Clinical Decision Support
C

CancerLinQ

CancerLinQ is ConcertAI's oncology intelligence suite for community practices, cancer centers and health system oncology programs. The American Society of Clinical Oncology launched it in 2013 to pool record data from oncology practices, and ConcertAI bought it in December 2023 under a multiyear cooperation agreement with ASCO. What began as automated reporting on ASCO quality measures now spans four modules.

SmartLinQ runs quality dashboards, care gap analysis and QOPI certified reporting, with Population Analytics showing disparities, treatment trends and outcomes. PatientLinQ lines a patient up against NCCN guidelines and real world cohorts drawn from more than 13 million records, flags gaps in testing or treatment and surfaces trials where the patient's likelihood of eligibility is 90% or higher. TriaLinQ automates trial screening on line of therapy, progression, recurrence and biomarker profiles, and ConcertAI says it screens 3.3 times faster than manual review.

Cara, ConcertAI's agentic AI platform, reads physician notes, pathology and genomic reports from more than 900 sites of care in all 50 states and refreshes the structured data weekly. Insights reach oncologists as nudges inside the existing workflow, down to a missing molecular test. Wilmot Cancer Institute cut annual QOPI chart abstraction from about 100 hours to 10 or fewer, and UCHealth Anschutz Cancer Pavilion tracks 20 care quality measures through the network. The suite is sold through an enterprise demo.

AI Health Index verifiedNovember 19, 2026
Compare CancerLinQ with other vendors
Founded
2013
Headquarters
Cambridge, Massachusetts
Categories
clinical-decision-support, clinical-trials-ai
Indexed Products
SmartLinQ, Population Analytics, PatientLinQ, TriaLinQ
Buyer Segments
Oncology practices, Cancer centers, Health system oncology programs
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

Extraction by Cara turns notes, pathology and genomic reports into the stage, biomarker, progression and line of therapy facts that PatientLinQ and TriaLinQ run on. PatientLinQ's cohort comparisons and its 90% eligibility likelihood flag, and TriaLinQ's criterion by criterion screening, do not exist without those models.

SmartLinQ's dashboards, QOPI reporting and Population Analytics carry value on structured data and benchmarking alone, and they were the product's core before ConcertAI added AI matching. The suite is an oncology data and quality platform with AI at the center of its two newest clinical modules, rather than a product where the model is everything.

DD on Autonomy and Oversight ModelNo oversight structure is published. An absolute claim that the system does not err grades here too, because a buyer who believes it will not build the review step that would catch a failure.
Vendor Published

TriaLinQ screens patients against eligibility factors such as progression, recurrence and line of therapy, and the suite page says automated matching works "ensuring no eligible patient is overlooked." For a probable match the product shows a determination on each of 20 to 30 criteria with a link to its source in the chart, and nurse navigators at Wilmot reviewed charts during rollout, so suggested matches meet a person before enrollment. That review checks what the model flagged.

It cannot surface an eligible patient the model missed, and the promise covers exactly those patients. Beg says ConcertAI does not assume the tools will care for patients on their own, yet no exception threshold, fallback screen for unflagged patients or rule routing a case to a reviewer is described.

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

Cara is ConcertAI's proprietary agentic AI platform, a chain of models and agents that parses notes, pathology and next generation sequencing reports, interprets concepts such as disease progression and diagnosis timelines, and writes a structured oncology data model. One layer of agents measures abstraction accuracy and another checks that the sequence of events is clinically coherent.

The models are trained on millions of clinical records curated by people, and the dataset refreshes weekly. PatientLinQ aligns more than 200 data variables with NCCN guidelines and real world cohorts. ConcertAI also runs a wider technical collaboration with NVIDIA. The underlying model families, release identifiers and an update practice that would tell a cancer center when a matching model changed are not named.

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

Cara, ConcertAI's own agentic AI platform, does the oncology interpretation behind every module, so the core models sit inside the parent company rather than with an outside model provider. NVIDIA and AWS are named company technology partners, the second as the cloud behind earlier network research environments. Older CancerLinQ network papers name outside firms that handled record linkage and deidentification at different points in the pipeline.

What stays unnamed is the current chain for an identifiable record moving through PatientLinQ or TriaLinQ: which of these partners touches it, whether a large language model from an outside provider runs inside Cara's agent chain, and the retention and training terms that would govern data on arrival. The result is an in house core with partial names around it rather than a full party list.

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

Wilmot Cancer Institute at University of Rochester Medicine told TechTarget in September 2026 that its yearly QOPI chart abstraction fell from about 100 hours to 10 hours or less after adopting CancerLinQ. UCHealth Anschutz Cancer Pavilion gained visibility into 20 care quality measures and found documentation gaps in advanced care planning and smoking status. Both are quality operations results at named sites.

