Issue 6 — PMCF activities for X-3 gaps A & B

Internal working document

This page is the specification for what Jordi needs to add to R-TF-007-002 Post-Market Clinical Follow-up (PMCF) Plan before the response to BSI is submitted. It is a prerequisite for closing BSI Item 6. Do not delete this page until the PMCF plan has been updated and verified.

Why this document exists

The CER now contains the following commitment in three places:

"Both gaps are addressed by specific PMCF activities (see R-TF-007-002 Post-Market Clinical Follow-up (PMCF) Plan)."

That commitment is made for Gap 4 — Autoimmune diseases and Gap 5 — Genodermatoses, both declared as acceptable evidence coverage gaps per MDCG 2020-6 § 6.5(e) in the X-3 disease categorisation decision (see x-3-disease-categorisation.mdx).

At the time of writing (2026-03-28), neither activity exists in R-TF-007-002. The PMCF plan currently addresses Gaps 1–3 (triage/malignancy, severity assessment, algorithmic stability). It has no section for evidence coverage gaps. The CER's forward reference is dangling. BSI will check.

This document specifies exactly what needs to be added.

---

BSI's requirements for PMCF activities

From Erin Preiss's statement in the clarification call (2026-03-25):

"La última en términos de PMCF plan — it looks like you have a lot of specific activities planned and here kind of you know some traceability maybe to how you know why you're doing some of those activities, what gaps there were from the clinical evaluation, like I said maybe from some of those specific clinical data limitations and how you're tracking, and also you know the specific methodology: things like sample size, acceptance criteria, time going to start."

And from the internal debrief (2026-03-25):

"Es fundamental vincular las brechas (gaps) aceptables encontradas en el CER con el PMCF para mantener una trazabilidad perfecta. Es fundamental explicar en el CER por qué una brecha, aunque existente, es aceptable y la evidencia sigue siendo suficiente para la validación."

Each new PMCF activity must therefore contain:

1. Explicit link to a named CER gap — the rationale must name the specific gap from the CER's "Need for more clinical evidence" section
2. Methodology — including study design, data source, and how autoimmune/genodermatosis diagnoses will be confirmed
3. Sample size with justification — or an explicit statement that passive surveillance does not permit pre-specified sample sizes, with reasoning
4. Acceptance criteria — measurable thresholds; not vague ("collect data")
5. Timeline — start date and expected completion or reporting frequency

The PMCF plan must not just list these as activities — it must also update the Coverage Mapping section (currently covers Claims 7GH, 3KX, 8PL, 1QF, 5RB and safety risks) to include explicit coverage of the two evidence gaps.

---

The gaps — precise definition from X-3

Gap A — Autoimmune diseases (3% of dermatological presentations)

What the CER says about this gap (Gap 4 in the CER's "Need for more clinical evidence" section):

Two autoimmune conditions appear in the portfolio — pemphigus vulgaris (BI_2024, 5 images) and bullous pemphigoid (DAO_Derivación_O_2022, 5 cases) — but pemphigus vulgaris is already accounted for within the Tier 2 rare diseases analysis. The autoimmune-specific evidence not counted elsewhere is therefore limited to bullous pemphigoid (5 cases in one study). This gap is declared acceptable because: (a) autoimmune skin conditions typically require serological confirmation beyond visual assessment, limiting the device's role to triage and differential ranking; (b) the device is a decision-support tool and the physician always makes the final diagnosis; (c) no acute mortality risk arises from misranking within this category.

What the PMCF activity must provide:

• Prospective data collection on autoimmune conditions in real-world deployment
• Per-condition accuracy tracking (not pooled "autoimmune" accuracy)
• Conditions to track specifically: bullous pemphigoid, lupus erythematosus (cutaneous), dermatomyositis, morphea, pemphigus foliaceus. Note: pemphigus vulgaris is already counted in Tier 2 — its data is not additional autoimmune coverage.
• Diagnosis confirmation requirement: autoimmune diagnoses must be confirmed by dermatologist assessment with serological confirmation where clinically indicated. Visual-only diagnoses are insufficient because X-3's acceptability argument rests on the claim that autoimmune conditions "typically require serological confirmation" — if the PMCF study uses visual-only ground truth, it undermines that argument.

