Clinical Trials AI
I

Inato

Inato connects clinical trial sponsors with research sites and helps site staff find patients for studies, across more than 6,000 sites in more than 50 countries and more than 25 sponsors, Sanofi, Amgen, Pfizer, Lilly and AstraZeneca among them. Sponsors use the platform for feasibility, site selection and enrollment tracking. A site can upload a patient's chart or pull records from a connected EHR and run AI prescreening against a study's inclusion and exclusion criteria; staff see an assessment for each criterion with a rationale and a source in the record, and the site team decides whom to contact or move to screening. Sites can also share aggregate patient access figures with sponsors before selection, and multisite networks track trial opportunities and potential participants across locations.

Pantheon Clinical Research used Inato to assess more than 60 potential participants in one weight loss trial, cutting review from about three hours to five minutes per patient and saving 181 hours and $4,521 in coordinator labor. Sanofi built prescreening workflows with Inato and its sites, and a COPD study case reports faster enrollment and fewer nonperforming sites. NextGen, CRIO and eClinPro connect the tools to clinical and research records, and CRIO sends patient data to Inato and takes screening results back.

Signup and prescreening are free for research sites. Kourosh Davarpanah and Liz Beatty cofounded the company in 2016; it operates in France and the United States and won a 2026 Fierce AI Innovation Award for clinical trial operations.

AI Health Index verifiedNovember 20, 2026
Compare Inato with other vendors
Founded
2016
Headquarters
Paris, France
Website
www.inato.com/
Categories
clinical-trials-ai
Indexed Products
Inato Marketplace, AI Patient Pre-Screening, Patient Access reports, Site Networks, Sponsor Feasibility and Site Selection
Buyer Segments
Pharmaceutical and biotechnology sponsors, Contract research organizations, Independent clinical trial sites, Multi-site research networks
Assessment

Capability Axes

An AI Health Index grade measures what a buyer can verify from public sources on the date shown. It is not a rating of how good the product is. A vendor can build an excellent system and grade low on an axis because it publishes nothing an outsider can check. How grades read

AI Capability
BB on AI CentralityThe model is the engine of a core module. The platform carries other value, but this capability does not exist without it.
Vendor Published

The prescreening tool compares patient records with inclusion and exclusion criteria across active studies and gives staff a per criterion assessment, a rationale and a reference to the supporting chart material. The same work lets a site show sponsors it can reach patients who match a trial's requirements.

Inato also runs a marketplace where sponsors advertise studies and sites present their capabilities, apply and manage communications, and feasibility and site selection serve sponsors apart from patient screening. Model based matching drives the chart review feature and feeds the patient access data used elsewhere on the platform.

BB on Autonomy and Oversight ModelThe oversight structure is described and one part is missing, commonly the threshold at which the system stops or what happens after it is wrong.
Vendor Published

Site staff review the rationale and source behind each eligibility assessment and decide which patients move to contact or full screening. A site can turn on automatic chart import and receive prescreening results back in its CRIO system; those automations update what the team sees and leave enrollment decisions with clinical staff, and the handoff to the research coordinator is laid out step by step. Inato also processes uploaded records for studies outside its marketplace. No uniform rule covers how the software treats unresolved criteria, missing data or conflicting evidence across trials.

BB on Model and Technology TransparencyThe approach or the suppliers are named without the version and update discipline behind them. Naming a supplier is the entry to this band both here and on Model Supply Chain Disclosure, which ask different questions of the same disclosure: who receives the data, and what produces the output.
Vendor Published

Google Gemini runs inside Inato's Google Cloud projects for eligibility assessment. When a chart arrives by upload or from a connected system, the platform redacts identifying information, then the model compares the record with the criteria for the site's studies and attaches the source information behind its assessment. The earlier trial matching evaluation used a different reasoning model, and its archived replication project identifies OpenAI's o1. Gemini is named as a family, with no deployed version, no account of how it was adapted to trial criteria and no notice to sites when model behavior changes.

BB on Model Supply Chain DisclosureSubstantial partial disclosure, or a chain that is structurally short: an in house build, a cleared model that cannot be quietly swapped, or a deployment where the transfer does not occur at all. Naming the model provider exits the band below into this one; the axis rises from here on the completeness of the party list and on the terms that govern data once it arrives.
Vendor Published

Google supplies both the host and the Gemini model for the current eligibility workflow, which Inato runs in its own Google Cloud projects with Google Cloud tools for redaction and storage. An earlier security PDF listed OpenAI as a vendor for deidentified records, and the current support pages place the model in the managed Google Cloud environment without dating the switch. No complete processor list covers the functions outside screening, and the use and retention terms at each step are only partly laid out.

