← Back
NVIDIA Blog

AI Is Helping Care Teams Get Patients the Right Care, Sooner

•10 min read•
#compute#llm#nvidia
Level:Advanced
For:AI Engineers
✦TL;DR

Dyania Health’s Synapsis AI is a clinical reasoning engine that ingests decades‑long free‑text patient records to surface evidence‑based clinical signals, running entirely on NVIDIA‑accelerated compute within a hospital firewall. The system was used at Cleveland Clinic to process over 7,800 aortic valve replacement records from 2005‑2021 and generate predictive risk models for valve deterioration at three‑, five‑ and ten‑year horizons. By leveraging NVIDIA NeMo, TensorRT and TensorRT‑LLM, Synapsis AI delivers on‑premise inference that keeps data local while dramatically reducing manual chart‑review time.

⚡ Key Takeaways

  • Processed >7,800 aortic valve replacement patient records (2005‑2021) to build multi‑year risk predictions.
  • Built with NVIDIA NeMo open libraries and optimized with NVIDIA TensorRT and TensorRT‑LLM for on‑premise GPU servers.
  • Trade‑off: retains full data privacy by staying inside the hospital firewall, but still requires clinician verification of AI‑generated signals.
  • Integration point: deploy Synapsis AI on internal GPU clusters using the same NVIDIA stack (NeMo → TensorRT → TensorRT‑LLM) to run inference locally.
  • Limitation: the tool is assistive only; clinicians must review and act on the surfaced evidence.
💡 Why It Matters

Engineers can now deliver high‑throughput, privacy‑preserving clinical analytics without moving PHI to the cloud, accelerating research and care pathways while keeping clinicians in the decision loop.

✅ Practical Steps

  1. Build and train clinical models with NVIDIA NeMo, then convert them with TensorRT and TensorRT‑LLM for deployment on on‑premise GPUs.
  2. Deploy the optimized model inside the hospital’s firewall to run Synapsis AI on internal patient record stores, ensuring data never leaves the premises.
  3. Have clinicians review the AI‑generated clinical signals before making care decisions.

Want the full story? Read the original article.

Read on NVIDIA Blog ↗

More like this

Introducing Gemini 4 Neon

Google DeepMind•#llm

DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency

Hugging Face Blog•#llm

AI’s GPU focus meets a CPU reality check at Dell and AMD

SiliconANGLE AI•#agents

NVIDIA RTX Spark Compact Desktops Out Now

NVIDIA Blog•#compute

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING