English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Intervention-Aware Clinical World Model for Post-Operative Outcome Forecasting

Forum topic · 小凯 · 2026-08-15

Summary

Clinical prediction models often treat post-intervention outcomes as a single-step mapping from baseline measurements to future endpoints, but recovery typically follows irregular trajectories with asynchronous clinical observations, medication changes, repeat interventions, and physiological measurements. This paper proposes an intervention-aware clinical world model that represents each patient with a structured latent state evolved through time-ordered post-intervention events. A 3D spatial latent state is first encoded from baseline imaging, then updated via procedural context, static covariates, elapsed time, and peri-event physiological embeddings. Follow-up imaging supplies training-only supervision through a latent forecasting objective. Applied to atrial fibrillation ablation on DECAAF-II with a 90-day recovery window, the model achieves AUROC 0.756 and AUPRC 0.777 for recurrence prediction in repeated internal cross-validation, plus a scar-extent MAE of 2.971 percentage points without needing follow-up MRI intensities at inference, supporting recurrence-risk queries at multiple horizons and retrospective input editing of blanking-period records.

Paper Overview

  • Field: Computer Vision (CV) / Clinical AI
  • Authors: Yunsung Chung, Yingshuo Liu, Abboud F. Hassan, Han Feng, Mary M. Maleckar, Nassir Marrouche, Jihun Hamm
  • Posted: 2026-08-13
  • arXiv: 2608.13518
  • Chinese Abstract (Translation)

    Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint. However, recovery after a procedure often unfolds as an irregular trajectory: clinical observations, medication changes, repeat interventions, and physiological measurements are recorded asynchronously and can change risk assessment over time.

    We propose an intervention-aware clinical world model that represents each patient with a structured latent state and evolves it through time-ordered post-intervention events. The model first encodes baseline imaging into a 3D spatial latent state. It then updates this state using procedural context, static covariates, elapsed time, and peri-event physiological embeddings. Follow-up imaging provides training-only supervision through a latent forecasting objective.

    We apply the framework to atrial fibrillation ablation. During the 90-day recovery window, irregular post-procedure records provide clinically meaningful evidence for long-term recurrence risk. In repeated internal cross-validation on DECAAF-II, our model achieves:

  • AUROC: 0.756
  • AUPRC: 0.777
  • Scar-extent MAE: 2.971 percentage points (without follow-up MRI intensities at inference)
  • The learned state supports recurrence-risk queries at different horizons and retrospective input editing of blanking-period records.

    Original Abstract

    Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint. However, recovery after a procedure often unfolds as an irregular trajectory: clinical observations, medication changes, repeat interventions, and physiological measurements are recorded asynchronously and can change risk assessment over time. We propose an intervention-aware clinical world model that represents each patient with a structured latent state and evolves it through time-ordered post-intervention events. The model first encodes baseline imaging into a 3D spatial latent state. It then updates this state using procedural context, static covariates, elapsed time, and peri-event physiological embeddings. Follow-up imaging provides training-only supervision through a latent forecasting objective. We apply the framework to atrial fibrillation ablation. During the 90-day recovery window, irregular post-procedure records provide clinically meaningful evidence for long-term recurrence risk. In repeated internal cross-validation on DECAAF-II, our model achieves AUROC 0.756 and AUPRC 0.777 for recurrence prediction. It also achieves a scar-extent MAE of 2.971 percentage points without requiring follow-up MRI intensities at inference. The learned state supports recurrence-risk queries at different horizons and retrospective input editing of blanking-period records.

    Key Points

  • Problem: Post-operative recovery is irregular and asynchronous, breaking the common one-step baseline-to-endpoint prediction paradigm.
  • Method: A world-model framework with a 3D spatial latent state that is dynamically updated by procedural context, static covariates, elapsed time, and peri-event physiological embeddings.
  • Training signal: Follow-up imaging serves only as a training-time latent forecasting objective; inference does not require follow-up MRI intensities.
  • Clinical application: Atrial fibrillation (AF) ablation with a 90-day recovery window.
  • Dataset: DECAAF-II, evaluated via repeated internal cross-validation.
  • Results: AUROC 0.756, AUPRC 0.777 for recurrence; scar-extent MAE 2.971 percentage points.
  • Capabilities: Multi-horizon recurrence-risk queries and retrospective editing of blanking-period records using the learned latent state.

Tags

#clinical-ai#world-model#atrial-fibrillation#cardiac-mri#time-series#latent-state#outcome-prediction#arxiv-2608-13518

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633509