Machine Learning Modelling

Uses

Preparation

Risks & contraindications

Comparisons

Highlighted claims

• The protocol will develop models for asthma, COPD, and combined asthma-COPD cohorts across two outcome types and three time windows. — Developing and validating an electronic health record-embedded AI model for managing multimorbid hospitalisation risk in patients with chronic RESpiratory disease (AiRES): a study protocol
• The three machine learning algorithms are LASSO logistic regression, XGBoost, and CatBoost. — Developing and validating an electronic health record-embedded AI model for managing multimorbid hospitalisation risk in patients with chronic RESpiratory disease (AiRES): a study protocol
• Model training will use standardized predictors, 10-fold cross-validation, and grid-search hyperparameter tuning. — Developing and validating an electronic health record-embedded AI model for managing multimorbid hospitalisation risk in patients with chronic RESpiratory disease (AiRES): a study protocol
• Feature selection removes near-zero variance predictors and then uses ensemble importance rankings to define a final feature set. — Developing and validating an electronic health record-embedded AI model for managing multimorbid hospitalisation risk in patients with chronic RESpiratory disease (AiRES): a study protocol
• Patient-level splitting is used to reduce overly optimistic estimates from repeated observations on the same patients. — Developing and validating an electronic health record-embedded AI model for managing multimorbid hospitalisation risk in patients with chronic RESpiratory disease (AiRES): a study protocol