Gap B — Genodermatoses (1% of dermatological presentations)

What the CER says about this gap (Gap 5 in the CER's "Need for more clinical evidence" section):

No direct representation in the clinical evidence portfolio. This gap is declared acceptable because: (a) these conditions are typically diagnosed through genetic testing and clinical history rather than image-based assessment alone; (b) the extreme rarity of these conditions makes prospective study recruitment impractical for pre-market evidence; (c) the device's role for these conditions is supportive (triage, differential ranking), not definitive.

What the PMCF activity must provide:

• Passive surveillance through PMS/PMCF data collection
• Explicit trigger: any case reported through PMS where a patient is subsequently confirmed to have a genodermatosis (epidermolysis bullosa, ichthyosis, Darier disease, etc.)
• Retrospective review of the device's output for those confirmed cases
• Active recruitment is explicitly not possible or required — but this must be stated in the activity as a justified methodology choice, not omitted

---

Specification for the two new activities

New section: D — Evidence Coverage Gaps

Add a new section D to the PMCF plan's "Specific PMCF Methods" section, after the existing C section. Title it:

D. Consolidated CER Gaps 4 & 5: Evidence Coverage for Autoimmune and Genodermatoses Conditions

Introductory paragraph for section D:

Per MDCG 2020-6 § 6.5(e), two epidemiological categories of dermatological disease are declared as acceptable evidence gaps in the Clinical Evaluation Report (Gaps 4 and 5 in R-TF-015-003 § "Need for more clinical evidence"). These gaps are declared acceptable based on the arguments documented in the CER: the rarity of these conditions, their diagnostic reliance on serological or genetic testing beyond visual assessment, and the absence of acute mortality risk from an incorrect visual ranking. The activities below are designed to monitor these gaps prospectively and retrospectively, ensuring that real-world deployment data does not reveal unexpected safety concerns or systematic misclassification in these categories.

---

Activity D.1 — Prospective surveillance of autoimmune skin condition recognition in clinical deployment

• Code: PMCF-AutoImmune-Coverage-2026
• Rationale: Addresses CER Gap 4 — Autoimmune diseases evidence coverage (declared acceptable per MDCG 2020-6 § 6.5(e) in R-TF-015-003 § "Need for more clinical evidence"). The pre-market evidence portfolio contains only bullous pemphigoid (5 cases, DAO_Derivación_O_2022) as autoimmune-specific evidence not already counted elsewhere. This activity systematically collects performance data for autoimmune skin conditions encountered in real-world clinical deployment.
• Methodology: Prospective, observational, real-world data collection from clinical sites deploying the device. When a healthcare professional confirms an autoimmune skin condition diagnosis (using serological testing or biopsy, where clinically indicated), the case is flagged for retrospective analysis of the device's output. The device's probability distribution for that image is reviewed to determine whether the correct autoimmune category was ranked within the Top-1, Top-3, and Top-5 results. No intervention is required from the HCP beyond standard clinical practice; the review is conducted by the clinical evaluation team.
• Conditions in scope: Bullous pemphigoid, cutaneous lupus erythematosus, dermatomyositis, morphea, pemphigus foliaceus, and any other ICD-11 autoimmune skin condition confirmed in clinical practice. Note: pemphigus vulgaris data contributes to Tier 2 rare diseases analysis (not to autoimmune-specific coverage); it is tracked separately and must not be counted as autoimmune coverage in this activity.
• Diagnosis confirmation standard: Diagnoses must be confirmed by a dermatologist. For bullous diseases, serological confirmation (anti-desmoglein antibodies for pemphigus; anti-BP180/BP230 for bullous pemphigoid) is required where clinically performed. For lupus and dermatomyositis, ANA panel results are required where available.
• Sample size & justification: Target: 50 confirmed autoimmune cases across all in-scope conditions over the surveillance period. This target is not pre-specified as a statistical power requirement but as a meaningful evidence threshold: 50 cases across 5+ autoimmune conditions provides sufficient data to identify systematic misclassification (e.g., autoimmune categories consistently ranked outside Top-5) versus random variation. Given the 3% prevalence of autoimmune conditions in dermatological practice, and assuming clinical sites process several thousand images per year collectively, 50 cases is achievable within 2–3 years of deployment without active recruitment.
• Acceptance criteria:
  • Primary: Top-3 accuracy for the confirmed autoimmune category ≥ 60%. Rationale: 60% is the minimum clinically meaningful threshold for a condition where the physician must combine the device output with serological testing — a Top-3 result that includes the correct category is sufficient for the device's role as a triage and differential ranking tool.
  • Safety: No confirmed autoimmune condition where the device ranked all autoimmune categories below Top-10 AND the physician subsequently reported that the device output contributed to a clinically significant delay in diagnosis. This criterion monitors the risk scenario described as "acceptable" in X-3 (delayed referral, not acute harm) and would require CAPA if triggered.
  • Surveillance trigger: If at any interim review (annual) more than 20% of confirmed autoimmune cases have the correct category ranked below Top-5, an unscheduled CER update and clinical evaluation review must be initiated.
• Timeline: Intended start: Upon CE marking. Data collection: continuous. First interim analysis: 12 months post-CE marking (or when 15 cases are accumulated, whichever comes first). Target completion: When 50 confirmed cases are accumulated or 36 months post-CE marking, whichever comes first.
• Reporting: Results integrated into the annual PMCF Evaluation Report and CER update.

