🫀 Student-Health-Conditions

📌 Aims of the Project

In recent years, student health challenges-such as stress, inadequate sleep, poor dietary habits, and mental health issues have become a growing concern worldwide. These factors not only affect well-being but also impact academic success. However, the intricate relationships between these health factors and academic outcomes remain underexplored.

This project analyzes multiple datasets to uncover connections between student health behaviors and academic performance. By leveraging data-driven insights, we aim to provide actionable recommendations to improve student well-being and educational outcomes.

🏁 Goal

• Develop and fine-tune a classification model to analyze correlations between health behaviors (e.g., mental health, physical activity, sleep) and academic performance (e.g., GPA, focus, grades).
• Identify universal patterns and context-specific trends by examining data from individual, national, and global perspectives.
• Offer evidence-based strategies to help schools, colleges, and policymakers enhance student success.

🔧 Methodologies

• Feature Selection and Correlation using statistics and visualizations:
  • Pearson Correlation, Spearman’s Rank Correlation, Chi-Square Test, Heatmaps, Boxplots, Pair Plot
• Data Inconsistencies such as missing values and outliers
  • Detection using summary statistics interquartile range, and visualizations.
  • Handling: Removal, transformation, or imputation.
• Predictive Modeling: A core component, aiming to accurately classify health risk levels.
  • Random Forest, XGBoost, K-Nearest Neighbors (KNN), Support Vector Machines (SVM)
  • Data Preprocessing: Encoding categorical variables and scaling numerical variables
  • Evaluation metrics: Accuracy, Precision, Recall, Weighted F1-Score

🔍 Purpose

The primary objectives of this project are:

1. Identify Correlations

Explore the relationships between health behaviors (e.g., sleep, physical activity, mental health) and academic outcomes (e.g., GPA, focus, grades).

2. Validate Across Contexts

Use individual, national, and global datasets to ensure robust, generalizable findings.

3. Develop Strategies

Provide evidence-based insights for schools, colleges, and policymakers to enhance student well-being and performance.

🚀 Possible Outcomes

• Expected Results: Successful predictive model, key health risk factors identified.
• Practical Applications: School-based interventions, policy and decision-making, integration into student health systems.
• Challenges and Ethical Considerations: Limitations in data quality, class imbalances, ensuring data privacy and security, addressing potential biases to ensure fail and equitable predictions.
• Future Research Opportunities: Utilizing larger and more diverse datasets, real-time health tracking.

💡 Project Implications

Ethical considerations are central to this project:

Data Privacy:

• Ensure compliance with FERPA and HIPAA by anonymizing datasets.

Equity & Accessibility:

• Prevent the misuse of health categorizations to stigmatize students or limit opportunities.

Empowerment:

• Use findings to promote healthy decision-making among students through supplemental educational content.

🎯 Conclusion

Positive Impact

• Informative results to expand student supports and education around the impact of stress and other factors on their health.

Model Comparison

• By exploring multiple model types, we can see how well each method predicts the classification levels.