R-TF-007-002 Post-Market Clinical Follow-up (PMCF) Plan

Manufacturer contact details

	Manufacturer data
Legal manufacturer name	AI Labs Group S.L.
Address	Street Gran Vía 1, BAT Tower, 48001, Bilbao, Bizkaia (Spain)
SRN	ES-MF-000025345
Person responsible for regulatory compliance	Alfonso Medela, Saray Ugidos
E-mail	office@legit.health
Phone	+34 638127476
Trademark	Legit.Health
Authorized Representative	Not applicable (manufacturer is based in EU)

Medical device characterization

	Information
Device name	Legit.Health Plus (hereinafter, the device)
Model and type	NA
Version	1.1.0.0
Basic UDI-DI	8437025550LegitCADx6X
Certificate number (if available)	MDR 792790
EMDN code(s)	Z12040192 (General medicine diagnosis and monitoring instruments - Medical device software)
GMDN code	65975
EU MDR 2017/745	Class IIb
EU MDR Classification rule	Rule 11
Novel product (True/False)	TRUE
Novel related clinical procedure (True/False)	TRUE
SRN	ES-MF-000025345

Intended use or purpose

Intended use

The device is a computational software-only medical device leveraging computer vision algorithms to process images of the epidermis, the dermis and its appendages, among other skin structures, enhancing efficiency and accuracy of care delivery, by providing:

• an interpretative distribution representation of possible International Classification of Diseases (ICD) categories that might be represented in the pixels content of the image
• quantifiable data on the intensity, count and extent of clinical signs such as erythema, desquamation, and induration, among others

Quantification of intensity, count and extent of visible clinical signs

The device provides quantifiable data on the intensity, count and extent of clinical signs such as erythema, desquamation, and induration, among others; including, but not limited to:

• erythema,
• desquamation,
• induration,
• crusting,
• xerosis (dryness),
• swelling (oedema),
• oozing,
• excoriation,
• lichenification,
• exudation,
• wound depth,
• wound border,
• undermining,
• hair loss,
• necrotic tissue,
• granulation tissue,
• epithelialization,
• nodule,
• papule
• pustule,
• cyst,
• comedone,
• abscess,
• hive,
• draining tunnel,
• non-draining tunnel,
• inflammatory lesion,
• exposed wound, bone and/or adjacent tissues,
• slough or biofilm,
• maceration,
• external material over the lesion,
• hypopigmentation or depigmentation,
• hyperpigmentation,
• scar,
• scab,
• spot,
• blister

Image-based recognition of visible ICD categories

The device is intended to provide an interpretative distribution representation of possible International Classification of Diseases (ICD) categories that might be represented in the pixels content of the image.

Device description

The device is a computational software-only medical device leveraging computer vision algorithms to process images of the epidermis, the dermis and its appendages, among other skin structures. Its principal function is to provide a wide range of clinical data from the analyzed images to assist healthcare practitioners in their clinical evaluations and allow healthcare provider organisations to gather data and improve their workflows.

The generated data is intended to aid healthcare practitioners and organizations in their clinical decision-making process, thus enhancing the efficiency and accuracy of care delivery.

The device should never be used to confirm a clinical diagnosis. On the contrary, its result is one element of the overall clinical assessment. Indeed, the device is designed to be used when a healthcare practitioner chooses to obtain additional information to consider a decision.

Intended medical indication

The device is indicated for use on images of visible skin structure abnormalities to support the assessment of all diseases of the skin incorporating conditions affecting the epidermis, its appendages (hair, hair follicle, sebaceous glands, apocrine sweat gland apparatus, eccrine sweat gland apparatus and nails) and associated mucous membranes (conjunctival, oral and genital), the dermis, the cutaneous vasculature and the subcutaneous tissue (subcutis).

Intended patient population

The device is intended for use on images of skin from patients presenting visible skin structure abnormalities, across all age groups, skin types, and demographics.

Intended user

The medical device is intended for use by healthcare providers to aid in the assessment of skin structures.