---

Activity D.2 — Passive surveillance of genodermatoses in post-market deployment

• Code: PMCF-Genodermatoses-Surveillance-2026
• Rationale: Addresses CER Gap 5 — Genodermatoses evidence coverage (declared acceptable per MDCG 2020-6 § 6.5(e) in R-TF-015-003 § "Need for more clinical evidence"). No genodermatoses cases appear in the pre-market clinical evidence portfolio. Active prospective recruitment is not feasible given the approximately 1% prevalence in dermatological practice and the dependence of genodermatosis diagnosis on genetic testing and clinical history rather than image-based assessment. This activity monitors genodermatoses cases encountered during real-world deployment.
• Methodology: Passive surveillance. Any case reported through the PMS system (complaint, vigilance report, user feedback, or clinical site communication) where the patient's confirmed diagnosis is a genodermatosis (epidermolysis bullosa, ichthyosis vulgaris, lamellar ichthyosis, Darier disease, Hailey-Hailey disease, neurofibromatosis type 1 cutaneous manifestations, or similar) is captured and retrospectively reviewed. The review examines: (a) what the device output for that image; (b) whether the correct genodermatosis category was present in the probability distribution; (c) whether the HCP reported any clinical harm attributable to the device output.
• No active recruitment: Active recruitment for genodermatoses is explicitly not conducted. Genodermatoses remain sufficiently rare in the post-market clinical population (approximately 1% of dermatological presentations) that active prospective recruitment would be impractical and would yield insufficient case numbers to support statistically meaningful conclusions within a reasonable timeframe. Moreover, genodermatosis diagnosis depends on genetic testing and clinical history, not image-based assessment — the device's role for these conditions is purely supportive (triage, differential ranking), making diagnostic accuracy under active recruitment conditions irrelevant to the device's actual clinical function. Passive surveillance is therefore the methodologically appropriate and proportionate choice.
• Sample size: No pre-specified target. Genodermatoses are sufficiently rare that a sample size target would be unrealistic. The activity is governed by a surveillance trigger (see Acceptance Criteria) rather than a sample size threshold.
• Acceptance criteria:
  • Safety (primary): Zero confirmed genodermatosis cases where the device output was identified by the treating HCP as contributing to patient harm. Given that X-3 declares this gap acceptable on the basis that the device's role is "triage and differential ranking, not definitive diagnosis," any case of harm linked to the device output would invalidate the acceptability argument and require immediate CER update and CAPA.
  • Surveillance trigger: If more than 3 genodermatosis cases are identified through PMS in any 12-month period AND the device ranked all genodermatosis categories below Top-5 for those cases, an unscheduled clinical evaluation review must be initiated to reassess whether the gap remains acceptable.
  • Coverage trigger: If at any annual review the cumulative number of genodermatosis cases in real-world deployment reaches 30, a formal diagnostic accuracy analysis is conducted and the results are used to update the gap declaration in the CER (either confirming acceptability with new evidence, or initiating active recruitment).
• Timeline: Intended start: Upon CE marking. Surveillance: continuous throughout device lifetime. Annual review: incorporated into the PMCF Evaluation Report and PSUR.
• Reporting: Any genodermatosis case identified through PMS is reported in the next annual PMCF Evaluation Report. If the safety trigger is met, an unscheduled PMCF Evaluation Report is issued within 30 days.

