WMHS · NeurIPS 2026 Workshop

About the workshop

Clinical trial simulation as a stress test for world models

Clinical trial simulation is a uniquely demanding and falsifiable testbed for one of the central open problems in machine learning: building reliable world models of complex, partially observed, intervention-rich systems.

This workshop focuses on patient world models — generative and reasoning-capable systems that learn from patient trajectories, trial protocols, interventions, mechanisms of action, and real-world evidence to support clinical trial simulation and decision-making.

Why now

Foundation models, sequence models, and generative simulators are converging with healthcare AI’s shift from static risk prediction toward longitudinal modelling, treatment response estimation, and real-world evidence — yet reliability in high-stakes medical settings remains unresolved.

Who should attend

Researchers and practitioners across machine learning, healthcare AI, causal inference, biostatistics, clinical development, epidemiology, AI for science, uncertainty and trustworthy ML, reasoning systems, digital health, pharma / biotech, real-world evidence, regulatory science, and translational medicine — including academia, industry, clinical research organizations, and interdisciplinary teams.

Topics of Interest

Where simulation, causality, and clinical evidence meet

We invite work that advances reliable, intervention-aware patient world models — including benchmarks, negative results, position papers, and emerging directions.

Patient world models using longitudinal, multimodal clinical data
Clinical trial simulation, virtual trial arms, synthetic controls, and external control cohorts
Counterfactual outcome prediction, treatment effect modelling, and target trial emulation
Foundation models for EHR, clinical trials, real-world evidence, and patient timelines
Representation of interventions, treatment regimes, endpoints, eligibility criteria, pathways, and mechanisms of action
Causal representation learning, causal inference, and off-policy evaluation for intervention-aware simulation
Uncertainty quantification, calibration, abstention, ambiguity, and selective prediction
Temporal reasoning, logical consistency, clinical plausibility, and protocol-aware reasoning
Agentic systems for trial design, protocol interpretation, evidence synthesis, and clinical research workflows
Benchmarking, robustness, and validation against real-world evidence, historical trials, clinical knowledge, and downstream clinical utility

Call for Papers

World Models for High-Stakes Health (NeurIPS 2026) invites submissions on architectures, algorithms, theory, empirical studies, benchmarks, demonstrations, and position papers related to patient world models, intervention-aware modelling, clinical trial simulation, virtual populations, and the evaluation and reliable deployment of AI in high-stakes healthcare. Submissions must present original, unpublished work that has not appeared at NeurIPS or other archival machine-learning venues.

Key dates

Submission deadline: September 1, 2026, AoE.
Notification: on or before September 29, 2026, AoE.
Workshop date: December 11–12, 2026 (Atlanta).

All deadlines follow the Anywhere on Earth (AoE) timezone.

Submission site

Submissions are managed via OpenReview and remain private during review. All authors should maintain up-to-date OpenReview profiles for conflict-of-interest management and paper matching. Submit your paper at the OpenReview submission portal.

Scope

We welcome contributions across the topics above. Accepted papers are presented as posters, with a subset selected for oral, spotlight, or demonstration talks, and we give a Best Paper Award and a Best Clinical Impact Paper Award for work with particularly strong potential to improve clinical research, healthcare delivery, or patient outcomes. The workshop is in person at NeurIPS 2026 in Atlanta.

Submission guidelines

Formatting

Submissions must be in English and use the NeurIPS 2026 workshop LaTeX template. Papers are submitted as a single PDF:

Full Papers: at most 9 pages of main text.
Extended Abstracts: at most 4 pages of main text.
Demo Track: working demonstrations of systems and tools for patient modelling, clinical trial simulation, healthcare AI evaluation, or related applications, presented alongside the poster sessions.
Position Papers: on validation, governance, regulation, evaluation standards, and the responsible clinical use of AI.

References and appendices do not count toward the page limit, but the main text must be self-contained.

Responsible-use statement

Every submission also includes a short responsible-use statement covering relevant limitations, uncertainty, potential clinical or societal impacts, and suggested mitigations. It is reviewed with the paper, and a missing statement is grounds for desk rejection.

Anonymity

The workshop uses double-blind review. Submissions must be anonymized, with author names, affiliations, and acknowledgments removed and prior work cited in the third person.

Non-archival policy

The workshop is non-archival. Papers under review elsewhere are welcome, and accepted papers may be published at other venues afterward. Work already published at NeurIPS or other archival machine-learning venues should not be submitted.

Contact

Email jay.nanavati@iqvia.com.

Submit your paper

Submissions are managed via OpenReview.

Open the OpenReview portal

Speakers & Panel

Voices across world models, causality, and clinical AI

The workshop brings together researchers and practitioners working across machine learning, clinical development, and trustworthy healthcare AI, with a cross-disciplinary panel on scientific validity, clinical usefulness, evaluation, and responsible deployment.

Invited Speakers

Nathan Kallus

Assistant Professor of Medical AI

Cornell University

Chris Tomlinson

Senior Fellow in Clinical Foundation Models

UCL / NHS Foresight

More

Additional speakers

To be confirmed

Panel Discussion

Moderator

Raja Shankar

VP Machine Learning

IQVIA

Panelist

Rose Yu

Assistant Professor of Computer Science

UC San Diego

Panelist

More

Additional panelists

To be confirmed

Additional speakers and panelists will be announced as the programme is finalised.

Program

08:00 – 08:10

Opening Remarks

Motivation, workshop objectives, and overview of the day.

08:10 – 08:45

Invited Talk 1: Patient World Models and Causal Digital Twins

Speaker to be confirmed.

08:45 – 09:20

Invited Talk 2: Causal Inference and Intervention-Aware Trial Simulation

Nathan Kallus.

09:20 – 09:45

Coffee Break

Informal discussion and networking.

09:45 – 10:45

Contributed Oral Session 1: Patient World Models and Trial Simulation

Patient world models, virtual trial arms, synthetic controls, EHR foundation models, and trajectory generation.

10:45 – 11:20

Invited Talk 3: Medical Foundation Models and Patient Trajectories

Chris Tomlinson.

11:20 – 12:20

Lunch Break

Informal networking.

12:20 – 12:55

Invited Talk 4: Real-World Evidence, Validation, and Deployment Reliability

Speaker to be confirmed.

12:55 – 13:55

Poster Session

Accepted papers and interaction across machine learning, clinical research, causal inference, and industry.

13:55 – 14:20

Structured Discussion: What Counts as Validation for a Patient World Model?

Moderated by Jay Nanavati. Discussion of historical trial emulation, synthetic controls, uncertainty, causal validity, generalisation, and clinical utility.

14:20 – 14:45

Coffee Break

Informal discussion and networking.

14:45 – 15:45

Contributed Oral Session 2: Reasoning, Evaluation, and Agentic Systems

Reasoning, protocol interpretation, benchmark design, evaluation, and agentic systems for clinical-trial design and evidence generation.

15:45 – 16:20

Invited Talk 5: Pharma AI, Clinical Development, and Evidence Generation

Speaker to be confirmed from GSK.

16:20 – 16:50

Closing Panel: From Patient World Models to Reliable Clinical Evidence

Moderated by Raja Shankar. Discussion of trustworthiness, reliability standards, data access, benchmarking, regulatory evidence, and responsible deployment.

16:50 – 17:00