Corrected resampled t -tests confirm improved performance over the non-sequential Transformer, while the comparison with XGBoost indicates a favorable trend without conclusive evidence.
← all excerpts
A Reproducible Post-Valve-Replacement EHR Cohort for Comparative AI Studies.
2
—
—
The sentences
The corrected resampled t -test supports a statistically significant improvement over the aggregated-feature Transformer (for both AUROC and AUPRC), whereas SeqT’s numerically higher scores than XGBoost did not reach statistical significance in either metric.