Chronic Apical Periodontitis Risk Prediction and Assessment

Workflow and Process:

Sample Selection and Preparation:

Objective: Select relevant CAP-related samples from the UK Biobank ensuring quality and representativeness.

Tasks: Integrate personal health information, blood biochemical indicators, and genetic data to construct feature sets.

Related Files/Directories:

S1_sample_selection.csv: CSV file with selected samples.

feature_info: Directory containing information about features used.

Data Integration and Feature Engineering:

Objective: Combine genetic and electronic medical record data to build comprehensive feature sets.

Tasks: Process and integrate various data types to prepare for model development.

Related Files/Directories:

data_integration: Directory containing scripts and data files for integration.

Machine Learning Model Development:

Objective: Develop and train various machine learning models, including random forest, support vector machine, logistic regression, and adaptive boosting, using the integrated data.

Tasks: Implement and train models to predict CAP risk based on the selected features.

Related Files/Directories:

code: Directory containing code files for machine learning model development.

models: Directory with trained model files.

Model Performance Evaluation:

Objective: Assess the performance of the machine learning models and compare their predictive capabilities.

Tasks: Evaluate models using metrics such as area under the curve (AUC) and sensitivity.

Related Files/Directories:

S2_traintest_id.RData: RData file with training and testing identifiers.

S4_model_performance.RData: RData file with model performance results.

S5_model_res.zip: Compressed file containing detailed model results