cs.LGNov 9, 2026

The Dark Matter of Clinical Data: An Identification Limit on Disentangling Physiology from Care Process in electronic health records

Authors: Mohammad Shahin, Krittaphas Chaisutyakorn, Dimitrios Proios, David Restrepo, Vishala Mishra, Boya Zhang, Aadarsh Sivaraman, Sparsh Roy, 

Organizations: Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Boston University School of Public Health, Boston, MA, USA · Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA · Siriraj Informatics and Data Innovation Center, Mahidol University, Bangkok, Thailand · 

Abstract

Representations learned from electronic health record (EHR) data encode patient physiology together with the clinical process that decides what is measured, when, and for whom. We formalize the data-generating process with latent physiology, ordering intent, laboratory values that exist only when measured, a learned representation, and clinical environments, and analyze two strategies for undoing this entanglement. First, no division of the information carried by laboratory "value" and "ordering" channels is identified from a single dataset: when ordering depends on the analyte, its distribution among untested patients is not recoverable, and a sentinel code for the undefined recorded value makes it carry all the entropy of the ordering indicator, fixing partial information decomposition (PID) for every redundancy measure satisfying the Williams-Beer axioms and invariant under injective re-encoding. Second, cross-site invariance of representation-conditional outcomes is a falsifiable implication of biological invariance taken jointly with exclusion and representation-sufficiency conditions, but not an identification strategy: we construct observationally equivalent models that disagree about biological invariance, whether the invariance test fails or passes. For binary physiology this happens exactly when case mix differs, the representation is lossy, and physiology affects the outcome. A worked example yields a 9.6-percentage-point cross-site gap under an unchanged biological mechanism. Tests performed for every patient remove the ordering gate, and measured tests can restore identification: biological invariance is identified when a test exactly summarizes outcome-relevant physiology, or, for binary physiology, when two tests with independent errors are available at sites with different case mix. Cross-site analyses should be reported as tests of a stated joint hypothesis.

Figures & tables

Explore similar work

CardsList
  1. Informative Missingness to Generate Irregular Clinical Time Series

    Jun 14, 2026Hadi Mehdizavareh, Gabriele Santangelo, Giovanna Nicora +4Synthetic Data GenerationTime Series Generation

  2. EHR2Trace: Auditable EHR Data Infrastructure for Patient World Models and Clinical Agents

    Sep 18, 2026Xinye Yang, Yuli Wang, Cheng Ting Lin +1Electronic Health RecordsData Provenance

  3. Information Set Emulation: Causal Certificates for AI Derived EHR Features

    Sep 15, 2026Takes Fujita, Nobutaka HattoriCausal Effect EstimationPartial Identification