Boosted-tree score
Each tree contributes a nonlinear correction; this is why XGBoost does not have one linear coefficient per laboratory variable.
PenuX maps early laboratory data to a boosted-tree score and an estimated probability of later Atlanta-defined severe acute pancreatitis (SAP).
Only measurements available at or before prediction time are eligible. Future organ-failure variables or post-deterioration interventions are excluded.
Each tree contributes a nonlinear correction; this is why XGBoost does not have one linear coefficient per laboratory variable.
When calibration is enabled, a development-only mapping \(g\) gives \(p_{cal}=g(p_{raw})\).
The threshold is locked from out-of-fold development predictions and is not moved after inspection of the final test cohort.
The table below is loaded from model-weights.json, generated from the 1,289-record Guilin Multi-ML cohort. The source target is explicitly normalized from raw 0=SAP, 1=non-SAP to PenuX 1=SAP.
| Rank | Feature | Gain weight | Splits |
|---|---|---|---|
| Loading model weights… | |||
Gain is an unsigned measure of how much a feature improved tree objectives when it was used for splits. It cannot be multiplied by a raw lab value to reproduce the XGBoost probability. Direction and patient-specific contribution require SHAP/PDP or direct tree inference.