Response

Fix

We have implemented a comprehensive update across the clinical documentation to address the deficiencies identified by the Notified Body regarding the PMCF Plan.

The following documents have been revised:

• R-TF-007-002 Post-Market Clinical Follow-up (PMCF) Plan: Expanded with detailed methodological descriptions for all 11 activities (A.1 through D.2), teledermatology clarification, and equivalent device evaluation. This includes two new activities (D.1 and D.2) addressing the evidence coverage gaps declared in the CER per MDCG 2020-6 § 6.5(e).
• R-TF-015-001 Clinical Evaluation Plan (CEP): Updated to ensure consistency with the 11-activity PMCF program, removing previous statements indicating no new studies were planned.

Furthermore, we have established the documentation structure for the supporting Clinical Investigation Plans (CIP, R-TF-015-004) for all planned PMCF studies within the technical documentation.

Response to BSI

We have updated the R-TF-007-002 Post-Market Clinical Follow-up (PMCF) Plan to address the points raised by the reviewer. Specifically, the following improvements have been made:

• Detailed Activity Descriptions: For each of the 11 PMCF activities (A.1 through D.2), we have provided a full and comprehensive description that includes:

  • Rationale: Clear justification for the activity, explicitly linked to the CER gaps (Triage, Severity Assessment, or Core Performance).
  • Methodology: Detailed study design (e.g., multireader multicase, prospective interventional, or retrospective observational).
  • Sample Size and Justification: Specific sample sizes (e.g., 30,000 images for A.1, 140 patients for A.2, 30 readers for C.1) with statistical or clinical feasibility rationales.
  • Acceptance Criteria: Measurable thresholds for success, such as AUC >= 0.8, diagnostic accuracy improvement of >= 10%, or Intraclass Correlation Coefficient (ICC) > 0.75 for reliability studies.
  • Timelines: Expected start and completion dates for each activity.

• Clarification of "Teledermatology": We have clarified in the PMCF rationale that "teledermatology" refers to a clinical workflow use-scenario (the remote capture and transmission of images) rather than a device feature. The PMCF activities evaluate the device's core performance within these specific real-world clinical contexts.

• Device Identification: We have explicitly confirmed throughout the plan that all activities evaluate the current version of the device, ensuring consistency across all technical records.

• Evaluation of Equivalent and Similar Devices: A new section has been added to the PMCF Plan providing an evaluation of clinical data from similar AI-based dermatology devices, as required by Annex XIV Part B 6.2(a).

• Consistency with the CEP: The R-TF-015-001 Clinical Evaluation Plan has been updated to correctly reflect the planned PMCF investigations, ensuring alignment between the scoping documents and the proactive data collection program.

• Section D: Evidence Coverage Gaps (new). A new section D has been added to the PMCF Plan addressing the two evidence coverage gaps declared in the CER per MDCG 2020-6 § 6.5(e). These activities ensure that the CER's acceptable gap declarations are supported by specific, linked PMCF activities:

  • Activity D.1: Prospective surveillance of autoimmune skin condition recognition in clinical deployment. Addresses CER Gap 4 (autoimmune diseases, 3% of dermatological presentations). Methodology: prospective, observational, real-world data collection from clinical sites. Diagnosis confirmation: dermatologist assessment with serological confirmation where clinically indicated. Conditions in scope: bullous pemphigoid, cutaneous lupus erythematosus, dermatomyositis, morphea, pemphigus foliaceus. Sample size: 50 confirmed autoimmune cases. Acceptance criteria: Top-3 accuracy for the confirmed autoimmune category >= 60%; safety criterion based on zero cases where the device output contributed to clinically significant diagnostic delay; surveillance trigger if at any annual interim review more than 20% of confirmed autoimmune cases have the correct category ranked below Top-5, initiating an unscheduled CER update. Timeline: continuous from CE marking; first interim analysis at 12 months or 15 cases; target completion at 50 cases or 36 months.

  • Activity D.2: Passive surveillance of genodermatoses in post-market deployment. Addresses CER Gap 5 (genodermatoses, 1% of presentations). Methodology: passive surveillance through PMS system. Active recruitment is explicitly not conducted, justified by the extreme rarity (approximately 1% of presentations) and the dependence of genodermatosis diagnosis on genetic testing rather than image-based assessment. No pre-specified sample size target. Acceptance criteria: zero confirmed genodermatosis cases where the device output contributed to patient harm; surveillance trigger if >3 cases in any 12-month period with all genodermatosis categories ranked below Top-5; coverage trigger at 30 cumulative cases initiating formal accuracy analysis. Timeline: continuous throughout device lifetime; annual review in PMCF Evaluation Report.

• Reference to Supporting Documents: The PMCF Plan now references the specific locations of the supporting Clinical Investigation Plans (R-TF-015-004) currently being drafted for the specific PMCF studies within the technical documentation.