User qualifications and competencies

This section outlines the qualifications and competencies required for users of the device to ensure its safe and effective use. It is assumed that all users already possess the baseline qualifications and competencies associated with their respective professional roles.

Healthcare professionals

No additional official qualifications are required for healthcare professionals (HCPs) to use the device. However, it is recommended that HCPs possess the following competencies to optimize device utilization:

• Proficiency in capturing high-quality clinical images using smartphones or equivalent digital devices.
• Basic understanding of the clinical context in which the device is applied.
• Familiarity with interpreting digital health data as part of the clinical decision-making process.

The device may be used by any healthcare professional who, by virtue of their academic degree, professional license, or recognized qualification, is authorized to provide healthcare services. This includes, but is not limited to:

• Medical Doctors (MD, MBBS, DO, Dr. med., or equivalent)
• Registered Nurses (RN, BScN, MScN, Dipl. Pflegefachfrau/-mann, or equivalent)
• Nurse Practitioners (NP, Advanced Nurse Practitioner, or equivalent)
• Physician Assistants (PA, or equivalent roles such as Physician Associate in the UK/EU)
• Dermatologists (board-certified, Facharzt für Dermatologie, or equivalent)
• Other licensed or registered healthcare professionals as recognized by local, national, or European regulatory authorities

Each HCP must hold the academic title, degree, or professional registration that confers their status as a healthcare professional in their jurisdiction, whether in the United States, Europe, or other regions where the device is provided.

IT professionals

IT professionals are responsible for the technical integration, configuration, and maintenance of the medical device within the healthcare organization's information systems.

No specific official qualifications are mandated. Nevertheless, it is advisable that IT professionals involved in the deployment and support of the device have the following competencies:

• Foundational knowledge of the HL7 FHIR (Fast Healthcare Interoperability Resources) standard and its application in healthcare data exchange.
• Ability to interpret and manage the device's data outputs, including integration with electronic health record (EHR) systems.
• Understanding of healthcare data privacy and security requirements relevant to medical device integration, including GDPR (Europe), HIPAA (US), and other applicable local regulations.
• Experience with troubleshooting and supporting clinical software in a healthcare environment.
• Familiarity with IT standards and best practices for healthcare, such as ISO/IEC 27001 (Information Security Management) and ISO 27799 (Health Informatics—Information Security Management in Health).

IT professionals may include, but are not limited to:

• Health Informatics Specialists (MSc Health Informatics, or equivalent)
• Clinical IT System Administrators
• Healthcare Integration Engineers
• IT Managers and Project Managers in healthcare settings
• Software Engineers and Developers specializing in healthcare IT
• Other IT professionals with relevant experience in healthcare environments, as recognized by local, national, or European authorities

Each IT professional should possess the relevant academic degree, professional certification, or demonstrable experience that qualifies them for their role in the healthcare organization, in accordance with the requirements of the United States, Europe, or other regions where the device is provided.

Use environment

The device is intended to be used in the setting of healthcare organisations and their IT departments, which commonly are situated inside hospitals or other clinical facilities.

The device is intended to be integrated into the healthcare organisation's system by IT professionals.

Operating principle

The device is computational medical tool leveraging computer vision algorithms to process images of the epidermis, the dermis and its appendages, among other skin structures.

Body structures

The device is intended to use on the epidermis, its appendages (hair, hair follicle, sebaceous glands, apocrine sweat gland apparatus, eccrine sweat gland apparatus and nails) and associated mucous membranes (conjunctival, oral and genital), the dermis, the cutaneous vasculature and the subcutaneous tissue (subcutis).

In fact, the device is intended to use on visible skin structures. As such, it can only quantify clinical signs that are visible, and distribute the probabilities across ICD categories that are visible.

Explainability

For visual signs that can be quantified in terms of count and extent, the underlying models not only calculate a final value, such as the number of lesions, but also determine their locations within the image. Consequently, the output for these visual signs is accompanied by additional data, which varies depending on whether the quantification involves count or extent.

