CIFoundry
Back to DermEngine

Evaluation packet

DermEngine

MetaOptima Technology Inc. · Dermatology

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
Not on record
Published evidence
Not on record
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.

From public directories

Third-party directories checked by our team. These are not the vendor's own pages and not an endorsement.

Listed in Epic Showroom
Connection Hub: DermEngine by DermEnginesource, checked Nov 21, 2026Epic’s public app directory. Listed developers pay Epic for services; Epic does not endorse, certify or validate listed products.

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

Compliance & risk

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. No regulatory status is listed. Ask whether the tool is regulated by the FDA as a medical device and, if so, for the clearance number and the exact cleared intended use.
  2. No published study is linked. Ask for peer-reviewed validation done outside the developer’s own sites, and for results on patients and equipment like yours.
  3. We found no public reports naming health systems that use it. Ask for reference sites similar to yours and contact them yourself.
  4. Will the vendor sign a HIPAA Business Associate Agreement?
  5. Does the vendor have a current SOC 2 Type II report or HITRUST certification you can review?
  6. Where is data stored and processed (cloud region, on-premises), and which subcontractors, including any large-language-model provider, touch patient data?
  7. It is listed in Epic Showroom, which says nothing about how it is configured. Ask which Epic integration it uses at live sites and where results appear for the clinician.
  8. 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 Dermatology AI guide.

Lesion assessment for clinicians

Use this section if a clinician uses the tool to assess a skin lesion from a photo, dermoscopy image or device measurement, for example to support a skin-cancer biopsy or referral decision.

Physician looks for

  • Who the intended user is: dermatologists, primary care physicians, or both. Check that the FDA authorization (if any) matches how you plan to use it.
  • Sensitivity and specificity reported separately for each skin type (Fitzpatrick I to VI), not one overall number.
  • Whether a result would change your biopsy or referral decision, or only confirm what you already planned.
  • Image-capture quality control: lighting, focus, distance, hair and glare, and whether the tool rejects a poor image or gives a result anyway.
  • For tools that add AI-written explanations: how wrong or overconfident text is caught.

Administrator looks for

  • Extra referrals and biopsies. A tool tuned to miss few cancers flags many benign lesions. Estimate the monthly volume and whether dermatology and pathology can absorb it.
  • Effect on dermatology wait times, including for patients the tool did not flag.
  • Device or subscription cost per lesion or per clinician, including disposables.
  • Whether any payer reimburses the AI assessment itself. If not, budget it as an operating cost.
  • Training time for primary care staff to capture usable images.

IT looks for

  • How images are captured (clinic devices, personal phones or a dedicated device) and whether they land in your EHR or image archive.
  • Device management for any phones or tablets used to take photos.

Compliance looks for

  • The intended users and lesion types in the authorization, and how use beyond them is prevented.
  • Patient consent for photographs, and whether the vendor keeps images or uses them for training.

Evidence to ask for

  • A study in the intended user group, for example primary care physicians, not only dermatologists.
  • Results by skin type with enough darker-skin cases to mean something. Ask how many.
  • Outcomes confirmed by biopsy, not only agreement with a dermatologist’s opinion.
  • Positive predictive value at the skin-cancer prevalence you expect in your clinics.

Test it locally

  • Run it on 100 to 200 of your own previously biopsied lesions, including darker skin types, and compare results with pathology.
  • Count how many of your benign lesions it would have sent for biopsy or referral.

Red flags

  • No performance data by skin type, or very few darker-skin cases.
  • Results shown without an image-quality check.
  • Intended use broader than the authorization, for example use on every lesion when it is authorized only for lesions already judged suspicious.
  • Only accuracy or AUC reported, without sensitivity and specificity.

Questions to ask the vendor

  • What are sensitivity and specificity for each Fitzpatrick skin type, and how many cases of each did you test?
  • Per 100 lesions assessed in a setting like ours, how many extra referrals or biopsies should we expect?
  • What happens when the image is poor quality?
  • Is the tool authorized for our intended users and patient ages?

Tools patients use directly

Use this section if patients photograph and check their own skin with the tool, without a clinician reviewing each result first.

Physician looks for

  • Whether it is FDA-authorized for this use, or sold as a wellness or information app.
  • What a low-risk result tells the patient. False reassurance can delay care for a melanoma.
  • Whether every result tells patients to see a clinician if they are worried, whatever the app says.
  • How high-risk results reach your clinicians, and how quickly.

Administrator looks for

  • New visit and message volume from app-triggered concerns, and who staffs the responses.
  • What photos and data the vendor keeps, and whether it can use them to train its products.
  • Liability if a patient relies on a low-risk result.

IT looks for

  • Whether app data or high-risk results reach your systems at all, and how.
  • The app’s security and privacy terms, and where photos are stored.

Compliance looks for

  • Whether the app is a regulated device or a wellness product, and that how you promote it matches.
  • Data collected outside HIPAA may fall under state consumer health-data laws or the FTC Health Breach Notification Rule.

Evidence to ask for

  • A study using photos patients took themselves, not clinic dermoscopy images.
  • How often confirmed melanomas received a low-risk result.

Red flags

  • Consumer marketing with diagnostic claims and no clearance.
  • No path from a high-risk result to a clinician.
  • Patient photos reused for training by default.

Questions to ask the vendor

  • In your studies, how often did a confirmed melanoma get a low-risk result?
  • Who sees a high-risk result, and within what time?
  • Do you keep patient photos, for how long, and for what?

Teledermatology triage and routing

Use this section if the tool sorts or prioritizes referrals and store-and-forward images rather than giving a diagnosis.

Physician looks for

  • How it decides what is urgent, and whether a dermatologist can override it.
  • How often it under-prioritizes a case later found to be cancer.

Administrator looks for

  • Fit with your referral system and EHR, or a separate portal staff must check.
  • Teledermatology throughput: consults reviewed per dermatologist hour.
  • Wait times for routine referrals after go-live.
  • Cost per consult or per seat.

IT looks for

  • Integration with your referral system and EHR (HL7 or FHIR), and where images are stored.
  • Single sign-on for dermatologists reviewing consults.

Compliance looks for

  • A log of the priority given to each referral and any override.
  • Scheduled reviews of under-triaged cancers, with a named owner.

Test it locally

  • Re-run it on 3 to 6 months of past referrals and compare its priority with the final diagnosis.
  • Track time from referral to first dermatology review, by priority level, before and after go-live.

Red flags

  • No under-triage rate for cancers
  • Urgency rules you cannot see or adjust

Questions to ask the vendor

  • What is your under-triage rate for cancers?
  • Can we view and adjust the urgency rules ourselves?

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.