Article

Modular Differentiable Explanations for Markov Disease Models: A Transparent Framework for Clinical Decision Support

2026-07-28

Abstract excerpt

<title>Abstract</title> <p>We propose a modular differentiable programming framework for clinical decision support, replacing conventional post-hoc explanation methods with an inherently interpretable continuous-time Markov chain (CTMC) model. The core innovation consists of partitioning the CTMC’s transition-rate matrix into clinically meaningful submatrices, each associated with a distinct factor such as biomar...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: df284fa6-4c97-54a0-b119-e0fa3607497e
DOI: 10.21203/rs.3.rs-10482355/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Modular Differentiable Explanations for Markov Disease Models: A Transparent Framework for Clinical Decision SupportDOI 10.21203/rs.3.rs-10482355/v1Read

Explainable Artificial Intelligence in Precision Medicine: Methods, Applications, and ChallengesSemantic proximity Read

Large Language Models forecast Patient Health Trajectories enabling Digital TwinsSemantic proximity Read

Multimodal Electronic Health Record Foundation Models with Electrocardiogram for Cardiovascular Disease PredictionSemantic proximity Read

Explainable Clinician-Supervised Artificial Intelligence as an Implementation Framework for Cardiovascular–Kidney–Metabolic Population Health: Synthetic Data Validation of the CHAPERONE-CKM FrameworkSemantic proximity Read

Explainable AI for Clinical Decision Support in Personalized Cancer Screening ProgramsSemantic proximity Read

Clinically grounded multi-agent artificial intelligence for preventive health managementSemantic proximity Read

RiskSqueezeNet: Squeeze-Excitation withAggregated Attention for Tumor Care RiskForecastingSemantic proximity Read

An explainable transformer model learning from entire treatment timelines for pan-cancer risk profiling across healthcare systemsSemantic proximity Read

Evaluation of a Generative Medical Event Foundation Model for Predicting Post-Discharge Trajectories in Emergency Department Abdominal PainSemantic proximity Read

Where risk becomes visible: a layered fixed-policy framework for diabetic kidney disease screening in type 2 diabetesSemantic proximity Read

Medical World Model: From Passive Prediction to Active Simulation in MedicineSemantic proximity Read

SurvivEHR: a competing risks, time-to-event foundation model for multiple long-term conditions from primary care electronic health recordsSemantic proximity Read