Cleerly

The product is AI analysis of coronary CT angiography. Cleerly Labs quantifies and characterizes atherosclerotic plaque and stenosis, and Cleerly ISCHEMIA derives a machine learning estimate of vessel level ischemia from the same imaging. There is no scanner or services layer; the company sells the algorithmic reading of a scan the customer already acquired. AI is the whole offering.

Decision support with published limits, and no published threshold or path after an error. The Indications for Use state that Cleerly Labs is an interactive tool for trained professionals that does not replace a qualified practitioner's judgment, warn that interpolated views can make tissue look healthy where small pathology is present, and state that ISCHEMIA is a diagnostic aid used by an interpreting provider, with patient management decisions not to rest on it alone.

Results reach clinicians as a physician report. The company does not publish the cutoff at which ISCHEMIA calls a vessel likely ischemic, whether and how Cleerly staff review analyses before reporting, or what happens when a result is wrong.

The clinical validation is published and specific: Cleerly ISCHEMIA was derived and validated using data from the CREDENCE and PACIFIC trials, and a PACIFIC sub-study reported high diagnostic accuracy against PET, FFR-CT, SPECT, and invasive FFR. The company states the ISCHEMIA prediction is based on coronary lesion morphology and plaque characteristics, and cites a training base of millions of images from more than 40,000 patients. What is less transparent is the model architecture itself and independent head to head benchmarking against other plaque analysis vendors. Strong on clinical derivation, lighter on model internals.

A short chain for the models, with the hosting layer unnamed. Cleerly builds its own plaque and ischemia models, cleared in its own name, so no outside model provider sits between a CT study and a result. The privacy notice confines the services to the United States and its territories and commits not to attempt re-identification of de-identified data, and it says de-identified or aggregated patient information may be used for analytics and product insight.

The trust center lists third party management as a control domain. Not published on the public pages: the cloud host, a subprocessor list, and whether submitted studies feed model development as distinct from analytics. An in house, cleared chain with residency stated.

Prospective, multicenter validation against the invasive reference, plus registry work on outcomes. Cleerly ISCHEMIA was validated in CREDENCE, a prospective multicenter trial of 612 stable patients referred for invasive angiography, with index tests read blind by core laboratories and invasive FFR as the reference: per vessel sensitivity 75.9 percent (167 of 220) and specificity 83.4 percent (521 of 625) in the company's 510(k) summary (K231335), and 76.2 and 85.2 percent across 582 patients and 1,521 vessel territories when US and non-US cohorts are pooled.

A post-hoc analysis of the PACIFIC trial compared it with FFRCT, PET and SPECT against invasive FFR, and the international CONFIRM2 registry links quantified plaque burden to risk. The company's claims that ISCHEMIA was more accurate than FFRCT and stress testing and was the only non-invasive ischemia test prognostic of later events come from its own analyses of CREDENCE and PACIFIC. Much of this work was generated with the company's clinical network and is peer reviewed and multicenter. The plaque quantification outcome claims rest on registry rather than randomized evidence.

The public privacy notice deliberately excludes patient data, so it offers no retention schedule, no deletion commitment and no model training terms for the asset the product actually handles, the coronary CT study. The one statement that does reach patient data points the other way: de identified or aggregated patient information may be used alongside customer personal information to perform analytics and gather product insight.

De identification is a mitigation rather than an exclusion, so submitted studies do contribute to product improvement in some form. There is a stated commitment not to attempt re identification of de identified data, and the services are confined to the United States and its territories. Nothing published says how long submitted studies persist after analysis, whether they inform model development, or what deletion can be required on termination.

The company processes patient data for customers and does not state business associate status in public material. Cleerly's privacy notice says it does not cover protected health information processed on behalf of customers, and a separate consumer health privacy policy addresses Washington, Nevada and Connecticut consumer health data laws.

The trust center offers SOC 2 Type 2 and HITRUST reports and a device security disclosure (MDS2), but neither the term business associate nor an agreement appears on the public pages. Acting for customers on their patients' data is what a business associate does, but saying so is the vendor's to do. A role implied by the scoping sentence, with no status or agreement stated.

Certifications are named and the reports can be downloaded without asking. Cleerly's public trust center (trust.cleerlyhealth.com) is open without login or approval and offers a SOC 2 Type 2 report (uploaded September 2026) and a HITRUST document, along with a Manufacturer Disclosure Statement for Medical Device Security (MDS2) for Cleerly Labs and ISCHEMIA, a redacted information security incident response plan and a security document packet.

