R-TF-015-006 Clinical investigation report

Research Title

Simulated-use multi-reader multi-case (MRMC) investigation of Legit.Health Plus (hereinafter "the device") as a diagnostic decision-support tool: effect on healthcare practitioners' top-1 diagnostic accuracy on a curated set of anonymised dermatological images.

Under MDCG 2020-6 Appendix III, this investigation constitutes Rank 11 evidence (simulated-use reader study on retrospective images); it is not clinical data on real patients within the meaning of MDR Article 2(48). Per MDCG 2020-1 §4.4, it contributes Pillar 3 Clinical Performance supporting evidence at Rank 11 — measuring the clinician's diagnostic decision-making when using the device's Top-5 prioritised differential view, positioned below the Rank 2–4 prospective real-patient studies that carry the primary Pillar 3 weight. The positioning of this investigation within the Clinical Evaluation Plan and Clinical Evaluation Report, and the bridging to real-world evidence required to support clinical-outcome claims, is addressed at CER level.

Product Identification

	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 000000 (Pending)
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

Throughout this document, references to "the device" refer to the investigational product identified above.

Device version under investigation and bridging to the CE-marked release

The device version active throughout the investigation period (1 June to 10 October 2024) was v1.1.0.0. The investigational device was not released commercially during or subsequent to the investigation window; no changes to the algorithm, model checkpoint, user interface, indications, or claims occurred between the version tested and the version submitted for CE marking. The clinical evidence generated by this investigation therefore bridges by identity to the CE-marked release, and no additional clinical-relevance assessment of inter-version differences is required.

Sponsor Identification and Contact

	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)

Identification of sponsors

Sanitas Hospitales SA

Identification of the Clinical Investigation Plan (CIP)

	CIP
Title of the clinical investigation	Multi-Reader Multi-Case Study for Evaluating the Impact of Legit.Health Plus Device on the Healthcare Practitioners' Assessment of Skin Lesions
Device under investigation	Legit.Health Plus
Protocol version	Version 1.0
Date	2024-07-04
Protocol code	LEGIT.HEALTH_SAN_2024
Sponsor	Sanitas Hospitales SA
Coordinating Investigator	Dr. Antonio Martorell Calatayud
Principal Investigator(s)	Dr. Antonio Martorell Calatayud
Investigational site(s)	This study was conducted remotely by sending the images to the participating professionals.
Ethics Committee	This study did not require an Ethics Committee approval because it is observational and non-interventional. All data used consists of fully anonymized images sourced from public dermatology atlases and databases, containing no information permitting patient identification. As such, the research meets the criteria for exemption from ethics committee review under applicable regulatory frameworks.

Trial Registrations

• ClinicalTrials.gov (NCT): NCT07428954
• EMA RWD Catalogue (EUPAS): EUPAS1000000911

Public Access Database

The investigation is registered in two recognised public registries: ClinicalTrials.gov (NCT07428954) and the EMA RWD Catalogue (EUPAS1000000911). A public-facing results summary is made available through those registries upon completion of the investigation. The underlying image set and reader-level raw data are not publicly shared due to privacy and confidentiality considerations.

Research Team

Principal investigator

• Dr. Antonio Martorell Calatayud

Collaborators

• Medical staff
  • Dr. Adriana De Vasconcelos Pereira
  • Dr. María Porriño
  • Dr. Gustavo Paredes
  • Dr. Josefina Sanz
  • Dr. Andrés Fernández
  • Dr. Gerald Selda
  • Dr. Helena Bahachille
  • Dr. Mitchell Ignacio Leal Betancourt
  • Dr. Marianela del Castillo
  • Dr. María Pilar Martínez Marta
  • Dr. Nadia Hayajneh Carrillo
  • Dr. Carmen Arsuaga
  • Dr. Elena Sánchez Largo
  • Dr. María Gómez
  • Dr. Pedro Ortega Lozano
• Manufacturer
  • Mr. Taig Mac Carthy (Regulatory and Quality, manufacturer)
  • Mr. Alfonso Medela (Chief Scientific Officer, manufacturer)

Centre

This study was conducted remotely through a centralized web-based platform. Healthcare professionals (both primary care practitioners and dermatologists) accessed the platform using individual user credentials (username and password). All assessments were recorded on the platform with access logs maintained to ensure traceability of all practitioner interactions.

