Description:
The predictive model is built to classify patients who become positive and negative cases through customer databases.
Project Objectives:
Identifying factors impacting sleep disorders.
Understanding how doctors identify sleep disorders in patients.
Determining attributes associated with sleep disorders.
Result:
Key highlights:
1. Data Collection and Analysis:
The dataset covers variables related to sleep, daily habits, and the presence of sleep disorders, including demographics, sleep duration, quality of sleep, physical activity, stress levels, BMI, and cardiovascular health.
Analysis procedures include cleaning and preparing the dataset, splitting into training and test sets, and applying techniques like PCA, LDA, QDA, Decision Tree, and Correspondence Analysis.
2. Sleep Disorders Definitions and Importance:
Definitions of sleep disorders like sleep apnea and insomnia.
Emphasizing the significance of addressing sleep disorders for overall health and well-being.
3. Biases and Data Analysis:
Discussing potential biases in data collection and analysis, such as selection bias, self-report bias, and gender bias.
4. Statistical Analysis and Results:
Utilizing statistical methods to analyze data, with a focus on understanding how various factors like age, gender, BMI, sleep duration, and lifestyle habits relate to sleep disorders.
5. Model Assessments:
Assessing various models like LDA, Decision Tree, and QDA for their accuracy and effectiveness in predicting and understanding sleep disorders.
6. Conclusion:
Summarizing key findings related to the objectives, including factors impacting sleep disorders, methods for identification by doctors, and attributes associated with these disorders.
Download full report