Crohn's Disease Treatment Prediction Model

DB for Machine learning using clinical data at baselines. Used to predicts the medium-term efficacy of biologic therapies for in patients with Crohn's Disease.

1. Data Collection Sources
- Electronic Health Records (EHR)
- Clinical trials and studies
- Genetic data
- Patient-reported outcomes
- Medical imaging

Types of Data
- Demographic information
- Clinical data (symptoms, disease severity, treatment history)
- Genetic data (SNPs, mutations)
- Lab results (CRP levels, fecal calprotectin)
- Imaging data (MRI, endoscopy)
- Lifestyle data (diet, smoking status)

2. Data Preprocessing Steps
- Data Cleaning: Handle missing values, remove duplicates, correct errors.
- Data Normalization/Standardization: Normalize lab results, standardize imaging data.
- Feature Engineering: Create new features from existing data, e.g., calculate disease activity scores.
- Encoding Categorical Data: Convert categorical variables to numerical ones using one-hot encoding or label encoding.
- Data Splitting: Split data into training, validation, and test sets.