Large language models (LLMs) embedded in medical Patient Digital Twins (PDTs) exhibit a systemic vulnerability: they can generate fluent, narratively persuasive, yet abductively unsound clinical explanations. In this context, abductive soundness means that an explanation preserves mechanistic plausibility, temporal coherence, explicit handling of missing premises, and sensitivity to counter-evidence. This article reframes the problem as architectural rather than as a mere deficit in training data. We identify three recurrent modes of abductive failure — missing-premise neglect, weak-mechanism support, and counter-evidence discounting. They arise when local semantics, formal world ontology, and the role-specific clinical semiosphere are collapsed into a single surface flow of generation. We propose a governed abductive architecture organised around seven runtime contours and operationalise it in the MS-AGIP platform for multiple sclerosis care. The architecture separates three subsystems: an ontology-guided Research Framework, a clinician-facing Neurologist Digital Twin, and a patient-controlled Patient Digital Twin. We show how disease-specific causal templates, evidence-tiered biomarker reasoning, provenance labels, temporal-coherence checks, molecular-clinical discordance detection, and governed patient-feedback updates jointly transform plausible narrative into sound abduction. The article presents an architectural blueprint and validation protocol aligned with TRIPOD+AI and DECIDE-AI. The architectural-versus-scale distinction has direct implications for safe medical AI: the difference between a fluent and a sound clinical system lies more in architecture and governance than in model size. None of the subsystems has yet been clinically deployed.
LLMs embedded in medical Patient Digital Twins can generate fluent, narratively persuasive, yet abductively unsound clinical explanations.
2.Contribution
Reframes abductive failure as architectural rather than a training-data deficit.
Identifies three recurrent modes: missing-premise neglect, weak-mechanism support, counter-evidence discounting.
Proposes a governed abductive architecture of seven runtime contours, operationalised as the MS-AGIP platform.
3.Architecture, methodology & evidence status
Evidence & statusThis is a preprint hosted on Preprints.org and has not undergone peer review. It is an independent research contribution; its claims and any reported experiments should be read as such.
The abstract above is the authoritative summary of the work as posted at the official source. This archival record does not add results, figures or claims beyond those in the published/posted manuscript. For the complete methodology, results and references, consult the official record or the archived PDF.
Choose a format below. BibTeX and RIS files are also downloadable directly.
Shirbint, E., & Rybalov, A. (2026). From Plausible Narrative to Sound Abduction: A Governed Abductive Architecture for Medical Digital Twins in Multiple Sclerosis Care. Preprints.org. https://doi.org/10.20944/preprints202605.0728.v1
Emanuel Shirbint, and Alexander Rybalov. 2026. “From Plausible Narrative to Sound Abduction: A Governed Abductive Architecture for Medical Digital Twins in Multiple Sclerosis Care.” Preprints.org. https://doi.org/10.20944/preprints202605.0728.v1.
@misc{shirbint2026medicaldigitaltwinssoundabduction,
title = {From Plausible Narrative to Sound Abduction: A Governed Abductive Architecture for Medical Digital Twins in Multiple Sclerosis Care},
author = {Emanuel Shirbint and Alexander Rybalov},
year = {2026},
doi = {10.20944/preprints202605.0728.v1},
url = {https://www.preprints.org/manuscript/202605.0728},
note = {Not peer-reviewed}
}
TY - PREPRINT
AU - Emanuel Shirbint
AU - Alexander Rybalov
TI - From Plausible Narrative to Sound Abduction: A Governed Abductive Architecture for Medical Digital Twins in Multiple Sclerosis Care
PY - 2026
DO - 10.20944/preprints202605.0728.v1
UR - https://www.preprints.org/manuscript/202605.0728
N1 - Not peer-reviewed
ER -