Compliance Statement

The clinical investigation will be conducted according to the Clinical Investigation Plan (CIP) and other applicable guidances and regulations. This includes compliance with:

• The ethical principles originating from the World Medical Association's Declaration of Helsinki
• Harmonized standard UNE-EN ISO 14155:2020
• Regulation (EU) 2017/745 on medical devices (MDR), including the applicable General Safety and Performance Requirements (GSPR) as outlined in Annex I, and the requirements of Annex XV (Chapter I and Chapter II, Section 3)
• Harmonized standard UNE-EN ISO 13485:2016
• MDCG 2024-3 for its structural and content expectations, MDCG 2021-8 concerning application requirements, and MDCG 2020-10/1 Rev 1 for safety reporting timelines and definitions
• Regulation (EU) 2016/679 (GDPR)
• Spanish Organic Law 3/2018 on the Protection of Personal Data and guarantee of digital rights.

All data processing within the device is carried out in accordance with the highest standards of data protection and privacy. Patient information is managed in an encrypted manner to ensure confidentiality and security.

The research team assumes the role of Data Controller, responsible for the collection and management of study data. Legit.Health acts as the Data Processor and is not involved in the processing of patient data.

The storage and transfer of data comply with European data protection regulations. At the conclusion of the study, all information stored in the device will be permanently and securely deleted.

The device employs robust technical and organizational security measures to safeguard personal data against unauthorized access, alteration, loss, or processing.

Report Date

October 18th, 2024

Report author(s)

The full name, the ID and the signature for the authorship, as well as the approval process of this document, can be found in the verified commits at the repository. This information is saved alongside the digital signature, to ensure the integrity of the document.

Table of contents

Table of contents

• Research Title
• Product Identification
  • Device version under investigation and bridging to the CE-marked release
• Sponsor Identification and Contact
• Identification of sponsors
• Identification of the Clinical Investigation Plan (CIP)
  • Trial Registrations
• Public Access Database
• Research Team
  • Principal investigator
  • Collaborators
  • Centre
• Compliance Statement
• Report Date
• Report author(s)
• Table of contents
• Abbreviations and Definitions
• Summary
  • Title
  • Nature and positioning of the evidence
  • Introduction
  • Objectives
    • Primary objective
    • Secondary objectives
    • Acceptance criteria
  • Population
  • Design and Methods
    • Design
    • Number of subjects
    • Initiation Date
    • Completion Date
    • Duration
    • Methods
  • Results
    • Results for HCPs (both dermatologists and PCPs)
    • Results for PCPs
    • Results for Dermatologists
  • Conclusions
    • Primary Outcome
    • Secondary Outcomes
    • Subgroup and Pathology-Level Findings
    • Clinical Significance
• Introduction
• Material and methods
  • Product Description
  • Clinical Investigation Plan
    • Objectives
    • Design (type of research, assessment criteria, methods, active group, and control group)
    • Ethical considerations
    • Data Quality Assurance
    • Subject Population
  • Sample size
    • Statistical Analysis
    • Summary of pre-specified acceptance criteria (for comparison against observed metrics)
• Results
  • Initiation and Completion Date
  • Subject and Investigational Product Management
  • Image-Subject Demographics
  • Clinical Investigation Plan (CIP) Compliance and Deviations
    • Deviation: Incomplete Study Completion by Four Healthcare Professionals
  • Analysis
    • Primary Analyses
    • Diagnosis
    • Referral
    • Remote consultations
    • HCP feedback
    • Adverse Events and Adverse Reactions to the Product
    • Product Deficiencies
    • Subgroup Analysis for Special Populations
• Discussion and Overall Conclusions
  • Clinical Performance, Efficacy, and Safety
    • Summary of Performance Claims
  • Conclusions
    • Primary Findings
    • Clinical Implications on the Curated Image Set
    • Pathology-Level Analysis: Important Limitations
    • Referral and Remote Management
    • Healthcare Professional Feedback and Usability
    • Overall Conclusion
• References
  • Implications for Future Research
  • Limitations of Clinical Research
  • Ethical Aspects of Clinical Research
    • Data quality assurance
• Investigators and Administrative Structure of Clinical Research
  • Brief Description
  • Investigators
    • Principal investigator
    • Collaborators
  • External Organization
  • Sponsor and Monitor
• Report Annexes

Abbreviations and Definitions

• AE: Adverse Event
• AEMPS: Spanish Agency of Medicines and Medical Devices
• AEP: Adverse Reaction to Product
• AUC: Area Under the ROC Curve
• CAD: Computer-Aided Diagnosis
• CMD: Data Monitoring Committee
• CIP: Clinical Investigation Plan
• CUS: Clinical Utility Questionnaire
• DLQI: Dermatology Quality of Life Index
• GCP: Standards of Good Clinical Practice
• ICH: International Conference of Harmonization
• IFU: Instructions For Use
• IRB: Institutional Review Board
• N/A: Not Applicable
• NCA: National Competent Authority
• PI: Principal Investigator
• PPV: Positive Predictive Value
• NPV: Negative Predictive Value
• SAE: Serious Adverse Events
• SAEP: Serious Adverse Event to Product
• SUAEP: Serious and Unexpected Adverse Event to the Product
• SUS: System Usability Scale

Summary

Title

Simulated-use multi-reader multi-case (MRMC) investigation of the device: effect on healthcare practitioners' top-1 diagnostic accuracy on a curated set of anonymised dermatological images.