• Count. When a visual sign is quantifyed by counting, the device generates bounding boxes for each detected entity. These bounding boxes are defined by their x and y coordinates, as well as their height and width in pixels.
• Extent. When a visual sign is quantifyed by its extent, the device outputs a mask. This mask, which is the same size as the image, consists of 0's for pixels where the visual sign is absent and 1's for pixels where it is present.

The explainability output can be found with the explainabilityMedia key. Here is an example:

{
  "explainabilityMedia": {
    "explainabilityMedia": {
      "content": "base 64 image",
      "detections": [
        {
          "confidence": 98,
          "label": "nodule",
          "p1": {
            "x": 202,
            "y": 101
          },
          "p2": {
            "x": 252,
            "y": 154
          }
        },
        {
          "confidence": 92,
          "label": "pustule",
          "p1": {
            "x": 130,
            "y": 194
          },
          "p2": {
            "x": 179,
            "y": 245
          }
        }
      ]
    }
  }
}

Applicable Standards and Guidelines

• MDCG 2020-5 Clinical evaluation - Equivalence (04/2020)
• MDCG 2020-7 PMCF plan template (04/2020)
• MDCG 2020-8 PMCF evaluation report (04/2020)
• EN ISO 14155:2020 Clinical investigation of medical devices for human subjects — Good clinical practice
• EN ISO 14971:2019 Medical devices — Application of risk management to medical devices

PMCF plan details

• PMCF plan number: 002
• PMCF plan date: 2026-03-11

Rationale and Specific Objectives of the PMCF Plan

The PMCF Plan is an integral part of the Post-Market Surveillance (PMS) system and serves as a continuous update to the Clinical Evaluation Report (CER), as required by Article 83 and Annex XIV, Part B of the MDR.

General Objectives

The overall aim of the PMCF is to confirm the safety and performance, including the clinical benefit of the device, throughout its expected lifetime. Also identify and analyze emergent risks on the basis of factual evidence. More specifically, the general objectives of the PMCF are to ensure the continued acceptability of the device's Benefit-Risk Ratio and identify possible systematic misuse or off-label use of the device.

Specific Objectives

To ensure the sustained acceptability of the benefit-risk profile, the latest Clinical Evaluation Report (CER, Version 1.0) requires the PMCF to gather targeted evidence aimed at:

1. Reinforcing existing clinical claims and long-term performance data; and
2. Documenting novel clinical benefits and effectiveness in specific areas like clinical decision support and referral management.

All PMCF activities described in this plan evaluate the Legit.Health Plus (version 1.1.0.0) device.

Teledermatology Terminology

Several activities (A.1, A.3, B.2) reference "teledermatology." This term describes a clinical workflow modality (remote clinical assessment) in which the device operates as a decision support tool, rather than a device feature itself. The device's core capability of processing dermatological images for diagnostic support and severity assessment is evaluated within these specific use scenarios to confirm real-world performance in different clinical settings.

The gaps are:

• Gap 1: Triage and Malignancy Prioritization. More evidence on the impact on reducing the average waiting time for skin cancer patients.
• Gap 2: Automated Severity Assessment and Monitoring for Specific Conditions. Additional clinical data to validate the device's performance in accurately assessing severity and monitoring progression of conditions such as Atopic Dermatitis, Acne, Frontal Fibrosing Alopecia, and Hidradenitis Suppurativa.
• Gap 3: Monitoring of Sustained Core Algorithmic Performance. Ongoing evaluation to ensure the device's core diagnostic algorithms maintain their accuracy and reliability in real-world clinical settings over time.

Data Sufficiency Justification

In accordance with Annex XIV, Part B, Section 6.1 of the MDR, the totality of the PMCF activities (combining General Methods and Specific Methods) is designed to collect sufficient clinical data—in both quality and quantity—to confirm the safety, performance, and clinical benefits of the device throughout its expected lifetime (5 years).

