Dyania Health speeds patient record review with AI
Dyania Health, a New Jersey-based clinical AI company, has developed Synapsis AI to analyze patient histories across physicians’ notes, reports and lab results. The system connects findings recorded years apart and produces clinical signals traceable to their sources, helping care teams identify patients who need attention and understand why. Clinicians must review the evidence and make every decision.
The platform runs on NVIDIA-accelerated computing inside a health system’s own firewall, allowing records to be processed onsite without patient data leaving the hospital. Dyania uses NVIDIA NeMo libraries to build and train its models, then TensorRT and TensorRT-LLM to optimize performance on hospital GPU servers. The approach aims to reduce manual chart review and give clinical teams more time with patients.
Cleveland Clinic used Synapsis AI to support a study of more than 7,800 aortic valve replacement patients between 2005 and 2021. By examining records, including echocardiograms collected after surgery, the platform helped build a predictive model of valve deterioration and reintervention risk. It completed chart review that would have taken clinicians years by hand. Other potential applications include identifying clinical trial candidates, finding care gaps in cardiology and oncology, and populating clinical registries.