For the newer trial workflow, ConcertAI reports screening 3.3 times faster than manual review and up to 50% higher enrollment, and chief executive Eron Kelly cites extraction precision and recall of 0.9 or higher. The trial and extraction figures name no site, cohort, comparison period or reference standard.

CC on AI Safety and PHI StewardshipGeneral assurances of privacy and security that do not answer the questions artificial intelligence raises: what is retained, what reaches a model, and what happens to it there.
Vendor Published

Identifiable practice records serve care and quality improvement, with access limited to the treating team and a small curation group, and CancerLinQ keeps that path apart from the deidentified datasets used for secondary research. Patients can ask their care team to opt out. Cara is trained on millions of curated clinical records, and its agents cross check each other's abstraction before data reaches the weekly refresh.

Left open are the questions AI raises: how long model inputs and outputs are kept, whether a practice's records train future versions of Cara, what reaches any outside model, and how a safety event, such as a wrong eligibility call that reached a patient, is investigated and disclosed to the practice.

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

Oncology practices join under a participation agreement, a data use agreement and a business associate agreement, the arrangement a May 2020 CancerLinQ data quality policy sets out for records shared for health care operations. Patient materials separate access to identifiable records by the treating practice and limited curation staff from research use of deidentified data, and the privacy policy explains how a patient opts out through the care team.

The business associate agreement itself is not available before contracting. Under ConcertAI's ownership it is also unclear which modules the agreement covers, whether trial screening falls inside health care operations, and how its terms bind the subcontractors that handle practice records.

DD on Security Certifications and Trust CenterControls are asserted with nothing independent behind them, or nothing is published. Read the note before concluding anything: this is the grade most often corrected on a second pass, because assurance material frequently sits on a parent domain or inside an old announcement rather than on the product pages.
Vendor Published

Access to identifiable records is limited to the treating practice's authorized users and a small group of curation staff, and an older CancerLinQ data quality policy sets confidentiality duties around collected records. ConcertAI's privacy notice covers its websites and demo inquiries rather than the suite. QOPI certification measures how a practice runs its quality program, not how the software is secured, so it is no security attestation.

For a suite holding longitudinal oncology records from more than 900 sites of care, no SOC 2 report, HITRUST certification, ISO 27001 certificate, penetration testing cadence or trust portal is offered on the CancerLinQ pages. The safeguards rest on the company's own description, with no outside audit a cancer center can open.

DD on FDA and Regulatory StatusThe positioning is unclear or unsupported: clinical claims with no regulatory position stated, or language implying a status the databases do not carry. An open enforcement action that names the product also grades here, whatever the positioning: an FDA warning letter with no close out letter posted, or a consent decree in force. The note says which of the two applies, and the grade returns to the positioning bands when FDA closes the action.
Vendor Published

PatientLinQ informs treatment decisions during a visit by comparing a patient with similar cohorts, flagging gaps in molecular testing and lining the case up against NCCN guidelines, and the suite page promises insights "to ensure confident care decisions." TriaLinQ screens patients for trials.

SmartLinQ's QOPI tie is a quality program certification for the practice, not a regulatory position for the software, and ConcertAI's site terms disclaim medical advice for its websites and materials, which says nothing about the clinical product. No FDA authorization covers the suite, and no statement names the clinical decision support exclusion or any other basis the treatment comparison relies on to sit outside device oversight. Clinical claims with no stated regulatory position leave the status open.

CC on AI Governance and Bias DisclosureResponsible artificial intelligence is committed to in policy language with no evaluation behind it. Most of the index sits here.
Vendor Published

Carole Tremonti, a registered nurse and vice president of the CancerLinQ Network, wrote an October 2026 essay urging hospital AI committees to govern tools across their whole lifecycle, seat patients and underrepresented groups, scale scrutiny to clinical risk and name who can pause or retire a tool.

It is general advice with no criteria, checklist or template for evaluating PatientLinQ or TriaLinQ, and while it warns that models can perform differently across populations, it gives no results for ConcertAI's own. Population Analytics helps practices see disparities in care, a separate question from whether the matching and cohort models perform evenly by cancer type, age, race or practice setting. No subgroup results, fairness method or outside audit of the models is offered.

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

Each probable trial match comes with a determination on each of its 20 to 30 eligibility criteria and a link to the source in the chart, and PatientLinQ shows the cohort and guideline context behind a treatment insight. That traceability lets a coordinator or oncologist challenge a suggestion against the record before acting on it, and support runs through a dedicated CancerLinQ help center. Nothing stands behind the output beyond that.