Methodological Quality and Quantity

• Quality: All specific PMCF activities are governed by formal Clinical Investigation Plans (R-TF-015-004) aligned with ISO 14155:2020 principles for clinical investigations. Studies evaluating diagnostic accuracy adhere to STARD (Standards for Reporting of Diagnostic Accuracy Studies) guidelines. The methodologies selected—ranging from large-scale retrospective analyses to prospective interventional trials—are internationally recognized and appropriate for software as a medical device (SaMD).
• Quantity: The sample sizes for the specific activities have been rigorously justified. For instance, Activity A.1 utilizes an extensive dataset of 30,000 images to ensure statistical power for low-prevalence malignant conditions, while Activities B.1-B.4 (severity assessment) utilize target cohorts of 30 to 100 patients to confidently evaluate Intraclass Correlation Coefficients (ICC). The general methods will systematically capture real-world data from the entire user base over the device's lifetime.

Comprehensive Coverage Mapping

The PMCF strategy ensures that all clinical performance claims, identified risks, and intended user populations are actively monitored. The following matrix illustrates the coverage of the PMCF activities:

Coverage of Clinical Performance Claims:

• Benefit 7GH (Diagnostic accuracy — all presentations): (a) General conditions: Monitored via C.1, C.2.1, C.2.2. (b) Rare diseases: Monitored via C.2.1, C.2.2. (c) Malignant lesions: Monitored via A.1, A.2, C.2.1.
• Benefit 5RB (Objective severity measurement): Confirmed via B.1 (FFA), B.2 (Acne), B.3 (Atopic Dermatitis), B.4 (Vitiligo).
• Benefit 3KX (Care pathway optimisation): (a) Waiting times: Confirmed via A.1, A.2. (b) Referral adequacy: Confirmed via A.3. (c) Remote care: Monitored via A.1, A.2.

Coverage of Safety and Residual Risks: While specific studies (like C.1 and C.2) assess performance limits, the continuous General PMCF Methods (PMS data, vigilance, and user feedback) are the primary mechanisms for monitoring the rare residual risks identified in the Risk Management Report (R-TF-013-003), such as:

• R-75H & R-DAG (Incorrect clinical output / Misdiagnosis): General Methods (complaint trending), plus specific accuracy tracking in C.1.
• R-AGQ & R-5L4 (Image quality / Lighting artifacts): General Methods (user feedback, failure rate monitoring) and C.2.3 (Reproducibility study).

Coverage of User Populations:

• Healthcare Professionals (HCPs - Dermatologists & GPs): Covered directly by A.2, A.3, B.1-B.4, C.1, and C.2.2.
• IT Professionals (ITPs): Monitored continuously via General Methods (system integration complaints, API uptime monitoring).

Continuous Evaluation Lifecycle (Continuity)

PMCF is not a one-time event but a continuous process spanning the 5-year expected lifetime of the device. The PMCF activities operate in iterative, annual cycles:

1. Execution: Specific studies and continuous general data collection are executed.
2. Analysis & Integration: Data is analyzed and integrated annually into the PMCF Evaluation Report and the Periodic Safety Update Report (PSUR).
3. CER Update: The PMCF Evaluation Report directly informs the annual update of the Clinical Evaluation Report (CER, R-TF-015-003).
4. Reassessment: Based on new data, the Risk Management File and state-of-the-art are reassessed. Any new evidence gaps trigger the design of subsequent specific PMCF studies for the next cycle, ensuring continuous, lifetime monitoring.

Evaluation of Equivalent and Similar Devices

Per Annex XIV Part B 6.2(a), the PMCF plan must include an evaluation of clinical data relating to equivalent or similar devices.

As documented in R-TF-015-003 Clinical Evaluation Report, the device has demonstrated equivalence to its predecessor (Legit.Health Legacy). Furthermore, the PMCF program monitors the state-of-the-art by continuously evaluating published clinical data from similar AI-based dermatology devices in the market, such as SkinVision, DERM, Dermalyser, ModelDerm, Huvy, and DermaSensor.

