Dark Mode
Hospital Readmission Risk Predictor
Patient Health Records & Digital Health
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Aids in predicting patients who are at a high risk of readmission within 30 days of hospital discharge. This synthetic dataset is structured to mimic realistic clinical and demographic patterns, helping organizations build predictive models aimed at reducing healthcare costs associated with preventable readmissions. The dataset focuses on 11 clinical and demographic variables relevant to patient outcomes.
Columns
The dataset includes 12 columns covering patient identifiers, clinical measurements, and outcomes:
- patient_id: Unique identification number for the patient (ID).
- age: Patient age recorded in years (Integer).
- gender: Patient reported gender (String, e.g., Male, Female, Other).
- blood_pressure: Measurement of systolic and diastolic blood pressure in mmHg (String, e.g., 143/94).
- cholesterol: Total cholesterol level in mg/dL (Integer).
- bmi: Body Mass Index (BMI).
- diabetes: Indicates whether the patient has diabetes (Boolean).
- hypertension: Indicates whether the patient has hypertension (Boolean).
- medication_count: Total number of medications prescribed.
- length_of_stay: Duration of the hospital stay.
- discharge_destination: Where the patient was discharged (e.g., Home, Rehab, Other).
- readmitted_30_days: The target variable, indicating if the patient was readmitted within 30 days (Boolean, Yes/No).
Distribution
The primary data file,
hospital_readmissions_30k.csv, contains 30,000 records, featuring 12 variables in total. The file size is approximately 1.57 MB. The data is simulated and is provided in a clean state, with no missing or mismatched values across the fields. The dataset is static, with an expected update frequency of "Never."Usage
This data is ideal for several applications, including:
- Developing and training machine learning models specifically designed to flag high-risk patients upon discharge.
- Performing detailed analysis to identify key risk factors, such as underlying conditions like diabetes or hypertension, and the impact of different discharge destinations on readmission likelihood.
- Informing healthcare operational planning and resource allocation strategies based on predictive risk insights.
Coverage
The scope is purely synthetic, simulating a diverse clinical population. Demographic coverage includes age (ranging from 18 to 90) and gender (Male, Female, Other). Clinical variables span common biometric and condition indicators, providing a wide range of factors for risk assessment. As the data is synthetic, there is no inherent geographic or time range restriction.
License
CC0: Public Domain
Who Can Use It
Intended users include data scientists focusing on medical risk modelling, machine learning engineers developing predictive maintenance tools for healthcare systems, and healthcare policy analysts researching preventative measures for hospital readmission.
Dataset Name Suggestions
- Hospital Readmission Risk Predictor
- Synthetic Clinical Readmission Data
- 30-Day Patient Readmission Forecasting
- Healthcare Patient Outcome Model Data
Attributes
Original Data Source: Hospital Readmission Risk Predictor
QUALITYLoading...