About MindScan
How It Works
An XGBoost classifier trained on 1,200 teen mental health records to predict depression risk.
Dataset
1,200 teen records covering social media habits, sleep, academics, stress, anxiety, and addiction levels.
Preprocessing
Label encoding for categorical features + SMOTE oversampling to handle class imbalance (~2.6% positive cases).
Model
XGBoost — a gradient boosted tree ensemble known for speed and accuracy on tabular data.
Output
0 = Low Depression Risk | 1 = Depression Risk Detected, plus a confidence score.
Input Features
| # | Feature | Type | Range / Values |
|---|---|---|---|
| 1 | Age | Numeric | 10 – 25 |
| 2 | Gender | Categorical | Male / Female |
| 3 | Daily Social Media Hours | Numeric | 0 – 24 hrs |
| 4 | Platform Usage | Categorical | Instagram / TikTok / Both |
| 5 | Sleep Hours | Numeric | 0 – 12 hrs |
| 6 | Screen Time Before Sleep | Numeric | 0 – 10 hrs |
| 7 | Academic Performance | Numeric | GPA 0.0 – 4.0 |
| 8 | Physical Activity | Numeric | 0 – 10 hrs/day |
| 9 | Social Interaction Level | Categorical | Low / Medium / High |
| 10 | Stress Level | Numeric | 1 – 10 |
| 11 | Anxiety Level | Numeric | 1 – 10 |
| 12 | Addiction Level | Numeric | 1 – 10 |