Product · Real-time chronic care monitoring

Vigil —Always watching between visits.

Vigil streams biometric signals from patient devices through Holoscan, detects deterioration via GPU inference on Jetson and cloud GPUs, and surfaces clinician-reviewed intervention recommendations grounded in the patient's Scribara encounter history.

Physical AI layer — extends the Scribara platform to the patient's home

HoloscanJetson OrinNVIDIA InceptionCMS RPMHIPAACGM · BP · SpO2
Holoscan sensor stream<500 ms
Jetson anomaly detecton-device
NeMo exacerbation risk24–72 hr
Encounter contextScribara Labs
The problem

Why Vigil exists

Specialty patients with CHF, diabetes, psoriasis, and COPD deteriorate between visits. By the time a referral reaches the specialist, the patient is in the ED. Existing RPM platforms produce context-free alerts that nurses triage without specialist insight.

  • Holoscan real-time multi-sensor pipeline (CGM, BP, SpO2, wearables)
  • Jetson Orin on-device inference — PHI stays at the clinic [ASPIRATIONAL]
  • NeMo 24–72-hour exacerbation prediction, grounded in encounter history [ASPIRATIONAL]
  • CMS RPM billing export (CPT 99453/99454/99457/99458) built in
01 / Stream

The patient's signal, always.

Holoscan ingests CGM, blood pressure, SpO2, and wearable data in real time — multi-sensor, time-aligned, sub-500 ms latency.

02 / Detect

Knows when something shifts.

TensorRT-compiled anomaly models (on Jetson at the edge or L4 in the cloud) score every patient's signal against their personal baseline — not a population threshold.

03 / Alert

Context, not just numbers.

Alerts are enriched with the patient's last Scribara encounter — last codes, medications, imaging findings — and a NeMo-drafted intervention recommendation. [ASPIRATIONAL]

04 / Intervene

One tap to act.

Approved recommendations trigger Authra for medication auths and Codexa for CCM billing codes — closing the loop without leaving the workflow. [ASPIRATIONAL]

Capabilities

What Vigil does

Multi-sensor streaming

Holoscan pipeline ingests CGM, blood pressure, SpO2, and wearable signals from multiple concurrent patients.

Personalized anomaly detection

Per-patient baseline models flag deviations; TensorRT-compiled for sub-500 ms inference.

Edge inference

Jetson Orin processes sensor streams on-device at the clinic — PHI stays local. [ASPIRATIONAL]

Encounter-grounded alerts

Every alert enriched with the patient's last Scribara encounter — notes, codes, medications, imaging.

Exacerbation prediction

NeMo models forecast CHF, diabetes, and COPD acute events 24–72 hours in advance. [ASPIRATIONAL]

RPM billing automation

CMS CPT 99453/99454/99457/99458 billing codes logged automatically — turns RPM into revenue.

GPU-essential

Why accelerated compute is required

Holoscan multi-sensor stream processing across dozens of concurrent patients requires GPU-parallel operations. TensorRT anomaly inference must return in under 500 ms for life-critical signals. NeMo exacerbation models run as continuous inference, not batch jobs. CPU cannot meet any of these requirements.

  • Holoscan SDK for clinical-grade real-time sensor streaming
  • Jetson Orin on-device inference <100 ms [ASPIRATIONAL]
  • TensorRT continuous anomaly model on L4 / A100 cloud
  • NeMo exacerbation training on H100/H200
Holoscan pipelinestream
Jetson Orin edgeon-device
TensorRT anomaly<500 ms
NeMo prediction24–72 hr
Impact

What it moves

0
Max alert latency on GPU
0
Advance exacerbation warning [ASPIRATIONAL]
0
$/patient/mo CMS RPM reimbursement
0
US chronic disease patients eligible for RPM
The ecosystem

Works with the rest of Scribara

Vigil uses encounter history and feeds monitoring outcomes back to the platform.

Nexar

Continuous monitoring outcomes compound population risk models

Explore

Augur

Synthetic biometric time-series data augments Vigil's training corpus

Explore

Orbis

Enrolled trial patients continue to be monitored by Vigil

Explore
Answers

Frequently asked

CGM (Dexcom, Abbott Libre), blood pressure (Withings, Omron), SpO2, and common wearables via HL7 FHIR Observation resources. Device integration APIs are [UNKNOWN] — confirmed at implementation.

Yes — the Jetson edge node is optional. Holoscan and TensorRT inference run equally well on cloud GPU (L4/A100) for clinics without an on-prem device.

Vigil logs the required device-supply, monitoring, and care-management events and generates CPT 99453/99454/99457/99458 billing records automatically for export to your billing system.

Your patients, covered between visits.

See Vigil monitoring a chronic cardiology panel in a live demo.