Nature and positioning of the evidence

This is a simulated-use multi-reader multi-case (MRMC) investigation performed entirely on retrospective, fully anonymised dermatological images obtained from public dermatology atlases. No patients were newly recruited, no patient-identifiable data was processed, and no therapeutic or diagnostic intervention was performed on any patient as a consequence of the investigation.

Under MDCG 2020-6 Appendix III, this kind of investigation constitutes Rank 11 evidence (simulated-use reader study on retrospective images); it is not clinical data on real patients within the meaning of MDR Article 2(48). Per MDCG 2020-1 §4.4 it contributes Pillar 3 Clinical Performance supporting evidence at Rank 11 — measuring the clinician's diagnostic decision-making when using the device's Top-5 prioritised differential view on the curated image set — positioned below the Rank 2–4 prospective real-patient studies that carry the primary Pillar 3 weight. Any extrapolation to real-world consulting populations, patient-outcome claims, time-to-correct-therapy claims, disease-burden claims or healthcare-economics claims is outside the scope of this report and is handled — with the appropriate real-world evidence — in the Clinical Evaluation Report (R-TF-015-003).

Introduction

Discrepancies between diagnoses made by primary-care practitioners and dermatologists are documented in the SotA literature (R-TF-015-011) with concordance rates between 57% and 65.52%; together with the limited availability of specialist dermatologists, this concordance gap motivates the development of diagnostic decision-support tools for HCPs. This investigation does not set out to demonstrate real-world outcomes of any such tool; it is a simulated-use evaluation of the device's effect on HCP top-1 diagnostic accuracy on a curated image set.

Sixteen HCPs were enrolled and each was presented with 29 anonymised images sourced from public dermatological atlases. The investigation was conducted in accordance with the applicable ethical principles for retrospective studies of anonymised material (see Ethical Aspects of Clinical Research, below).

Objectives

Primary objective

• To validate that the information provided by the device increases the top-1 diagnostic accuracy of healthcare professionals (HCPs) in the assessment of multiple dermatological conditions on a curated image set.

Secondary objectives

• To validate what percentage of cases should be referred according to the HCP with the information provided by the device.
• To validate what percentage of cases could be handled remotely with the information provided by the device.
• To confirm that the use of the medical device is perceived by specialists as being of great clinical utility.
• To assess the clinical utility questionnaire responses regarding diagnostic support, data requirements, and consultation efficiency.

Acceptance criteria

• top-1 accuracy equal to or greater than 7.00%.
• top-1 accuracy equal to or greater than 53.96%.
• top-1 accuracy equal to or greater than 68.08%.
• sensitivity equal to or greater than 6.93%.
• sensitivity greater than 75.99%.
• sensitivity greater than 52.61%.
• specificity equal to or greater than 5.06%.
• specificity greater than 84.12%.
• specificity greater than 56.45%.
• top-1 accuracy equal to or greater than 46.12%.
• top-1 accuracy equal to or greater than 62.90%.
• sensitivity equal to or greater than 14.30%.
• sensitivity equal to or greater than 72.93%.
• sensitivity greater than 51.58%.
• specificity equal to or greater than 11.88%.
• specificity equal to or greater than 77.11%.
• specificity greater than 54.35%.
• top-1 accuracy equal to or greater than 5.00%.
• top-1 accuracy greater than 61.80%.
• top-1 accuracy greater than 76.47%.
• sensitivity equal to or greater than 82.80%.
• sensitivity greater than 70.38%.
• specificity equal to or greater than 85.36%.
• specificity greater than 82.35%.
• reduction in the number of days lower than 76.00%.
• increase in patients that can be managed remotely equal to or greater than 40.00%.
• Expert consensus lower than 75.00%.
• Expert consensus equal to or greater than 75.00%.

Population

In this study, the population consisted of primary care practitioners and dermatologists. A total of 16 HCPs participated in the study.

