acePredictive and mechanistic evaluation of ODE-informed machine learning for systemic lupus erythematosus disease-activity stratification
Mechanistic consistency does not necessarily imply improved prediction. We evaluated ordinary differential equation (ODE)-informed machine learning for systemic lupus erythematosus (SLE) disease-activity stratification, assessing predictive utility and mechanistic consistency separately. GSE65391 data classified 131 patients as high (n = 56) or low (n = 75) disease activity. A published four-state ODE generated anti-inflammatory, immune-complex, tissue-damage, and pro-inflammatory features. Architecture-matched…
The published ODE's states showed consistent disease-activity directionality and stable relationships under perturbation and parameter variation, giving a structured way to examine lupus dynamics.
The initial predictive advantage of adding ODE features to a Random Forest weakened under stricter out-of-fold evaluation, and no robust incremental discrimination was established.
External checks used modality-specific proxies that showed only exploratory directional analogy and did not validate the source-defined ODE states.
Evidence
- Peer-reviewedComputational Biology and Chemistry2026-10-15
How should this claim be treated?
Truvace Impact Record TRV-2026-1963, v1: “Predictive and mechanistic evaluation of ODE-informed machine learning for systemic lupus erythematosus disease-activity stratification.” Truvace, 2026-10-20. /record/TRV-2026-1963 (accessed at citation time). sha256 2e11450cdaf9e119…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-1963 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.