Dark Mode
Healthy Aging Sleep and Healthcare Prediction Data
Public Health & Epidemiology
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Derived from the National Poll on Healthy Aging (NPHA), this dataset aggregates survey responses from seniors to facilitate the development and validation of machine learning algorithms. The primary objective of the data is to predict the number of different doctors a respondent visits within a year. It captures a holistic view of senior health by integrating demographic details with self-assessed physical, mental, and dental health metrics, alongside detailed sleep-related variables. This resource is particularly valuable for geriatric healthcare research, predictive modelling of healthcare resource utilisation, and understanding the interplay between sleep quality, general health, and medical consultation frequency.
Columns
- Number of Doctors Visited: Target variable categorising the total count of different doctors seen (1: 0-1 doctors, 2: 2-3 doctors, 3: 4 or more doctors).
- Age: The patient's age group (1: 50-64 years, 2: 65-80 years).
- Physical Health: Self-assessment of physical well-being on a scale from Excellent to Poor.
- Mental Health: Self-evaluation of mental or psychological health on a scale from Excellent to Poor.
- Dental Health: Self-assessment of oral or dental health on a scale from Excellent to Poor.
- Employment: Employment status including Working full-time, Working part-time, Retired, or Not working.
- Stress Keeps Patient from Sleeping: Binary indicator (Yes/No) regarding stress impact on sleep.
- Medication Keeps Patient from Sleeping: Binary indicator (Yes/No) regarding medication impact on sleep.
- Pain Keeps Patient from Sleeping: Binary indicator (Yes/No) regarding physical pain disturbance during sleep.
- Bathroom Needs Keeps Patient from Sleeping: Binary indicator (Yes/No) regarding bathroom needs affecting sleep.
- Unknown Keeps Patient from Sleeping: Binary indicator (Yes/No) for unidentified sleep disturbances.
- Trouble Sleeping: General indicator of sleeping difficulties.
- Prescription Sleep Medication: Frequency of use (Use regularly, Use occasionally, Do not use).
- Race: Racial or ethnic background of the patient.
- Gender: Gender identity of the patient (Male/Female).
Distribution
The dataset is structured in a tabular CSV format (NPHA-doctor-visits.csv) containing 714 valid records. It comprises 15 columns, consisting of categorical and ordinal variables suitable for classification tasks. There are no mismatched or missing values reported across the primary fields, ensuring high data integrity for immediate analysis.
Usage
- Healthcare Utilisation Prediction: Train multi-class classification models (e.g., Random Forest) to forecast the frequency of doctor visits among seniors.
- Geriatric Health Analysis: Investigate correlations between self-reported physical/mental health and medical help-seeking behaviour.
- Sleep Study Research: Analyse specific sleep disturbances (pain, stress, medication) and their relationship to broader health outcomes and doctor visitation rates.
- Socio-Demographic Impact Studies: Explore how age, race, gender, and employment status influence healthcare access and usage in the ageing population.
Coverage
- Demographic Scope: Seniors aged between 50 and 80 years.
- Geographic Scope: United States (implied by the National Poll on Healthy Aging context).
- Data Reliability: Filtered subset specifically curated for algorithmic validation.
License
CC BY-SA 4.0
Who Can Use It
- Data Scientists: For building and testing classification algorithms and predictive models.
- Healthcare Analysts: To understand factors driving patient volume and resource allocation.
- Academic Researchers: Investigating healthy ageing, sleep hygiene, and public health trends.
- Policy Makers: Evaluating the health needs and medical dependency of the senior workforce and retirees.
Dataset Name Suggestions
- NPHA Senior Doctor Visits and Health Metrics
- Healthy Aging Sleep and Healthcare Prediction Data
- Geriatric Health Status and Medical Visit Classification
- Senior Citizen Health, Sleep, and Doctor Usage Dataset
Attributes
Original Data Source: Healthy Aging Sleep and Healthcare Prediction Data
QUALITYLoading...