Model

Model Training

Configure benchmarking parameters for clinical classification.

Platform Note: This demonstration environment uses an ephemeral filesystem. Newly uploaded datasets and trained models will be reset upon session timeout or application restart.

Train Model

Select an approved dataset and define the learning architecture.

Training Input Guide

Choose a method to reveal its inputs and parameters.

Loading method parameters...

Shared inputs · applies to all methods

Dataset: Select a dataset that has completed Add Data intake. Training uses the columns approved during mapping; missing-value handling is applied to the approved rows.
Learning method: Select the algorithm to benchmark. Method-specific parameters appear below when a method is chosen.
Validation folds: Number of cross-validation folds to use for evaluation (integer between 2 and 10). Each target class must have at least as many rows as the selected fold count.
Random state: Integer seed used to make cross-validation splits and any randomized training deterministic for reproducibility.