ConcertAI's website terms disclaim accuracy warranties for site materials and advertised services, and no error correction commitment, indemnity or remedy tied to a wrong match or a misleading cohort comparison is offered outside the suite contract. Chief executive Eron Kelly cites precision and recall of 0.9 or higher for the extraction, with no method or denominator behind the figure.

Integration and Deployment
CC on EHR and Interoperability DepthIntegration is claimed through standards or a middleware layer with no system named and nothing to verify.
Vendor Published

Participating organizations send structured fields and unstructured content from their electronic health records, including physician notes, pathology reports and genomic lab reports, into the network, where Cara extracts and harmonizes them for dashboards, cohort comparisons and screening. Shaalan Beg, ConcertAI's chief medical officer for oncology, calls the company agnostic to every EHR vendor and molecular lab.

Earlier network papers name Epic, OncoEMR, MOSAIQ and ARIA as source feeds, which shows the network has taken in several record formats. For the current PatientLinQ and TriaLinQ modules no record system is named, the interface each module uses goes undescribed, and nothing shows insights or matches written back into a named EHR rather than presented in a separate view.

CC on Deployment Model and Data ResidencyA single hosted option with location implied rather than committed.
Vendor Published

The suite runs as a hosted service that pools a practice's clinical records with oncology data from a national network of more than 900 sites of care in the United States. Earlier CancerLinQ research environments ran on purpose built Amazon Redshift instances, and ConcertAI names AWS as a current technology partner, so the cloud context is clear. A weekly pipeline refresh rebuilds the structured dataset each practice sees.

Left open are a residency commitment for identifiable data in the current suite, how one practice's records are isolated from the wider network, and whether quality reporting, patient comparisons and trial screening share one processing path. Only the hosted option is described, with no private cloud or on premises route for a health system that wants one.

Commercial
CC on Commercial TransparencyNo price is published and the posture is discoverable: a buyer can establish how the product is sold and what drives the cost before contacting the vendor. Most of the index sits here.
Vendor Published

Cancer centers and oncology networks reach the suite through ConcertAI's demo request and a specialist call, with no price, rate card or self service trial. The cost drivers are visible all the same. SmartLinQ, Population Analytics, PatientLinQ and TriaLinQ are sold as one integrated system, so scope runs from a single practice automating QOPI abstraction to a multisite network putting trial matching in front of navigators at every clinic.

Each deployment needs record feeds from participating sites, and implementation can span many facilities. The unit of charge, whether a module can be bought alone, any minimum term and onboarding costs are settled in the proposal.

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

Settings span oncology practices, cancer centers and health system oncology programs using the suite for quality reporting, care gap work, treatment comparison and trial recruitment. The network draws on more than 900 sites of care across all 50 states, academic, community and health system settings among them, with records across solid tumors and blood cancers.

In hub and spoke systems the tools reach patients at satellite clinics as well as the main campus, as at Wilmot Cancer Institute across its regional sites. Validation is uneven by module. Quality reporting has named deployments at Wilmot and UCHealth Anschutz, while matching performance by cancer type, practice setting or trial phase comes with no breakdown.

Alternatives

Alternatives to CancerLinQ

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

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

VieCure sells Halo Intelligence, an oncology electronic medical record and clinical decision support platform built for community cancer care.

Generative chat interface over the American Society of Clinical Oncology's own library of clinical practice guidelines, announced in May 2025 and developed by ASCO and Google Cloud on the Vertex AI platform with Gemini models.

Digital cognitive assessment and care planning platform.

Precision oncology company running hospital linked genomics laboratories in India, the United Arab Emirates, Nepal and the Philippines.

Oncology AI that reads the whole patient chart. OncoLLM, a family of oncology-tuned models tuned further on each institution's records, reads every note, report, scan and fax and returns structured answers with a citation to the line in the chart behind each one.

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
Enterprise quote
ConcertAI sells the CancerLinQ Suite to oncology practices, cancer centers and health system oncology programs through a demo and an enterprise proposal. SmartLinQ, Population Analytics, PatientLinQ and TriaLinQ are presented as one integrated system across quality, treatment and trial workflows. Participating practices sign a business associate agreement alongside participation and data use agreements. Module coverage under the current ConcertAI agreement is set in contracting. Onboarding connects record feeds from each participating site, including notes, pathology and genomic reports, before quality reporting and screening go live. No onboarding or integration fee is listed. Vendor Published

No rate card, unit of charge, minimum commitment or per module price appears for the suite, and there is no self service purchase or priced pilot.