Through the literature screening activities described in the General PMCF Methods, clinical data (such as published diagnostic accuracy metrics, false-negative rates, and real-world implementation challenges) from these similar devices are systematically reviewed. This ongoing evaluation ensures that:

1. The performance and safety thresholds of Legit.Health Plus remain aligned with or superior to current market standards.
2. Any newly identified risks or complications associated with similar AI technologies are proactively incorporated into our Risk Management File and targeted by our PMCF activities.

PMCF activities

The PMCF activities are divided into general methods (proactive data collection) and specific methods (targeted studies).

General PMCF Methods (Drawing Clinical Data from PMS)

These methods represent the routine, continuous collection and evaluation of clinical information derived from the Post-Market Surveillance (PMS) system (as detailed in the PMS Plan). The clinical data gathered through these ongoing activities are formally assessed within the PMCF framework to ensure the continued acceptability of the benefit-risk ratio.

• Gathering Clinical Experience/User Feedback: Continuous collection and evaluation of field reports, service reports, and user surveys to identify performance issues or potential safety concerns in real-world use.
• Systematic Screening of Scientific Literature: Regular and documented searches for new publications related to the device, similar devices, or the underlying technology to identify previously unknown risks or long-term trends.
• Analysis of Clinical Data from PMS: Comprehensive review of all reported incidents, complaints, and vigilance reports (Serious Incidents, FSCA) to detect trends that may impact the clinical benefit or risk profile.
• Evaluation of Public Information: Monitoring registries, regulatory databases (e.g., Eudamed), and public safety communications to gather external real-world evidence.

note

These general activities are defined and explained in detail in the document R-TF-007-001.

Metric Definitions and Clinical Rationale

All performance metrics used in the activities below (including Top-1, Top-3, Top-5 accuracy, AUC, Sensitivity, Specificity, PPV, NPV, ICC, and Overall Percent Agreement) are defined with their clinical rationale and relevance to the intended purpose in the Glossary of R-TF-015-003 Clinical Evaluation Report. These definitions ensure a common and patient-centric understanding of the assessment criteria throughout the device's lifecycle.

Specific PMCF Methods.

The following targeted activities will be undertaken to address the specific objectives listed in the Specific Objectives section.

A. Consolidated CER Gap 1: Triage and Malignancy Prioritization

Confirmation of Real-World Triage and Prioritization Effectiveness. The PMCF program must generate targeted, post-market clinical data to confirm the clinical effectiveness and operational impact of the device in reducing patient waiting times for high-risk conditions and to validate its accuracy in prioritizing patient follow-up and referrals.

Activity A.1: Legit.Health Plus performance in automated triage in teledermatology workflows

• Code: Legit.Health_triaje_VH_2025
• Rationale: Addresses Gap 1. Confirms the device's clinical benefit of reducing waiting times for high-risk patients (Clinical Benefit 3KX) in a large-scale retrospective setting.
• Methodology: Observational and Retrospective study evaluating the performance of Legit.Health Plus (version 1.1.0.0) when integrated into established teledermatology triage pathways. The study analyzes historical image data and compares device-suggested triage priority with the actual clinical outcome.
• Sample Size & Justification: 30,000 images. This large-scale dataset ensures statistical significance across a wide range of dermatological conditions and confirms performance in low-prevalence malignant conditions.
• Acceptance Criteria:
  • Percentage of reduction of waiting time: >= 50%.
  • Malignancy detection: AUC >= 0.8, sensitivity >= 75%, specificity >= 80%.
  • Diagnostic accuracy: Top-1 >= 50%, Top-3 >= 70%, Top-5 >= 80%.
• Timeline: Intended Start: June 2026. Expected Completion: December 2026.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/VH_triaje_2025/)

Activity A.2: Clinical validation of Legit.Health Plus for prioritising follow-up visits in patients at risk of melanoma

• Code: CVCSD_VC_2402
• Rationale: Addresses Gap 1. Specifically targets the prioritisation of melanoma follow-up, confirming the device's role in high-risk referral management.
• Methodology: Prospective and Single-centre study with intervention using Legit.Health Plus (version 1.1.0.0). The device is used to assist in the scheduling of follow-up visits for patients with lesions suspected of malignancy.
• Sample Size & Justification: 140 patients. Sufficient to estimate the population percentage of rescheduled procedures with a 95% confidence level and a precision of ± 10 percentage points, assuming p=q=0.5 and a 20% loss-to-follow rate.
• Acceptance Criteria:
  • Increase in the percentage of correctly rescheduled procedures.