---

Updates required in the PMCF plan beyond the two new activities

1. Specific Objectives section

Add to the existing list of gaps:

• Gap 4: Autoimmune diseases evidence coverage. The pre-market evidence portfolio contains insufficient direct evidence for autoimmune skin conditions (3% of dermatological presentations). The gap is declared acceptable per MDCG 2020-6 § 6.5(e) and is addressed through Activity D.1.
• Gap 5: Genodermatoses evidence coverage. No genodermatoses cases appear in the pre-market clinical evidence portfolio (1% of presentations). The gap is declared acceptable per MDCG 2020-6 § 6.5(e) and is addressed through Activity D.2.

2. Coverage Mapping section

Add to the existing "Comprehensive Coverage Mapping" subsection:

Coverage of Evidence Gaps (MDCG 2020-6 § 6.5(e)):

• Gap 4 (Autoimmune diseases): Addressed by Activity D.1 (prospective surveillance, 50-case target, Top-3 accuracy ≥ 60%).
• Gap 5 (Genodermatoses): Addressed by Activity D.2 (passive surveillance, safety-trigger-based, zero-harm criterion).

3. Data Sufficiency Justification section

Add a paragraph explaining how the two new activities contribute to overall sufficiency:

Activities D.1 and D.2 address the two evidence coverage gaps declared acceptable in the CER per MDCG 2020-6 § 6.5(e). These activities do not generate pre-market evidence — they are prospective and passive surveillance activities respectively. Their function is to confirm, through real-world deployment monitoring, that the acceptability justifications made in the CER (limited clinical role, no acute mortality risk, physician final decision) hold in practice. If either activity's surveillance trigger is met, the PMCF program initiates corrective action including unscheduled CER update.

---

Connection to BSI Item 6

BSI Item 6 (clinical review) raises deficiencies in the PMCF plan. The item specifically asks about:

• PMCF activity descriptions and their link to identified clinical gaps
• Sufficiency of planned activities to cover the device's safety and performance over its lifetime

The CER's commitment ("Both gaps are addressed by specific PMCF activities") will be the first thing BSI checks when reviewing the PMCF plan in the Item 6 response. If activities D.1 and D.2 are not present in the submitted R-TF-007-002, the CER's Gap 4/5 declarations will be unsupported — which turns an "acceptable gap with PMCF" into an "unsupported gap," which is a non-conformity.

Activities D.1 and D.2 must be in R-TF-007-002 before the Round 1 response is submitted to BSI.

---

What Jordi needs to do

1. Add the Section D introductory paragraph and Activities D.1 and D.2 to R-TF-007-002-Post-Market-Clinical-Follow-up-PMCF-Plan.mdx, after the existing Section C block.
2. Add Gap 4 and Gap 5 to the Specific Objectives section.
3. Add the Evidence Gaps coverage mapping to the Coverage Mapping subsection.
4. Add the data sufficiency paragraph for Gaps 4 and 5 to the Data Sufficiency Justification section.
5. Update the decision status in x-3-disease-categorisation.mdx — mark "Add PMCF activities for gaps A & B to PMCF Plan" as Done.
6. Run npm run build:qms and verify no errors.

Do not modify the acceptance criteria in D.1 without discussing with the team — the 60% Top-3 threshold was chosen deliberately to be defensible given the diagnostic difficulty of autoimmune conditions (the physician always makes the final call using serology). A higher threshold would be impossible to defend given the limited pre-market data and the nature of the conditions.