RESEARCH PREVIEW — NOT FOR CLINICAL USE. EchoReview AI is an investigational workflow tool. Output is a preliminary, non-diagnostic impression intended to support cardiologist review for research and quality-improvement purposes only. Not FDA-cleared. Do not use for patient care decisions. Do not upload identified PHI without an executed BAA.
Non-clinical shadow pilot · ~2 hours / week

Request Advisor Access

A 90-day shadow study for critical access hospitals, rural cardiology programs, and cardiologist advisors. AI output runs alongside your normal read — never in place of it — so there is zero change to patient care. Expect roughly 2 hours per week of your time during the pilot.

Shadow-mode only
Parallel reads; no clinical reliance on AI output.
Co-authored abstract
ASE / ACC-ready QI abstract with your name on it.
Advisor equity
Founding cardiologist advisors receive equity + design input.

Structured 30 / 60 / 90-day workflow

A concrete cadence for your research team — from IRB and BAA setup through shadow-read validation and outcome reporting. All phases run as non-clinical QI/research; no AI output is used for patient care.

Days 0–30

Stand-up & onboarding

Governance, access, baseline metrics

  • Execute BAA + Data Use Agreement
  • Site PI submits Pilot Kit protocol to local IRB
  • Provision org tenant, invite 2–5 users, enable 2FA
  • Capture baseline: avg. read turnaround, weekly echo volume, after-hours backlog
  • Train 1 sonographer + 1 cardiologist on de-identified upload flow
Deliverable: Signed agreements, IRB acknowledgement, baseline metrics worksheet
Days 31–60

Shadow-read & calibration

Parallel reads, no clinical reliance

  • Upload ≥ 50 de-identified studies/week
  • Cardiologist issues normal read; logs AI preliminary impression separately
  • Track concordance, false-positive, and false-negative rates by view
  • Weekly 30-min review call with EchoReview clinical team
  • Log all UX friction in shared issue tracker
Deliverable: Concordance report (n ≥ 200 studies), UX punch-list, mid-pilot readout
Days 61–90

Outcomes & decision

Evidence package, go / no-go

  • Measure simulated turnaround impact vs. baseline
  • Survey clinician trust + workflow fit (validated NASA-TLX subset)
  • Draft co-authored QI abstract (ASE / ACC submission-ready)
  • Site PI + EchoReview review safety log, audit trail, addendums
  • Decision: extend, expand to second site, or close-out
Deliverable: Final pilot report, abstract draft, renewal or close-out memo

Success criteria the research team agrees to up front

  • ≥ 200 de-identified studies uploaded across the pilot
  • AI preliminary impression returned in < 90 seconds (median)
  • ≥ 80% concordance with cardiologist read on normal vs. abnormal triage
  • Zero PHI incidents; 100% of uploads pass de-identification check
  • Cardiologist sign-off completed on 100% of reviewed studies
  • Net Promoter Score ≥ +20 from clinician users at day 90

Prefer a shorter engagement? The same framework compresses into a 30-day feasibility sprint (onboarding + 100 shadow reads) or a 60-day evaluation (drops the outcomes phase). Indicate your preferred length in the notes below.

Hospital

Echo program

Primary contact

Anything else?

By submitting, you acknowledge this is a research/QI pilot and EchoReview AI is not FDA-cleared for clinical use. PHI must not be uploaded until a BAA is executed.