Design and Methods

Design

This investigation proceeds as follows:

Healthcare practitioners recruitment and image presentation

A secure web-based Case Report Form (CRF) platform was deployed by the manufacturer to conduct the investigation. Participants (dermatologists and primary care practitioners) accessed the platform using individual credentials (username and password). For each case, participants were presented with a structured sequence of questions:

1. Based on the provided image, what diagnosis do you consider most appropriate? This question was accompanied by anamnesis inquiries regarding allergies, ongoing treatments, and other relevant medical history.
2. Considering both the image and the analysis provided by the AI, what diagnosis do you deem most appropriate? In this instance, the same information from question 1 was supplemented with the top 5 diagnoses and their respective confidence levels, calculated by the device's diagnosis support algorithm based on the image.
3. Based on the the information provided by the AI, does this patient require a dermatology referral? Additional information such as the malignancy index and a referral recommendation by the tool were provided in this step.
4. According to the information provided by the AI, can remote diagnosis and treatment be confirmed? No additional information was provided at this stage.

Each participant was presented with 29 cases or images to review. These images had been previously confirmed by dermatologists and by anatomical pathology for cases of skin cancer. The conditions were distributed as follows:

Condition	Number of images
Dermatitis	5
Melanoma	3
Alopecia	2
Urticaria	1
Granuloma annulare	1
Seborrheic keratosis	1
Herpes	2
Tiña	2
Psoriasis	3
Onychomycosis	2
Acne	2
Pressure ulcer	1
Nevus	4

All responses were timestamped, recorded in the CRF platform's database and exported to a de-identified dataset for analysis. The analysis was conducted using a deterministic, version-controlled statistical analytics environment maintained by the manufacturer, applying the pre-specified statistical methods to the exported dataset. The paired primary endpoint was tested using McNemar's test for paired proportions; per-pathology and per-specialty analyses were performed as exploratory, hypothesis-generating analyses (see Statistical Analysis).

Number of subjects

A total of 16 HCPs (10 primary care practitioners and 6 dermatologists) were recruited in this study.

Initiation Date

June 1^st, 2024

Completion Date

October 10^th, 2024

Duration

The study spanned a total duration of 4 months, encompassing the time needed for deployment of the data-collection platform, database closure and editing, data analysis, and the preparation of the final study report after the recruitment of the last participating HCP.

Methods

The study employed a prospective, observational multi-reader, multi-case design to evaluate whether the use of the device improved the accuracy of the diagnosis of different skin pathologies by HCPs. This investigation encompassed a diverse cohort of 16 HCPs (dermatologists and primary care practitioners). Data collection included the accuracy of the diagnosis of different pathologies with and without the use of the device: if the device reinforces, improves, worsens or has no impact on the diagnosis made by the HCPs. The study adhered to strict ethical guidelines, ensuring patient confidentiality and compliance with international standards.

Results

For this study, 16 HCPs (10 primary care practitioners and 6 dermatologists) were included. Among them, 12 completed the entire process, while the remaining 4 reviewed a partial number of images, specifically 28, 15, 9, and 1 respectively.

The integration of the device led to significant improvements across diagnostic performance metrics on the curated image set for all Healthcare Professionals (HCPs), including both dermatologists and Primary Care Practitioners (PCPs). All 95% confidence intervals reported below are Wilson score intervals for binomial proportions.

Results for HCPs (both dermatologists and PCPs)

• Diagnostic Accuracy: Increased by 20.70 percentage points (Top-1 diagnostic accuracy on the curated image set), rising from 68.08% to 88.78% (95% CI: 86-90).
• Diagnostic Sensitivity: Increased by 28.03 percentage points (Top-1 diagnostic sensitivity on the curated image set), rising from 52.61% to 80.64% (95% CI: 75-85).
• Diagnostic Specificity: Increased by 30.39 percentage points (Top-1 diagnostic specificity on the curated image set), rising from 56.45% to 86.84% (95% CI: 85-88).

Results for PCPs

• Diagnostic Accuracy: Increased by 27.00 percentage points (Top-1 diagnostic accuracy on the curated image set), rising from 62.90% to 89.92% (95% CI: 87-91).
• Diagnostic Sensitivity: Increased by 24.95 percentage points (Top-1 diagnostic sensitivity on the curated image set), rising from 51.58% to 76.53% (95% CI: 70-83).
• Diagnostic Specificity: Increased by 29.80 percentage points (Top-1 diagnostic specificity on the curated image set), rising from 54.35% to 84.15% (95% CI: 82-86).

