Evidence status

Findings and interpretation

This page separates source-cohort evidence, newly computed PenuX feature importance and targets that still require validation.

Research use only. Published benchmark values are not relabelled as prospective PenuX clinical performance.

Current findings

FindingValueInterpretation
Multi-ML source records1,289204 SAP (15.8%) after correct target interpretation.
Raw target coding0=SAP, 1=non-SAPThe source model code explicitly inverts the raw target before modeling. PenuX now records this correction.
Development split used for gain export1,031258 records held out and not used to compute feature-gain weights.
Class weightscale_pos_weight ≈ 5.33Reflects the minority SAP class after target normalization.
Top XGBoost gain featureCa ≈ 7.21%Largest normalized gain in the current all-feature development model.
Next gain featuresα-HBDH 4.59%, CRP 4.08%, WBC 3.28%Consistent with the source paper's emphasis on calcium, inflammatory markers and α-HBDH.
Published XGBoost discriminationAUROC ≈ 0.92Source-cohort literature benchmark, not yet a prospective PenuX result.
PenuX watch targetSensitivity ≥98%Must be tested using a development-locked threshold and external validation.
Clinical deploymentNot establishedRetrospective/open-data results do not validate bedside use.

Top learned gain weights

RankFeatureGain weight
Loading…
Important.

Gain is unsigned feature importance. It is not a linear coefficient and does not tell you that doubling a laboratory value doubles risk.