Icon

JKISeason4-6 - Heart Failure Prediction

Beginner-friendly objectives:
1. Load and preprocess the heart disease dataset, ensuring that the data is clean and ready for analysis.
2. Perform a train-test split on the dataset, maintaining the class distribution for accurate model evaluation.need to

Notes:

May need to transform some of the features to change distribution, to remove values that may be wrong e.g. zero cholestrol

Feature descriptions related to heart disease prediction (K-AI):

  1. ChestPainType: This feature categorizes the type of chest pain experienced by the patient, which can indicate different underlying heart conditions. Common types include typical angina, atypical angina, non-anginal pain, and asymptomatic.

  2. RestingBP: This measures the resting blood pressure of the patient in mmHg. High blood pressure is a significant risk factor for heart disease.

  3. Cholesterol: This indicates the total cholesterol level in the blood, measured in mg/dl. High cholesterol levels can lead to plaque buildup in arteries, increasing heart disease risk.

  4. FastingBS: This represents the fasting blood sugar level, measured in mg/dl. A fasting blood sugar level greater than 120 mg/dl may indicate diabetes, which is a risk factor for heart disease.

  5. RestingECG: This feature describes the results of a resting electrocardiogram, which can show the electrical activity of the heart and help identify abnormalities.

  6. MaxHR: This is the maximum heart rate achieved during exercise testing, measured in beats per minute (bpm). A lower maximum heart rate can indicate poor heart health.

  7. ExerciseAngina: This binary feature indicates whether the patient experiences angina (chest pain) during exercise. It is a significant indicator of heart disease risk.

  8. Oldpeak: This measures the ST depression induced by exercise relative to rest, which can indicate the severity of heart disease. It is a continuous variable measured in mm.

  9. ST_Slope: This feature describes the slope of the ST segment during exercise testing, which can indicate the presence of heart disease. It can be categorized as upsloping, flat, or downsloping.

Intermediate-friendly objectives:

1. Implement a parameter optimization loop to fine-tune the model's hyperparameters for improved performance.

2. Within the Parameter Optimization Loop, conduct cross-validation to assess the model's robustness and generalization (default: Naïve Bayes, but feel free to experiment with other models).

3. Integrate multiple data science techniques, including one-hot encoding and normalization, to enhance the model's predictive power.

4. Evaluate the model's performance using advanced metrics and visualization techniques to gain insights into its accuracy and reliability.

5. Use the Surrogate Random Forest model from Global Feature Importance to determine the top 3 most important features driving predictions.

CSV Reader
70-20 SplitMean of Target Column:Partition 1 - 0.556Partition 2 - 0.547
Partitioning
Statistics
Box Plot
Naive Bayes Learner
Parameter Optimization Loop End
Parameter Optimization Loop Start
Naive Bayes Predictor
Number to String
Category to Number
X-Partitioner
Random Forest Learner
X-Aggregator
Scorer
Random Forest Predictor
Capture Workflow Start
Capture Workflow End
Category to Number (Apply)
Number to String
Input: 0 : Model as a Workflow Object 1 : Data from Model Test Partition Output: 0 : Global Feature Importance
Global Feature Importance

Nodes

Extensions

Links