BB on Clinical and Operational EvidenceNamed deployments with dated outcome figures and enough method to test them, or published research short of independent validation.
Vendor Published

Pantheon Clinical Research cut review of complex records from about three hours to five minutes per patient in one weight loss trial, across more than 60 patients, an estimated 181 hours and $4,521 of coordinator time. A COPD study case claims faster enrollment and fewer nonperforming sites, with no figures attached.

A 2025 Communications Medicine study by Inato authors reported results for an earlier pipeline built on a different model, and those results do not carry to the current Gemini deployment. The 98% accuracy figure shown with current screening comes with no sample, scoring method or separate evaluation of the Gemini version.

BB on AI Safety and PHI StewardshipCategorical commitments are published, such as no training on customer data, without the retention schedule behind them.
Vendor Published

Charts arrive as PDFs or through a site authorized connection and are redacted before the model reviews them, and Inato keeps the deidentified clinical information under random identifiers in Google Cloud. A site authorized connection can also store structured names and contact details for the site's own use, while sponsors and Inato staff cannot see identifying information in that workflow. Processing is limited to site instructions and trial needs, with no retention window for redacted records and no process for investigating an unsafe or incorrect eligibility assessment.

Regulatory and Compliance
BB on HIPAA and BAA PostureBusiness associate status is stated and supported by a substantive privacy document, with the agreement or its scope not fully published. For a vendor outside the United States, an equivalent regime documented to this depth grades here. A vendor whose product does not process protected health information grades here too when it says so plainly and explains the scope, with a service privacy document behind it: stating a position a buyer can rely on is the posture this axis grades, and the band above is closed to it because there is no agreement to publish.
Vendor Published

Inato signs a business associate agreement with US sites before data is processed, and its guidance sets out the roles of the site, the sponsor and Inato and separates US agreements from the data processing agreements used for other sites. Records are redacted before model processing, though an authorized EHR connection can store identifying information for the site's use, and the homepage carries HIPAA and GDPR badges. The agreement template comes from the security team on request, so its full text, and how it binds subprocessors for each way patient data arrives, cannot be read in advance.

BB on Security Certifications and Trust CenterA recognized certification is named in the vendor own material without the artifact, or with a scope or renewal question the buyer has to raise. A recognized certification here is an audit of how the vendor operates security, such as SOC 2, HITRUST or ISO/IEC 27001. A certification has a scope and a clock, and both are part of this grade. A certification the vendor attaches to its data center, hosting facility or cloud provider, rather than presenting as its own, is the host's and does not count here.
Vendor Published

Inato holds ISO 27001 certification for its patient prescreening platform, a claim NextGen's integration materials repeat, and the homepage shows an ISO badge. Its security pages cover annual third party penetration testing, continuous monitoring through Drata, restricted access and encrypted storage, and documentation is available from the security team.

The certificate, the audit body and the scope are not public, so whether the attestation covers both the sponsor marketplace and every region running the current screening tool is open. Google Cloud's own controls apply to its part of the data path.

CC on FDA and Regulatory StatusNo device claim is made and the product is scoped accordingly. Most administrative and operational products sit here and are not penalized for it, because this axis grades the appropriateness of the positioning rather than possession of a clearance. A stated limit on use, such as research use only or a clause that the product gives no medical advice, beside marketing that sells the product for clinical decisions also sits here, with both quoted, because the buyer has to ask which one governs.
Vendor Published

The prescreening workflow checks whether a chart holds information that matches a protocol's requirements, and its output is a candidate assessment for a research site, with clinical staff deciding whether to go on to full screening. The tool also helps sites estimate a pool of possible participants before sponsors choose locations.

It is sold as preparation and operations for clinical research, not as diagnosing a condition, treating a patient or settling eligibility without staff review, and no FDA clearance is claimed for the platform.

DD on AI Governance and Bias DisclosureNothing published on how model behavior is governed or tested. Multilingual operation with no subgroup performance sits here when the vendor markets recognition quality as a strength, because a caller the system failed to understand leaves no complaint and no record.
Vendor Published

The matching screen shows why a chart was classified against each criterion and points staff to its source. Inato aims to make trial recruitment more representative through a wider site network and better patient access figures, an operational goal that says nothing about how often the screening model misses eligible people in different groups.

Sites in more than 50 countries submit charts in many languages and formats, yet no results for the Gemini implementation are broken out by patient population, condition or language, and the earlier published model study used a different pipeline with no subgroup evaluation.