  • = 80% agreement between the dermatologist and device regarding rescheduling.

  • Malignancy detection: AUC >= 0.8, sensitivity >= 85%, specificity >= 90%.
  • Diagnostic accuracy: Top-1 >= 50%, Top-3 >= 70%, Top-5 >= 80%.
  • Reduction in waiting time for malignant lesions: >= 30%.
• Timeline: Intended Start: April 2026. Expected Completion: June 2027.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/Sant_Pau_2024/)

Activity A.3: Pilot study for the clinical validation of Legit.Health Plus for automatic triage in primary care teledermatology

• Code: Legit.Health_clinical_VH_2025
• Rationale: Addresses Gap 1. Evaluates the device's effectiveness in the primary care to dermatology referral interface.
• Methodology: Prospective, Multicentre and Interventional study using Legit.Health Plus (version 1.1.0.0). The study assesses how device-provided triage recommendations affect the referral decisions of primary care physicians.
• Sample Size & Justification: 50 patients. Designed as a proof-of-concept pilot study to evaluate feasibility and preliminary effectiveness in a multicentre setting.
• Acceptance Criteria:
  • Diagnostic accuracy: Top-1 >= 50%, Top-3 >= 70%, Top-5 >= 80%.
  • Agreement between device and dermatologist diagnosis: κ > 0.8.
  • Statistically significant reduction of unnecessary referrals: >= 20%.
  • Malignancy detection: AUC >= 0.8, sensitivity >= 75%, specificity >= 80%.
  • Increase in correctly identified and referred "preferent" cases: >= 20%.
  • Reduction of cumulative waiting time for consultations: >= 30%.
• Timeline: Intended Start: April 2026. Expected Completion: April 2027.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/VH_clinical_2025/)

B. Consolidated CER Gap 2: Automated Severity Assessment and Monitoring for Specific Conditions

Confirmatory Validation of Severity Assessment and Monitoring Performance. The PMCF program must generate specific clinical evidence to confirm the performance claims regarding the device's capability to accurately measure and quantify the severity of specific dermatological conditions (e.g., Atopic Dermatitis, Acne, and Frontal Fibrosing Alopecia) against clinical Gold Standards. Consequently, these studies are planned to gather a strong body of evidence to confirm the clinical benefits related to severity assessment and monitoring (Clinical Benefit 5RB) in real-world settings.

Activity B.1: Pilot study for the clinical validation of Legit.Health Plus for quantification of severity and monitoring of FFA

• Code: LEGIT_AFF_EVCDAO_2021
• Rationale: Addresses Gap 2. Validates the hair counting and hair-loss monitoring capabilities for Frontal Fibrosing Alopecia.
• Methodology: Observational and Prospective study using Legit.Health Plus (version 1.1.0.0). The device algorithm's automated hair count is compared against manual specialist hair counting (gold standard).
• Sample Size & Justification: 100 patients. Estimated based on the patient volume at the Dermatology Service of the Ramón y Cajal University Hospital to provide sufficient data for reliability analysis.
• Acceptance Criteria: ICC > 0.75 (good to excellent reliability).
• Timeline: Intended Start: June 2026. Expected Completion: June 2027.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/AFF_2026/)

Activity B.2: Pilot study for the clinical validation of Legit.Health Plus for automatic assessment of severity and monitoring of acne

