NVIDIA Highlights AI Tool for Faster, More Complete Patient Record Review

Dyania Health is using Synapsis AI to analyze years of patient records and surface clinical signals for care teams, according to NVIDIA. The system is designed to reduce manual chart review while keeping clinicians responsible for reviewing evidence and making decisions.
- Dyania Health's Synapsis AI analyzes notes, reports and lab results across patient records.
- The system runs inside a health system's firewall on NVIDIA-accelerated computing.
- Cleveland Clinic used it to study more than 7,800 aortic valve replacement patients.
- Clinicians review the evidence and make every decision.
AI searches across fragmented medical histories
Hospitals hold decades of patient information in physicians’ notes, operative reports, imaging and pathology reads, discharge summaries, lab results and other records. Because much of this information is written as free text, understanding a patient’s full history can require clinicians to read through years of charts.
Dyania Health, a New Jersey-based clinical AI company, developed Synapsis AI to address that challenge. NVIDIA describes the platform as a clinical reasoning engine that works across every note, report and lab result in a patient’s record. It connects findings that may be separated by years and uses them to answer clinical questions in a way similar to a specialist reviewing a chart.
The platform produces clinical signals that can be traced to their sources in the record. These signals tell care teams which patients may need attention and why. Clinicians then review the evidence, confirm it and decide what action to take.
Processing stays inside the hospital
Synapsis AI runs on NVIDIA-accelerated computing inside a health system’s own firewall. According to NVIDIA, this allows an entire health system’s patient records to be processed onsite, so the data does not leave the hospital or get shared outside it.
Dyania builds and trains its clinical models with NVIDIA NeMo open libraries. It uses NVIDIA TensorRT and TensorRT-LLM to optimize the models for faster and more efficient operation on a hospital’s own GPU servers.
NVIDIA presents Synapsis AI as an assistive system rather than an autonomous decision-maker. The tool surfaces evidence from medical records, but a clinician must still confirm the information and act on it. Moving part of the chart review process to an AI system could give clinical teams more time to spend with patients, while the firewall-based design addresses the handling of sensitive patient data.
Cleveland Clinic study shows a practical use case
Cleveland Clinic used Synapsis AI in a study of more than 7,800 aortic valve replacement patients treated between 2005 and 2021. The system reviewed each patient’s record, including echocardiograms added in the years after surgery.
It used that information to build a predictive model of valve deterioration and reintervention risk at the three-, five- and ten-year marks after an aortic valve replacement procedure. NVIDIA says the platform completed chart review across the full cohort, a task that would have taken clinicians years to complete by hand.
“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 Dr. Lars Svensson, chief of the Heart, Vascular & Thoracic Institute at Cleveland Clinic.
NVIDIA says the same approach could support other tasks in which answers are contained in medical records, including finding patients eligible for clinical trials, closing care gaps in cardiology and oncology, and populating clinical registries. For healthcare users, the announcement points to AI being used to organize existing information and prioritize clinical attention, while care teams remain at the center of decisions.


