Background The Therapeutic Distance framework (Paper 1) achieved AUC 0.61 for orbit-based mortality prediction in 11,627 sepsis patients. We hypothesised that incorporating state-dependent parameter relevance would substantially improve prediction.

Methods We extended the framework to 84,176 ICU patients from MIMIC-IV v3.1 across 16 clinical syndromes. Validation included full-population leave-one-out (n=59,362), head-to-head comparison against SAPS-II and logistic regression on 34,467 matched patients with bootstrap confidence intervals, temporal validation, outcome permutation, sensitivity analysis, and calibration assessment. A K-matrix of 120 state-dependent parameter constants was computed.

Results Full-population leave-one-out achieved AUC 0.832 (n=59,362). On 34,467 matched patients, Therapeutic Distance (AUC 0.841) significantly outperformed both SAPS-II (0.786; Δ=+0.055, 95% CI +0.048 to +0.061, p<0.001) and logistic regression with identical parameters (0.788). Temporal validation showed stable performance (Δ=−0.006). Outcome permutation confirmed genuine signal (AUC 0.859→0.498 with shuffled mortality; five replicates, range 0.494–0.510). Sensitivity analysis demonstrated near-zero variation (Δ 0.0006–0.003). Calibration was acceptable (mean predicted–observed deviation 0.016 across deciles; Brier score 0.126). The framework performed well for 8 of 16 syndromes (AUC >0.70) and failed for DKA and post-cardiac surgery (AUC <0.40). Unlike global severity scores, the framework provides therapy-specific risk stratification.

Conclusions Therapeutic Distance provides therapy-specific risk stratification that exceeds the discrimination of both established severity scores and standard machine learning while remaining robust to hyperparameter choices, temporal drift, and outcome permutation. The framework defines clear boundaries where it succeeds and fails.

AB is the developer of chicxulub.ai.

This study did not receive any funding.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

Ethics committee/IRB of Beth Israel Deaconess Medical Center (Boston, MA) gave ethical approval for the creation of the MIMIC-IV database (protocol 2001P001699). Ethics committee/IRB of Beth Israel Deaconess Medical Center waived ethical approval for secondary analyses of de-identified MIMIC-IV data. Access was obtained through PhysioNet after completion of the Collaborative Institutional Training Initiative (CITI) program in human subjects research.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes