Patient Data
This is the complete dataset used to train and test our prediction model.
| Blood Pressure (Systolic) | Cholesterol | Heart Rate | Blood Sugar | Risk |
|---|---|---|---|---|
| 150 | 250 | 90 | 130 | risky |
| 118 | 190 | 72 | 95 | risk less |
| 160 | 280 | 95 | 150 | risky |
| 125 | 210 | 78 | 105 | risk less |
| 135 | 225 | 82 | 115 | risky |
| 115 | 185 | 68 | 92 | risk less |
| 145 | 230 | 88 | 120 | risky |
| 110 | 180 | 65 | 90 | risk less |
| 170 | 290 | 100 | 160 | risky |
| 122 | 205 | 75 | 100 | risk less |
How the Model is Trained
The model learns from patient data using a process called "supervised learning".
Step 1: Train-Test Split
The dataset is split into two parts: a larger Training Set to teach the model, and a smaller Testing Set to evaluate its accuracy. The blue rows in the table above represent the testing data.
Full Dataset
10 records
→
Training Set
8 records
Testing Set
2 records
Step 2: Training the Random Forest
The model is a Random Forest, which is a collection of many individual Decision Trees. Each tree is trained on a random subset of the training data and features (like blood pressure, cholesterol, etc.). When making a prediction, all trees "vote", and the majority outcome becomes the final prediction. This makes the model more accurate and robust for risk assessment.
Tree 1
Tree 2
Tree 3
...
Many Trees