Table 3 Summary of predictive models for all the three multivariate clinical models in terms of their hyperparameters.
From: AI-driven analysis by identifying risk factors of VL relapse in HIV co-infected patients
Statistical Model | Multivariate Model | Hyperparameters |
|---|---|---|
RSF | Model 1 | n_estimators=1000, min_samples_split=10, min_samples_leaf=15, n_jobs=-1 |
Model 2 | ||
Model 3 | ||
XGBoost | Model 1 | eta=0.002, max_depth=3, objective=“survival:cox”, subsample=0.5, num_boost_round=1000, early_stopping_rounds=10, evals=[(dval, ‘val’)], verbose_eval=0 |
Model 2 | ||
Model 3 | ||
SSVM | Model 1 | rank_ratio=0.1, max_iter=1000, tol=1e-6 |
Model 2 | rank_ratio=1, max_iter=1000, tol=1e-6 | |
Model 3 | ||
CPH | Model 1 | alpha=0.05 |
Model 2 | ||
Model 3 |
