Dark Mode
Patient Attendance and Demographics Data
Public Health & Epidemiology
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Medical appointment no-shows significantly impact healthcare efficiency and resource allocation. Uncover patterns in patient attendance with this robust collection of records designed to aid in the prediction of whether a patient will attend their scheduled medical visit. Comprising over 100,000 entries, the data captures patient demographics, health conditions, and appointment details, serving as a solid foundation for training machine learning models to forecast attendance and improve public health operations.
Columns
- PatientId: Unique identifier for the patient.
- AppointmentID: Unique identifier for the specific appointment.
- Gender: Patient gender (Male or Female).
- ScheduledDay: The date and time when the appointment was booked.
- AppointmentDay: The date of the actual medical appointment.
- Age: Age of the patient.
- Neighbourhood: The location where the appointment takes place.
- Scholarship: Indicates if the patient is enrolled in the welfare program (True/False).
- Hipertension: Indicates if the patient has hypertension (True/False).
- Diabetes: Indicates if the patient has diabetes (True/False).
- Alcoholism: Indicates if the patient suffers from alcoholism (True/False).
- Handcap: Indicates if the patient has a handicap (True/False).
- SMS_received: Indicates if an SMS reminder was sent to the patient (True/False).
- Showed_up: The target variable indicating if the patient attended the appointment (True/False).
- Date.diff: The time difference between the scheduling date and the appointment date.
Distribution
- Format: CSV
- Size: 107,000+ rows
- Structure: 15 columns structured for classification tasks, containing a mix of numerical, boolean, and categorical data types.
Usage
- Predictive Modelling: Train classification algorithms to estimate the probability of a patient missing their appointment.
- Healthcare Resource Optimisation: Analyse patterns to adjust staffing and scheduling to mitigate the impact of no-shows.
- Public Health Analysis: Investigate correlations between demographics, health conditions (such as diabetes or hypertension), and appointment adherence.
- Notification Efficiency: Evaluate the effectiveness of SMS reminders in reducing absentee rates.
Coverage
- Geographic Scope: Includes data from 81 unique neighbourhoods (e.g., Jardim Camburi, Maria Ortiz).
- Time Range: Covers appointment scheduling dates from November 2015 to June 2016, and actual appointment dates from April 2016 to June 2016.
- Demographic Scope: Captures a wide age range from infants to seniors (up to 115 years old), with a gender distribution of approximately 66% female and 34% male.
License
CC0: Public Domain
Who Can Use It
- Data Scientists: For building and testing binary classification models.
- Healthcare Administrators: To understand operational inefficiencies and improve patient turnout.
- Public Health Researchers: To study the social determinants of health access and attendance.
- Student Analysts: As a clean, substantial dataset for practicing data visualisation and cleaning techniques.
Dataset Name Suggestions
- Medical Appointment Attendance Records
- Healthcare No-Show Predictor
- Patient Attendance and Demographics Data
- Clinical Appointment Adherence Log
Attributes
Original Data Source: Patient Attendance and Demographics Data
QUALITYLoading...