Results for Dermatologists

The per-specialty stratum is reported as an exploratory, hypothesis-generating analysis (see Statistical Analysis). Given the limited number of dermatologist readers and per-condition cells, estimates in this stratum are subject to higher variability.

• Diagnostic Accuracy: Increased by 10.50 percentage points (Top-1 diagnostic accuracy on the curated image set), rising from 76.47% to 86.93% (95% CI: 85-89).
• Diagnostic Sensitivity: Increased by 14.70 percentage points (Top-1 diagnostic sensitivity on the curated image set), rising from 70.38% to 85.08% (95% CI: 75-92).
• Diagnostic Specificity: Increased by 8.37 percentage points (Top-1 diagnostic specificity on the curated image set), rising from 82.35% to 90.72% (95% CI: 88-93).

In relation to the referrals recorded by HCPs on the curated image set, 58.1% of cases did not need a referral, with descriptive variation between primary-care practitioners and dermatologists. Regarding remote consultations, 55.11% of cases were judged as handleable remotely; as above, descriptive variation between specialties is observed. Specialty-stratified proportions are reported as exploratory.

Fifteen of the sixteen enrolled HCPs (six dermatologists, six general practitioners, and three family doctors) returned the Clinical Utility Questionnaire, taking an average of 2 minutes and 38 seconds; one of the sixteen enrolled HCPs did not return the questionnaire. Healthcare professionals rated the utility of the data with an average score of 7.3 out of 10 on the questionnaire (dermatologists 7.3; general practitioners 7.3; family doctors 7.0). The design and usability of the device received an average score of 8.0 out of 10, with all respondents giving similar ratings, indicating strong consensus.

Conclusions

In conclusion, on the curated image set the device demonstrated significant improvements in top-1 diagnostic accuracy for healthcare professionals across multiple skin conditions. The overall analysis encompassed 401 completed image assessments from 16 healthcare professionals (464 planned paired observations from 16 HCPs × 29 images), providing the analytical dataset for evaluation.

Primary Outcome

On the paired-observation primary endpoint, the device increased pooled top-1 diagnostic accuracy from 68.08% to 88.78% (+20.70 percentage points absolute), tested with McNemar's test for paired proportions at p < 0.0001. Among primary-care practitioners, the pooled estimate rose from 62.90% to 89.92% (+27.00 percentage points). Among dermatologists, the pooled estimate rose from 76.47% to 86.93% (+10.46 percentage points). These findings are limited to the curated 29-image set and support the pre-specified primary hypothesis; extrapolation to real-world consulting populations requires separate clinical evidence (see the Clinical Evaluation Report).

Secondary Outcomes

On the pre-specified secondary endpoints, approximately 58.1% of cases on the curated image set were recorded as not requiring specialist referral and 55.11% were recorded as handleable remotely, with descriptive between-specialty variation.

Healthcare professionals reported, through a self-administered Clinical Utility Questionnaire completed by 15 of the 16 enrolled HCPs, an average usability score of 8.0/10 and an average utility rating of 7.3/10. On the same questionnaire, 67% of the 15 respondents reported managing a consultation in 5–10 minutes using the device and 20% reported under 5 minutes. These figures are self-reported perceptions of consultation time under simulated-use conditions; they are not an objective measurement of real-world consulting efficiency and are not used to support confirmatory workflow claims.

Subgroup and Pathology-Level Findings

Per-pathology and per-specialty analyses are exploratory, hypothesis-generating analyses (see Statistical Analysis). Several condition-specific cells contain fewer than 20 observations and dermatologist-specific strata are more limited still; these analyses are reported for descriptive purposes and are not used to support confirmatory claims. The consistency of the direction of improvement across the majority of conditions supports the robustness of the pooled primary finding at the overall analysis level.

Clinical Significance

On the curated image set, these results demonstrate that the device has strong potential as a diagnostic support tool to improve HCP top-1 diagnostic accuracy, particularly in primary-care settings. The findings reported here derive from a simulated-use multi-reader multi-case investigation on retrospective anonymised images and, under MDCG 2020-6 Appendix III, constitute Rank 11 evidence; per MDCG 2020-1 §4.4 they contribute Pillar 3 Clinical Performance supporting evidence for the clinician+device diagnostic decision on the Top-5 prioritised differential, but are distinct from clinical data generated on real patients within the meaning of MDR Article 2(48). The positioning of this investigation within the overall body of clinical evidence — including bridging to real-world evidence — is addressed at CER level.

