CIFoundry
Back to PathChat (PathChat DX)

Evaluation packet

PathChat (PathChat DX)

Mahmood Lab (Harvard Medical School / Mass General Brigham); licensed to Modella AI · Pathology

Prepared November 22, 2026 from the public listing on CIFoundry. It shows what the public record says and what to ask the vendor. It is not a recommendation or an endorsement.

1. What the public record shows

Regulatory status
FDA Breakthrough Designation
Published evidence
Linked study
Named health-system users
Not on record
Integrations
Not on record
Data inputs
Not on record
HIPAA BAA
Not on record
SOC 2 / HITRUST
Not on record
Deployment model
Not on record

Integrations, data inputs, BAA, SOC 2, HITRUST and deployment model are reported by the vendor and not checked by us. Confirm them in writing.

2. Evaluation checklist for your role

Each question shows what the public record says: on record (with its source), reported by the maker, or not on record. It is a list of things to check, not a score.

For every reviewer

Administrator & finance

Your ticks and notes stay in this browser. Nothing is sent to us.

3. Gaps to raise with the vendor

Based on what is missing or worth confirming in this tool’s public record.

  1. We found no public reports naming health systems that use it. Ask for reference sites similar to yours and contact them yourself.
  2. Will the vendor sign a HIPAA Business Associate Agreement?
  3. Does the vendor have a current SOC 2 Type II report or HITRUST certification you can review?
  4. Where is data stored and processed (cloud region, on-premises), and which subcontractors, including any large-language-model provider, touch patient data?
  5. How does it integrate with your EHR or imaging system, and where do results appear for the clinician?
  6. Is your data used to train the vendor’s models, and can it be deleted when the contract ends?

4. Questions for this kind of tool

From our Digital pathology AI guide.

The digital foundation (applies to every tool)

Use this section for any tool that analyzes whole-slide images.

Questions to ask

  • Which scanners, file formats and viewers are covered by the clearance or validation? Is it tied to one scanner?
  • What does storage cost per year at your slide volume, and who pays for it?
  • Have you validated whole-slide imaging for diagnosis in your lab? The College of American Pathologists guideline calls for at least 60 cases per application and a washout period between glass and digital reads.

Red flags

  • Scanner-agnostic claims without data
  • No storage cost estimate

Cancer detection and grading

Use this section if the tool finds or grades cancer on slides, for example prostate biopsies or lymph nodes.

Questions to ask

  • Is it authorized as an adjunct (a second look after the pathologist) or for primary diagnosis? Use it only as authorized.
  • How much did it improve pathologist detection in a reader study, and on which tissue types and stains?
  • How does it handle small foci, artifacts and unusual morphology?
  • What is the effect on sign-out time in a prospective setting?

Test it locally

  • Run it on a set of your own signed-out cases, including difficult ones, and compare with final diagnoses.

Red flags

  • Use for primary diagnosis beyond the cleared indication
  • Results only from the developer's own lab

Biomarker quantification

Use this section if the tool scores stains or counts cells, for example HER2, PD-L1 or Ki-67.

Questions to ask

  • How does agreement with expert pathologists compare with agreement between pathologists, especially near treatment cut-offs?
  • Which antibody clones, stain platforms and protocols was it validated on?
  • Is the score used to choose therapy? If so, what regulatory status does it have for that use?

Red flags

  • No data near clinical cut-offs
  • Validated on a different stain platform than yours

Case prioritization and quality control

Use this section if the tool sorts the worklist or flags slide problems (blur, folds, missing tissue) rather than making a diagnosis.

Questions to ask

  • How often does it place a cancer case low on the list?
  • Does it reduce rescans and turnaround time in practice?

Measure

  • Turnaround time for urgent cases and rescan rate before and after go-live

5. Questions for every tool

The 12 questions that apply to every tool

Fit and evidence

  • Intended use. Does the stated use match the patients, setting, user and decision you plan to use it for?
  • Evidence level. From weakest to strongest: vendor-internal test, retrospective external validation, prospective "silent" run, prospective live study, randomized trial, proven change in outcomes. Ask which level the claims rest on and look for peer-reviewed external validation.
  • Population and equipment. Ask for results by age, sex, race and ethnicity, language and payer, and, where relevant, skin type and body habitus. Ask for results on your scanner or device vendors, EHR and protocols.
  • Local validation. Before go-live, run the tool on your own recent cases and compare it to ground truth. Agree in the contract on what counts as passing.

Workflow and people

  • Workflow cost. Count clicks, alerts per clinician per shift, minutes added per case, and who acts on the output. A strong tool that nobody acts on has no value.
  • Integration. Native EHR or PACS integration or a separate window? Single sign-on? Where do results land?
  • Human oversight. Who has the final say, how are disagreements with the tool handled, and how do you guard against over-reliance? Train users on known failure modes, not just features. Explanations matter most for risk scores and decision support.

After go-live

  • Monitoring. Who checks for drift, how often, and what triggers a pause? Re-check after vendor updates, scanner or EHR changes, and shifts in your patient population. Agree in advance on the results that would retire the tool.
  • Model updates. Version control, advance notice of changes, and the right to stay on a version you validated.

Data, liability and money

  • Data rights and security. BAA, where data is stored and processed, encryption, retention, SOC 2 or HITRUST, whether your data trains the vendor's models, the list of subcontractors that touch patient data (including any large-language-model provider), and whether data can be deleted.
  • Liability and patient notice. Who is liable when AI-assisted care goes wrong is still unsettled, and responsibility currently stays with the clinicians and organizations using the tool. Ask your malpractice carrier, and cover indemnification, audit rights and incident reporting in the contract. Joint Commission and CHAI guidance says patients should be told when AI directly affects their care, with consent where relevant.
  • Money and exit. Pricing model, any real payment pathway, the return you will measure, termination for performance failure, data return, and no auto-renewal without a performance review.

6. Notes and decision

Problem we want to solve and how we will measure it

Vendor answers and follow-ups

Local test plan and what counts as passing

Decision, owner and next step

CIFoundry is an independent, vendor-neutral directory. Listing is free, and no one can pay to change a listing or this packet. Check every fact with the vendor and the primary source before relying on it.