Analyzing 100k genomes dragged at 8 hours per case. GPU nodes cut processing to 40 minutes, unlocking the program’s scale.
A genomic medicine program within a major healthcare system aims to sequence 100,000 patient genomes and link them to full electronic health records for research and clinical use.
Standard genomic analysis on high-performance computing clusters faced severe bottlenecks, with variant calling taking up to eight hours per genome...
“Our goal is to enable genomic research in the medical system in a way that links the data to the full electronic health records of a patient. To link the entire depth, history, and every feature that exists in electronic records that often can’t really be obtained from biobanks.”
Academic medical center for patient care, medical education, and biomedical research.
NVIDIA is a technology company that specializes in semiconductors, graphics processing units, and artificial intelligence for applications in data centers, gaming, and more.
Related implementations across industries and use cases
Iterating on spatial data took 10 hours per run. GPU acceleration cut this to 3 minutes, enabling scale to 100 million cells.
Legacy CPUs bottlenecked genome analysis at 50 hours per sample. GPU pipelines cut this to 31 minutes—97x faster.
Clinicians spent 50 hours per case sifting data. AI now ranks disease risks, cutting diagnosis time from 7 years to 1 month.
Manual triage meant urgent faxes sat for days. AI now routes millions of documents to 1,200+ destinations in seconds.
Manual segmentation took 20 minutes, delaying care. AI now analyzes hemorrhages in seconds, aiding decisions across 23 regional sites.
Experts spent 15 minutes pulling data from scattered systems. Natural language prompts now generate detailed reports instantly.
Lab supply orders were handwritten in notebooks. Digital ordering now takes seconds, saving 30,000 hours for research annually.