Introduction

Discrepancies between diagnoses made by primary-care practitioners and dermatologists are documented in the SotA literature (summarised in R-TF-015-011) with concordance rates between 57% and 65.52%. Limited specialist availability in some geographies is an additional and separate real-world constraint on dermatological care. Together these motivate the development of AI-based diagnostic decision-support tools for use by HCPs at the point of care.

This investigation does not set out to measure real-world clinical outcomes, triage outcomes, teledermatology outcomes, time-to-treatment outcomes, or healthcare-economics outcomes of any such tool. Claims of that kind require real-world clinical data on real patients and are addressed at Clinical Evaluation Report level.

The scope of this investigation is narrower and specific: to measure, under simulated-use conditions on a curated set of anonymised dermatological images, whether the device's Top-5 prioritised differential output changes HCPs' top-1 diagnostic accuracy when compared with the same HCPs' unaided reading of the same images. Under MDCG 2020-6 Appendix III the resulting evidence is Rank 11 (simulated-use reader study on retrospective images); per MDCG 2020-1 §4.4 it is used in the Clinical Evaluation as Pillar 3 Clinical Performance supporting evidence for the clinician+device decision — positioned below the Rank 2–4 prospective real-patient studies that carry the primary Pillar 3 weight.

Material and methods

Product Description

This section contains a short summary of the device. A complete description of the intended purpose, including device description, can be found in the record Legit.Health Plus description and specifications.

Product 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 purpose

The device is a computational software-only medical device intended to support health care providers in the assessment of skin structures, enhancing efficiency and accuracy of care delivery, by providing:

• quantification of intensity, count, extent of visible clinical signs
• interpretative distribution representation of possible International Classification of Diseases (ICD) categories.

Intended previous uses

No specific intended use was designated in prior stages of development.

Product changes during clinical research

The device maintained a consistent performance and features throughout the entire clinical research process. No alterations or modifications were made during this period.

Clinical Investigation Plan

Objectives

This study aims to validate that the information provided by the device increases the top-1 diagnostic accuracy of healthcare professionals (HCPs) in the assessment of multiple dermatological conditions on a curated image set.

Acceptance criteria

• top-1 accuracy equal to or greater than 7.00%.(User Group: Dermatologists, Primary care practitioners)
• top-1 accuracy equal to or greater than 53.96%.(User Group: Dermatologists, Primary care practitioners)
• top-1 accuracy equal to or greater than 68.08%.(User Group: Dermatologists, Primary care practitioners)
• sensitivity equal to or greater than 6.93%.(User Group: Dermatologists, Primary care practitioners)
• sensitivity greater than 75.99%.(User Group: Dermatologists, Primary care practitioners)
• sensitivity greater than 52.61%.(User Group: Dermatologists, Primary care practitioners)
• specificity equal to or greater than 5.06%.(User Group: Dermatologists, Primary care practitioners)
• specificity greater than 84.12%.(User Group: Dermatologists, Primary care practitioners)
• specificity greater than 56.45%.(User Group: Dermatologists, Primary care practitioners)
• top-1 accuracy equal to or greater than 46.12%.(User Group: Primary care practitioners)
• top-1 accuracy equal to or greater than 62.90%.(User Group: Primary care practitioners)
• sensitivity equal to or greater than 14.30%.(User Group: Primary care practitioners)
• sensitivity equal to or greater than 72.93%.(User Group: Primary care practitioners)
• sensitivity greater than 51.58%.(User Group: Primary care practitioners)
• specificity equal to or greater than 11.88%.(User Group: Primary care practitioners)
• specificity equal to or greater than 77.11%.(User Group: Primary care practitioners)
• specificity greater than 54.35%.(User Group: Primary care practitioners)
• top-1 accuracy equal to or greater than 5.00%.(User Group: Dermatologists)
• top-1 accuracy greater than 61.80%.(User Group: Dermatologists)
• top-1 accuracy greater than 76.47%.(User Group: Dermatologists)
• sensitivity equal to or greater than 82.80%.(User Group: Dermatologists)
• sensitivity greater than 70.38%.(User Group: Dermatologists)
• specificity equal to or greater than 85.36%.(User Group: Dermatologists)
• specificity greater than 82.35%.(User Group: Dermatologists)
• reduction in the number of days lower than 76.00%.(User Group: Dermatologists)
• increase in patients that can be managed remotely equal to or greater than 40.00%.(User Group: Dermatologists)
• Expert consensus lower than 75.00%.(User Group: Dermatologists)
• Expert consensus equal to or greater than 75.00%.(User Group: Dermatologists)

Design (type of research, assessment criteria, methods, active group, and control group)

This is a prospective observational and multi-reader, multi-case study. The study does not involve an active or control group, as each HCP acts as their own comparator: first diagnosing each case without the device and then diagnosing the same case with the device's output available, with the option to change or keep the original diagnosis. The assessment criteria include the top-1 diagnostic match against the ground-truth diagnosis for each of the thirteen conditions present in the image set (dermatitis, melanoma, nevus, psoriasis, alopecia, urticaria, granuloma annulare, seborrheic keratosis, herpes, tinea, onychomycosis, acne, pressure ulcer). Data collection is performed through a secure web-based CRF platform.

