Dyania Health's Synapsis AI helped Cleveland Clinic study more than 7,800 heart valve patients, and Nvidia said the chart review would have taken clinicians years to do by hand.
Key Takeaways
- Cleveland Clinic used Synapsis AI to support a study of more than 7,800 aortic valve replacement patients
- Synapsis AI runs inside a health system's own firewall, so patient data never leaves the hospital
- Clinicians review the evidence and make every decision
- Dyania Health is a New Jersey-based clinical AI company that built the tool
Nvidia announced in a Nov. 13 blog post that health systems and startups are using AI to support clinicians, streamline workflows and improve patient care. Nvidia said its technologies provide the compute behind the applications, while clinicians stay at the center, reviewing AI outputs and guiding decisions.
Also Read: AWS Pledges $100M Of AI To Bring Health Care To Poorer Communities
How Synapsis AI Works
Hospitals hold decades of patient history, most of it written as free text. That includes physicians' notes, operative reports, imaging and pathology reads and discharge summaries.
Synapsis AI is a clinical reasoning engine. It works across every note, report and lab result in a patient's record and connects findings that may be years apart. The output is a set of clinical signals, each traceable to its source in the record, that tells care teams which patients need attention and why.
Nvidia said the tool is assistive. It surfaces evidence that a clinician must still confirm and act on.
Keeping Patient Data Inside the Hospital
Synapsis AI runs on Nvidia-accelerated computing inside a health system's own firewall. The entire health system's patient records can be processed onsite, so patient data is never shared and never leaves the hospital.
Dyania builds and trains its clinical models with Nvidia NeMo open libraries. It then uses Nvidia TensorRT and TensorRT-LLM to run them faster and more efficiently on the hospital's own GPU servers.
The Cleveland Clinic Study
Synapsis AI reasoned across each patient's record, including every echocardiogram added in the years after surgery. It used that information to build a predictive model of valve deterioration and reintervention risk.
| Detail | Value |
|---|---|
| Patients studied | More than 7,800 aortic valve replacement patients |
| Study period | Between 2005 and 2021 |
| Risk checkpoints | Three, five and ten years after the procedure |
| Risks predicted | Valve deterioration and reintervention |
Nvidia said the platform completed chart review across the full group 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 said the same approach can be applied to any healthcare challenge where the answer sits inside the medical record. Examples it gave include identifying patients eligible for clinical trials, closing care gaps in cardiology and oncology, and populating clinical registries.
Read Next: Nvidia Gives Banks And Hospitals More Control Over AI Transcripts
Originally published on Fathom News.
