clinical condition, with high costs and worsening of ventricular function. Objective To quantify the readmission rate and identify the predictors of rehospitalization in patients with acute decompensated heart failure. Methods Hospital-based historic cohort of patients admitted with acute decompensated HF in a private hospital from Recife/PE, from January 2008 to February 2016, followed-up for at least 30 days after discharge. Demographic and clinical data of admission, hospitalization, and clinical and late outcomes were analyzed. Logistic regression was used as a strategy to identify the predictors of independent risks. Results 312 followed-up patients, average age 73 (± 14), 61% males, 51% NYHA Class III, and 58% ischemic etiology. Thirty-day readmission rate was 23%. Multivariate analysis identified the independent predictors ejection fraction < 40% (OR = 2.1; p = 0.009), hyponatremia (OR = 2.9; p = 0.022) and acute coronary syndrome (ACS) as the cause of decompensation (OR = 1.1; p = 0,026). The final model using those three variables presented reasonable discriminatory power (C-Statistics = 0.655 – HF 95%: 0.582 – 0.728) and good calibration (Hosmer-Lemeshow p = 0.925). Conclusions Among hospitalized patients with acute decompensated heart failure, the rate of readmission was high. Hyponatremia, reduced ejection fraction and ACS as causes of decompensation were robust markers for the prediction of hospital readmission within 30 days of discharge. (Int J Cardiovasc Sci. 2020; 33(2):175-184)

● Region.