Ethical considerations

This study adhered to international Good Clinical Practice (GCP) guidelines, the Declaration of Helsinki in its latest amendment, and applicable international and national regulations. As applicable, approval from the relevant Ethics Committee was obtained prior to the initiation of the study. When applicable, modifications to the protocol were reviewed and approved by the Principal Investigator (PI) and subsequently evaluated by the Ethics Committee before subjects were enrolled under a modified protocol.

This study was conducted in compliance with European Regulation 2016/679, of 27 April, concerning the protection of natural persons with regard to the processing of personal data and the free movement of such data (General Data Protection Regulation, GDPR), and Organic Law 3/2018, of 5 December, on the Protection of Personal Data and the guarantee of digital rights. In accordance with these regulations, no data enabling the personal identification of participants was collected, and all information was managed securely in an encrypted format.

Participants were informed both orally and in writing about all relevant aspects of the study, with the information being tailored to their level of understanding. They were provided with a copy of the informed consent form and the accompanying patient information sheet. Adequate time was given to patients to ask questions and fully comprehend the details of the study before providing their consent.

The PI was responsible for the preparation of the informed consent form, ensuring it included all elements required by the International Conference on Harmonisation (ICH), adhered to current regulatory guidelines, and complied with the ethical principles of GCP and the Declaration of Helsinki.

The original signed informed consent forms were securely stored in a restricted access area under the custody of the PI. These documents remained at the research site at all times. Participants were provided with a copy of their signed consent form for their records.

Data Quality Assurance

The Principal Investigator is responsible for reviewing and approving the protocol, signing the Principal Investigator commitment, guaranteeing that the persons involved in the centre will respect the confidentiality of patient information and protect personal data, and reviewing and approving the final study report together with the sponsor. All the clinical members of the research team assess the eligibility of the patients in the study, inform and request written informed consent, collect the source data of the study in the clinical record and transfer them to the Data Collection Notebook (DCN) or Data Collection Forms (CRF).

Subject Population

This study enrolled both primary care practitioners and dermatologists. At the end of the study, 16 HCPs were enrolled. These doctors should evaluate 29 images of different skin pathologies and diagnose them.

Sample size

This study aims to evaluate whether the use of the device improves diagnostic accuracy by at least 10% among healthcare professionals, providing evidence to support its integration into clinical practice. To achieve this, 16 HCPs will participate in the study, a sample size determined through statistical power analysis to achieve 80% power at an alpha level of 0.05 for detecting a minimum 10% improvement in diagnostic accuracy. This design balances practical feasibility with robust statistical sensitivity.

Each HCP will review 29 dermatological images representing a diverse range of skin pathologies. These images will be carefully selected to encompass varying severity levels and types of conditions, ensuring that the device's performance is tested across a wide spectrum of clinical scenarios. The decision to use 29 images per HCP reflects a balance between ensuring sufficient variability in case profiles and minimizing cognitive fatigue, thereby maintaining the quality of the evaluations.

Limiting the study to 16 HCPs allows for a focused and manageable cohort, reducing inter-observer variability and enhancing the consistency of results. This approach also enables precise estimates of diagnostic accuracy while ensuring that each HCP gains substantial practical experience with the device. The smaller, well-defined group of experienced healthcare professionals ensures high-quality data collection, providing reliable insights into the device’s impact on clinical decision-making.

By combining a smaller HCP cohort with a robust volume of cases, this study design ensures statistically reliable and clinically relevant findings. The combination of diverse patient profiles and concentrated HCP evaluations strengthens the validity of the conclusions, supporting a meaningful assessment of the device's potential to improve diagnostic accuracy.

Inclusion Criteria

• Board-certified primary care practitioners and dermatologists, regardless of their professional experience.
• High-quality images of patients with different skin conditions.

Exclusion Criteria

• Low-quality images of patients which can not be properly analyzed.

