Software for adults (18 and over) in hospital critical care that estimates the likelihood of hemodynamic instability in the next 8 hours and flags patients at low risk of deterioration. Predictions are for reference only; no treatment decision should rest on them alone.
FDA: 510(k) K200717 CLEWICU System, January 2021 (confirmed)
FDA: 510(k) K233216 CLEWICU System, January 2024 (confirmed)
CE: no CE marking found in public sources (to confirm)
Lilly et al., Chest 2024 (retrospective, CLEW co-authors): on 3,191 external ICU stays, alerts caught 61% of instability events; 22% of alerts were true.
FDA file K233216 (retrospective, 6,534 and 5,069 stays): 63-69% of events caught; 10-12% of alerts true.
No independent peer-reviewed study found by AI4Hospitals.
No named current customer site found. Study sites were UMass Memorial and WakeMed (United States); Sheba and Tel Aviv Sourasky (Israel) used it for COVID-19 tele-ICU in 2020 as an investigational device (vendor-declared).
– Evidence is retrospective and vendor co-authored; no independent study found.
– Many alerts are false positives: 22% of alerts were true in Lilly 2024, 10-12% in FDA data.
– It catches about 6 in 10 instability events; a missing alert does not rule out deterioration.
– No CE marking and no named current customer site found; use outside the US is not documented.
This profile is not medical advice or an endorsement. Hospitals should perform their own due diligence (regulatory compliance, GDPR, cybersecurity, integration, local clinical validation). How we evaluate
Every profile documents the precise indication, regulatory status, vendor-supported and independent evidence, real-world deployment, limits and dated sources.
A independent systematic review or prospective multicentre study · B at least one independent peer-reviewed study · C peer-reviewed, vendor-supported · D vendor claims only.
Vendors, authors and clinicians can request a correction. Corrections are dated on the profile.