It enumerates controls across twelve domains, including governance and risk, third party management, access control, network and data security, application security, security monitoring, and response and recovery. Named certifications presented as retrievable artifacts. The page itself does not name the HITRUST assessment type or the SOC 2 audit period.

Each product's position is stated and the lead clearance can be found. Cleerly ISCHEMIA was cleared on 8 September 2023 (K231335; 21 CFR 870.2200, adjunctive cardiovascular status indicator) as an automated machine learning based decision support tool and diagnostic aid for patients analyzed with Cleerly Labs, and the company states that patient management decisions should not rest on it alone.

Cleerly Labs, its web based plaque and stenosis analysis software for CCTA from any CT scanner, was cleared in 2020 and is labeled as not intended to replace a qualified practitioner's judgment, with a warning that interpolated views can make tissue look healthy where small pathology exists. Both indications are published on the company's Indications for Use page. Cleerly COMPARE, for comparing serial scans, is marketed alongside them, and its clearance is not identified on the indications page.

Results by group are published for geography and, per the company's publications, for sex and age; race is described, not validated. Cleerly's 510(k) summary for ISCHEMIA (K231335) reports sensitivity and specificity separately for US patients (149 patients, 285 vessel territories: 79.5 and 82.5 percent) and non-US patients (433 patients, 1,236 territories: 75.5 and 85.8 percent), with counts and intervals.

The company's publications include diagnostic performance of the ischemia algorithm by sex and age, a CONFIRM2 analysis in which quantitative plaque carries higher relative risk in women, and plaque distributions by age, sex and self reported race in about 30,000 patients; most of this work is company sponsored with disclosed interests. The sex and age results sit in journal papers rather than on the company's pages, and no performance comparison by race or body habitus is published. No AI governance framework or bias policy is published. Results within groups, short of a published comparison across the groups where coronary CT is most at risk.

An error rate with its method and denominator is published for the lead ischemia product; nothing else stands behind the output. Cleerly's own 510(k) summary for Cleerly ISCHEMIA (K231335, cleared 8 September 2023) reports validation in CREDENCE, a prospective multicenter trial in which core laboratories read the index tests blind against invasive FFR: per vessel territory sensitivity 75.9 percent (167 of 220) and specificity 83.4 percent (521 of 625) in the validation half, and pooled across cohorts from the US and elsewhere (582 patients, 1,521 vessel territories) sensitivity 76.2 percent and specificity 85.2 percent, with per patient sensitivity 86.6 and specificity 69.8 percent.

That is a trial population result for ischemia estimation, not performance in any one practice, and it does not cover plaque quantification. No warranty, indemnity or remediation commitment is published.

Cleerly operates as a CCTA analysis service that returns a physician report, sitting in the cardiac imaging and reporting pathway rather than integrating deeply with the EHR. Specific PACS, cardiology information system, and EHR connectors are not enumerated in the materials reviewed, so integration is described at the workflow level rather than through a published connector list.

A cloud analysis service confined to the United States. Hospitals and imaging centers submit coronary CT studies to Cleerly's web based service and receive a physician report; the privacy notice states that the services are confined to the United States and its territories, which settles where data rests at the country level. The site names no cloud host or regions within the US, and says nothing of tenant isolation or how long studies persist after analysis.

No price is published; payer coverage is documented. Cleerly publishes billing guidelines, coverage pages and a payer policy lookup tool: AI plaque analysis of coronary CT carries Category I CPT code 75577 from January 2026, ISCHEMIA is billable under Category I code 75580, and Medicare contractor and commercial payer policies are reported to cover more than 86 million lives.

Those describe what a provider can bill, not what Cleerly charges: no per study price, license structure or volume terms are published, and the route in is a demo. No price, with how the product is bought and paid for discoverable.

Coverage is named for coronary CT, with validation behind the ischemia product. Cleerly Labs analyzes CCTA from any CT scanner for patients with known or suspected coronary artery disease, and ISCHEMIA estimates vessel level ischemia as a diagnostic aid; COMPARE tracks change between scans. ISCHEMIA was validated in stable patients referred for non-emergent invasive angiography at 23 centers in and outside the US, with results reported for both.

What is not published is where the plaque quantification is validated by setting (screening, emergency, post-intervention) and which patients or scans fall outside it, beyond the warning about interpolated views. The narrow scope is not the limit; the limit is how much of it is validated with stated exclusions. Named coverage with validation behind part of it.