• Code: Legit.Health_acne
• Rationale: Addresses Gap 2. Validates the ALADIN algorithm for automated acne severity scoring (Clinical Benefit 5RB).
• Methodology: Observational, Single-centre and Interventional study using Legit.Health Plus (version 1.1.0.0). Agreement is measured between the device-calculated acne severity and expert consensus using smartphone photos.
• Sample Size & Justification: 30 patients. Sufficient for a proof-of-concept pilot study to determine the agreement between automated and expert assessment.
• Acceptance Criteria: ICC > 0.75.
• Timeline: Intended Start: April 2026. Expected Completion: November 2026.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/ALADIN 2026/)

Activity B.3: Pilot study for the clinical validation of an automatic EASI scoring system for atopic dermatitis

• Code: Legit_aEASI_HVN
• Rationale: Addresses Gap 2. Validates the automated Eczema Area and Severity Index (EASI) scoring for atopic dermatitis monitoring (Clinical Benefit 5RB).
• Methodology: Retrospective and Single-centre study using Legit.Health Plus (version 1.1.0.0). Compares device-calculated EASI scores against historical expert consensus scores.
• Sample Size & Justification: 100 patients. Sufficient to estimate and detect agreement with a 95% confidence level and a precision of ± 10 percentage points.
• Acceptance Criteria: ICC > 0.75.
• Timeline: Intended Start: Early May 2026. Expected Completion: August 2026.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/aEASI_HVN_2026/)

Activity B.4: Prospective Validation of Legit.Health Plus for Automated Calculation of the Vitiligo Area Scoring Index (AVASI)

• Code: Legit.Health_AVASI
• Rationale: Addresses Gap 2. Validates the AVASI algorithm for vitiligo severity quantification and body surface area measurement.
• Methodology: Prospective, cross-sectional, multicenter and observational study using Legit.Health Plus (version 1.1.0.0).
• Sample Size & Justification: 100 patients (10 per participating center). Designed to achieve sufficient statistical power while maintaining clinical feasibility across multiple sites.
• Acceptance Criteria:
  • Agreement (ICC) for severity assessment: > 0.75.
  • Mean Absolute Error (MAE) for body surface area measurement: < 10%.
  • Bland-Altman analysis: Mean bias < 5 points and 95% LoA within ± 15 units on the VASI scale.
• Timeline: Intended Start: March 2026. Expected Completion: March 2027.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/AVASI_2026/)

Activity B.5: Confirmatory validation of an artificial intelligence algorithm for severity assessment of Hidradenitis Suppurativa

Code: Legit.Health_AIHS_Confirmatory_2026

• Rationale: Addresses Gap 2. Validates and confirms the AIHS4 algorithm for hidradenitis suppurativa severity assessment, expanding the results of the pilot study Legit.Health_AIHS4_2025.
• Methodology: Prospective, observational, multi-reader, multi-case study using Legit.Health Plus (version 1.1.0.0).
• Sample Size & Justification: 100 patients. Designed to achieve sufficient statistical power while maintaining clinical feasibility and to address the sample size limitations observed in the initial AIHS4 study.
• Acceptance Criteria:
  • Agreement (ICC) for severity assessment: > 0.75.
  • Mean Absolute Error (MAE): < 10%.
  • Bland-Altman analysis: Mean bias < 5 points and 95% LoA within ± 15 units on the IHS4 scale.
• Timeline: Intended Start: September 2026. Expected Completion: December 2026.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/AIHS4_2026/)

C. Consolidated CER Gap 3: Core Diagnostic Performance and Stability Monitoring

Monitoring of Sustained Core Algorithmic Performance. The PMCF program must conduct formal, periodic monitoring to demonstrate the sustained stability and effectiveness of the device's core diagnostic algorithms (e.g., accuracy, AUC, Top-N metrics) in the post-market phase, ensuring continued acceptable performance over time.