CC on AI Liability and RecourseMechanisms exist that let someone challenge an output, such as audit trails, source traceability or review before commit, with nothing standing behind the output and no route for the harmed party.
Vendor Published

Research site staff can open the chart reference behind an eligibility assessment and set it aside when the records support a different finding, a point of challenge before the site uses the output for enrollment. Inato's marketplace terms disclaim the accuracy and reliability of results and cap collective liability at $1,000.

The 98% accuracy figure on the marketplace comes with no account of how mistakes are counted on the current deployment, and no output warranty or correction remedy for a patient the model overlooked appears in the commercial or patient data terms.

Integration and Deployment
BB on EHR and Interoperability DepthNamed systems with read access or one directional writing, or standards support with named deployments behind it.
Vendor Published

Charts come from NextGen Enterprise, which lists the integration for version 5.9.0 and later, over read only bulk FHIR connections. Inato and CRIO describe a two way connection to the trial management system that brings in patient data and returns screening results so coordinators can follow up in CRIO, and Inato carries a CRIO Certified Partner badge. eClinPro also connects, and sites without a connector upload an export. The write path runs to research systems, and the clinical chart itself stays unchanged.

DD on Deployment Model and Data ResidencyNothing published about where the system runs or where the data rests.
Vendor Published

Inato's own Google Cloud projects run the prescreening model and store records under pseudonymous identifiers, and site authorized EHR connections can deliver new records automatically after setup. US research sites work under different restrictions and agreements from sites in other regions. The privacy notice describes transfers outside Europe under contractual safeguards for the information it covers, without naming the country where clinical screening records are hosted. The Google Cloud region, the backup location and whether clinical workloads are isolated by tenant or by project are not stated.

Commercial
BB on Commercial TransparencyA price or a pricing basis is published without full tiers, so a buyer can size the cost before making contact.
Vendor Published

Research sites register for the marketplace and start AI prescreening at no charge, including for trials found elsewhere, so a site can try the product without a sales conversation. Sponsor and contract research organization workflows cover planning, site selection and enrollment tracking, and the marketplace terms set those customers apart from the sites that create accounts. No rate per study, per candidate or per selected site is shown for sponsors, and whether enterprise sponsor contracts add implementation or program support fees is not stated.

BB on Setting and Specialty CoverageCoverage is named with validation behind part of it.
Vendor Published

Independent research sites and site networks use the same screening workflow before sponsor selection and after a study opens. Pantheon Clinical Research gives a timed example in a weight loss study, a COPD study case covers enrollment, Sanofi developed workflows with research sites, and Phoenix Desert Clinical Trials describes daily use across its network. The software also checks patients against criteria for studies a site found outside Inato. Measured results exist for the one weight loss workflow, with nothing comparable across other therapeutic areas or for each way a site brings in its charts.

Alternatives

Alternatives to Inato

Other products that do the same kind of work as Inato, and what each one does.

Bond Health runs clinical trial recruitment from chart screening and advertising through to booked visits and consent support, for research sites, site networks, health systems, sponsors and CROs.

HealthKey helps research practices find potential clinical trial participants in their existing patient records. Teams supply a protocol's inclusion and exclusion criteria, and the software applies those criteria across structured EHR fields, clinical notes, and documents such as faxed PDFs.

Clinical trial platform that embeds patient identification, eSource and data capture inside provider organizations so trials can run in routine care, paired with its own recruitment coordinators and eligibility specialists.

Alleviate Health provides conversational recruitment software for clinical research sites. Its agents contact potential participants, ask initial eligibility questions, and arrange an on-site visit or a call with a clinical research coordinator.

ConcertAI's Accelerated Clinical Trials platform helps pharmaceutical sponsors and contract research organizations design, plan and run oncology studies.

AiCure's H.Code platform verifies how clinical trial participants take their medication between visits.

Commercial

Pricing

Vendor-published figures are labeled as such. Figures labeled “Estimated” are derived from third-party sources and have not been confirmed by the vendor.

Entry Price Pricing Basis BAA Tier Implementation Source
Free for research sites
$0 baseline
Research sites use the marketplace and AI prescreening at no charge. Sponsors and CROs arrange access for study planning, site selection and enrollment. US sites sign a business associate agreement before data processing; the template comes from the security team. Research site signup is free; no sponsor implementation fee is shown. Vendor Published

No sponsor plan, charge per study or contract minimum is shown. The free site offer includes prescreening for trials found outside the marketplace.