NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting
Researchers introduce NOAH, a time-aware generative transformer trained on 559 million MIMIC clinical events to forecast multimodal patient trajectories.
NOAH is a task-agnostic, time-aware generative transformer trained on over 559 million clinical events from 431,000 hospital visits by 299,000 patients across the MIMIC dataset family. It uses bidirectional time integration and a variational latent space to model the stochastic evolution of patient states, natively processing medical images, time-series signals, categorical events, and structured or unstructured clinical records. The model supports autoregressive forecasting with optional time control, zero-shot classification, and counterfactual intervention simulation, with strong probing performance across clinical outcomes, 15 ICD chapters, and 29 comorbidities.
- Bidirectional time integration and variational latent space capture stochastic clinical trajectories.
- Natively handles medical images, time-series signals, categorical events, and clinical text.
- Enables zero-shot classification and counterfactual intervention simulation.
- Strong probing results across 15 ICD chapters and 29 comorbidities.
- AI models
- NOAH
From the original article
1 min read at huggingface.co
The digitization of healthcare has generated vast, longitudinal, and multimodal patient records over a lifetime, yet fully exploiting these data to represent and predict patient state trajectories remains a critical challenge. Current AI models often struggle to capture the complex, irregular temporal dynamics and inherent stochasticity of real-world multimodal patient data.
By Tobias Susetzky, Raphael Rehms, Dmitrii Seletkov · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.