Activity C.1: Image-based diagnosis non-interventional performance analysis

• Code: PMCF-ICD-DXP-2026
• Rationale: Addresses Gap 3. Ensures the stability of core diagnostic performance across all 346 ICD-11 categories in a multireader setting.
• Methodology: Observational, non-interventional reader study using anonymised data and Legit.Health Plus (version 1.1.0.0).
• Sample Size & Justification: 100 cases and at least 30 readers. Per Obuchowski-Rockette and Hillis framework, 30 readers significantly reduce the Reader-related Variance Component, while 100 cases cover the spectrum of disease severity.
• Acceptance Criteria: AUC > 0.8; Top-5 >= 70%; Top-3 >= 55%; Top-1 >= 40%.
• Timeline: Intended Start: November 2026. Expected Completion: March 2027.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/ICD_DXP_2026/)

Activity C.2: FDA Pivotal Performance Analysis (Legit.Health US Version)

To satisfy FDA 510(k) requirements and confirm real-world performance for the US market, this activity is divided into three distinct studies.

Activity C.2.1: Retrospective Standalone Performance Study

• Rationale: Validates that the device standing alone achieves the required sensitivity for high-risk lesions.
• Methodology: Retrospective, cross-sectional study using an enriched dataset (1:1 malignant to benign ratio) to ensure representation of Fitzpatrick skin phototypes IV-VI and younger patients (< 40 years). Ground truth is consensus histopathology.
• Acceptance Criteria: Diagnostic sensitivity >= 90% for high-risk lesions (Melanoma, BCC, SCC).
• Timeline: Completion March 2027.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/Legit.Health-US-version-1-1-0-0/)

Activity C.2.2: Multi-Reader Multi-Case (MRMC) Second-Read Study

• Rationale: Demonstrates the adjunctive benefit of the device for primary care physicians.
• Methodology: Prospective, blinded, sequential-read study involving 30 board-certified PCPs evaluating 100 cases (50 malignant, 50 benign).
• Acceptance Criteria: Superior diagnostic sensitivity for aided PCPs compared to unaided clinical assessment.
• Timeline: Completion March 2027.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/Legit.Health-US-version-1-1-0-0/)

Activity C.2.3: System Reproducibility and Robustness Study

• Rationale: Proves that diagnostic performance is independent of the image capture hardware.
• Methodology: Prospective, observational, cross-sectional method-comparison study using a repeated measures design on at least 50 lesions captured with various smartphones and dermatoscopes.
• Acceptance Criteria: Overall Percent Agreement (OPA) >= 95% between different validated acquisition systems.
• Timeline: Completion March 2027.
• Protocol Document: R-TF-015-004 Clinical Investigation Plan (Location: clinical/Investigation/Legit.Health-US-version-1-1-0-0/)

Reference to relevant parts of the technical documentation

The objectives and methodology of this PMCF Plan are directly derived from the data, conclusions, and residual risks identified in the following technical documents:

• R-TF-015-003 Clinical Evaluation Report.
• R-TF-015-006 Series Pre-market Clinical Investigation Reports.
• R-TF-013-002 Risk management record.
• Description and specifications.
• R-TF-001-008 Label.
• R-TF-025-004 Summative evaluation protocol.
• R-TF-007-001 Post-Market Surveillance (PMS) Plan.
• Instructions for use.

Estimated date of the PMCF evaluation report

The results and conclusions of the PMCF activities will be documented in the PMCF Evaluation Report. This report will form an integral part of the Periodic Safety Update Report (PSUR), in accordance with Article 86 and Annex XIV, Part B, Section 5 of Regulation (EU) 2017/745. The PSUR will be generated after the first year of market placement of the device and updated on an annual basis, as required for Class IIb devices.

Estimated completion date: The first update is scheduled for one year after initial CE marking (Initial Report) / April 2027 (Full PMCF Report including FDA Pivotal data).

Signature meaning

The signatures for the approval process of this document can be found in the verified commits at the repository for the QMS. As a reference, the team members who are expected to participate in this document and their roles in the approval process, as defined in Annex I Responsibility Matrix of the GP-001, are:

• Author: Team members involved
• Reviewer: JD-003 Design & Development Manager, JD-004 Quality Manager & PRRC
• Approver: JD-001 General Manager

ㅤ