Dyania Health Runs Synapsis AI on Hospital-Owned GPU Systems

Dyania Health and NVIDIA announced on November 13, 2026 that Synapsis AI is running on hospital-owned NVIDIA accelerated computing, with an initial Cleveland Clinic study covering 7,812 aortic-valve replacement patients. The collaboration is designed to review records across patient populations without moving them outside health-system networks.

Dyania Health describes Synapsis AI as a clinical reasoning engine that reads years of notes, operative reports, imaging reports and laboratory results, then answers clinical questions with evidence linked to the chart. Its outputs are clinical signals intended to show care teams which patients need attention and why; clinicians review the evidence and make every decision.

On-Premises Clinical Reasoning

The deployment uses NVIDIA AI Enterprise across the software stack. Dyania trains its proprietary clinical models with NeMo, then uses TensorRT and TensorRT-LLM to optimize inference on hospital GPU servers. Inference therefore stays within the hospital’s private network instead of sending patient records to an external environment.

NVIDIA said the system remains assistive: it surfaces evidence from medical records that clinicians must confirm and act on. That distinction matters because the deployment automates chart review and signal detection, not the clinical decisions that follow.

The companies are targeting a manual bottleneck in hospital research and care management. Important details often sit in narrative text rather than structured fields, limiting the charts staff can review for registries, outcomes studies and predictive models. Synapsis AI applies longitudinal review across a health system’s population, with potential uses including care-gap detection, observational research and clinical-trial matching.

Cleveland Clinic Valve Study

The study examined patients who received aortic valve replacements between 2005 and 2021, reviewing up to 16 years of care per patient. Synapsis AI answered 88 clinical questions for each patient covering valve characteristics, co-existing conditions, laboratory trends, medications, follow-up ultrasound measurements and subsequent clinical events. Much of that history was contained in narrative notes and echocardiogram reports.

NVIDIA said the platform completed chart review across the full cohort, work that would have taken clinicians years to perform manually. The resulting dataset was used to train a predictive machine-learning model that estimates valve-failure and reintervention risk at three, five and 10 years and revises those estimates with each new ultrasound.

Dyania reported that implanted valve type was the strongest determinant of how quickly a valve deteriorated, while age and other medical conditions influenced whether and when a second procedure occurred. The analysis also examined how follow-up information, such as post-surgery ultrasounds, can substantially raise predictive accuracy around future interventions.

“Using technology to bring together and analyze information that can help us predict the duration of implanted heart valves is a promising step towards enhanced outcomes and more personalized care for patients,” said Lars G. Svensson, chief of Cleveland Clinic’s Heart, Vascular & Thoracic Institute.

The study demonstrates dataset construction and risk prediction, not improved patient outcomes. Dyania says the tool is intended to inform care and requires external clinical validation before broader clinical reliance.

Deployment Roadmap

Dyania’s collaboration announcement says the companies plan to pursue health-system deployments in the United States and internationally, publish joint case studies and integrate Synapsis AI with NVIDIA’s healthcare software stack. Technologies under evaluation include NVIDIA Confidential Computing for training and inference, NVIDIA Dynamo for distributed inference serving and Multi-Instance GPU for partitioning GPUs across concurrent clinical workloads.

The companies are also evaluating scaling to multiple Blackwell Ultra GPUs as processing moves from batch reviews toward near-real-time clinical insight at the point of care. These remain evaluation goals rather than completed deployments. For health systems, the practical question is whether externally validated models can turn population-scale record review into reliable clinical action while clinicians retain control of care decisions.