ModelsParticula-Healthcare
Clinical extraction,inside the firewall.
Particula-Healthcare extracts diagnoses, medications, dosages, and codes from clinical notes, with a built-in PHI redaction pass. It runs on-prem inside your compliance boundary, so protected health information never crosses the wire.
ON-PREM · PARTICULA-HEALTHCARE
$ POST /v1/extract · discharge_summary.txt
→ particula-healthcare · PHI redacted
→ "diagnosis": "I10 hypertension"
→ "medication": "lisinopril 10mg"
✓ 200 · 55 ms · zero cloud calls
ready
PARTICULA-HEALTHCARE · ON-PREM · ZERO TELEMETRY
What it doesSee it on your data
Diagnoses, meds, codesConditions, medications, dosages, and ICD-10 codes from discharge summaries, progress notes, and referrals.
PHI stays insideA redaction pass runs before anything is logged or stored. Names, dates, and identifiers never leave the extraction boundary.
HIPAA-ready deploymentOn-prem architecture docs, data-flow diagrams, and audit support for your compliance review. Attestation follows your environment.
Grounded to the noteEvery extracted field carries a span pointing back to the source sentence, so clinicians can verify instead of trust.
Spec sheetCompare all six
Context window32K tokensA full discharge summary with history fits in one request.
Median latency55 ms medianBatch 1 on the reference single-GPU deployment. Our own measurement: the shipped harness reproduces it on your hardware.
InterfaceOpenAI-compatible RESTServed by vLLM, deployed with Docker Compose or Helm. Drop-in for existing OpenAI client code.
Hardware1× 48 GB GPUL40S or A6000 class, on-prem. Sizing reviewed before the pilot.
Fine-tuningLoRA on your dataTuning jobs are included with Enterprise. A few hundred labeled examples from your pipeline is usually enough to move the needle.
How deployment worksStart at step 01
01Discovery call
30 minutes, no slides. Your task, your data shape, and the security constraints around it. If this model is the wrong fit, we say so on the call.02Pilot install
Containerized deployment to staging in your VPC or on-prem, on the same stack as Lumen and Notetaker. The eval harness runs on your data and the numbers go into the pilot agreement.03Production rollout
Runbook handoff, operator training, and 90 days on call. After that it is yours to operate, no vendor dependency.More modelsAll six models
Request a demo
“Bring a hundred real examples from your pipeline. We run the model on them live, the harness scores the output in front of you, and you decide with numbers instead of a sales deck.”
Sebastian Mondragon, Founder of Particula Tech
Request a demo30 minutes · no sales deck