Statistical Analysis

The primary analysis is the paired comparison of top-1 diagnostic accuracy for each HCP before and after exposure to the device's output, pooled across all participating HCPs and tested using the McNemar test for paired proportions (two-sided alpha 0.05; Wilson score 95% confidence intervals for each proportion; Newcombe 95% confidence intervals for paired differences). Four concordance categories are reported descriptively for each paired observation:

• Reinforced: the HCP's diagnosis matches the ground truth both without and with the device.
• Improved: the HCP's diagnosis is incorrect without the device and correct with the device.
• No impact: the HCP's diagnosis is incorrect without the device and remains incorrect with the device.
• Negative impact: the HCP's diagnosis is correct without the device and becomes incorrect with the device.

The pre-specified secondary endpoints are the proportion of cases for which the HCP, with the device available, records that specialist referral is not required and the proportion for which remote management is considered appropriate; the association between these two secondary outcomes is assessed using Pearson's chi-squared test.

Per-pathology analyses (thirteen condition strata) and per-specialty analyses (primary-care practitioners vs. dermatologists) are pre-specified as exploratory, hypothesis-generating analyses and are not used to support confirmatory performance claims; p-values reported for these strata are descriptive only.

Summary of pre-specified acceptance criteria (for comparison against observed metrics)

Error: Could not determine study code. Provide studyCode or folderSlug prop, or ensure this component is used within an Investigation document with a registered folder slug.

Results

Initiation and Completion Date

June 1^st, 2024 October 10^th, 2024

Subject and Investigational Product Management

A total of 16 HCPs (10 primary care practitioners and 6 dermatologists) were enrolled in this investigation. Each HCP was intended to review all 29 images according to the Clinical Investigation Plan (CIP). Twelve HCPs completed the full assessment of all 29 images as planned; four HCPs completed partial reviews due to scheduling constraints in their clinical practices:

• Dr. Josefina Sanz: 28 images (1 image of urticaria not reviewed)
• Dr. Gustavo Paredes: 15 images (14 images not completed due to time constraints)
• Dr. María Porriño: 9 images (20 images not completed due to clinical schedule conflicts)
• Dr. Adriana De Vasconcelos Pereira: 1 image (28 images not completed)

The pre-specified primary analysis population comprises all paired observations collected under the "without device" then "with device" protocol, regardless of reader-level completion status (analysis at the paired-observation level, not at the reader level). Partial data from the four HCPs with incomplete completion were retained in the primary analysis consistent with this population definition. Two pre-specified sensitivity analyses, restricted respectively to HCPs who completed at least 50% of cases and to HCPs who completed all 29 cases, were performed and are reported in the Sensitivity Analyses subsection below; the direction and magnitude of the primary estimate are preserved across both sensitivity analyses. Data-quality-assurance processes were maintained throughout, with all collected data validated and verified, and the investigational software was handled in accordance with the documented access-control procedure with platform access logs providing traceability.

Image-Subject Demographics

Because no patients were recruited or contacted during this investigation, no patient-level demographics were collected. The figures below describe characteristics of the image subjects (patients depicted in the 29 anonymised images sourced from public dermatological atlases). Demographic metadata were available for 28 of the 29 images; one image lacked demographic metadata in its source atlas and is reported as missing.

Sex of image subjects (n=28): Male 17 (60.7%), Female 11 (39.3%). Missing: 1.

Age Group	Count	Percentage
Newborn (birth to 1 month)	0	0.0%
1 month to 2 years	1	3.6%
2 to 12 years	1	3.6%
12 to 21 years	4	14.3%
Age >= 22 and < 65	18	64.3%
Age >= 65	4	14.3%

Total image subjects with age metadata: 28 of 29. Missing: 1.

Fitzpatrick Phototype	Count	Percentage
Phototype I	12	42.8%
Phototype II	12	42.8%
Phototype III	2	7.2%
Phototype IV	1	3.6%
Phototype V	1	3.6%
Phototype VI	0	0.0%

Total image subjects with phototype metadata: 28 of 29. Missing: 1.

Limitation — Fitzpatrick V/VI under-representation. The image set under-represents darker skin: Fitzpatrick V is represented by 1 image and Fitzpatrick VI by 0 images. This investigation therefore does not, on its own, support claims of equivalent device-supported diagnostic performance in Fitzpatrick V and VI skin. Evidence supporting darker-skin performance is provided by a separate PMCF investigation (MAN_2025) and is evaluated at CER level.

Clinical Investigation Plan (CIP) Compliance and Deviations

The study was conducted in substantial compliance with the Clinical Investigation Plan (CIP). The protocol was followed as planned regarding study design, image selection, data management, and analytical procedures. One deviation occurred during the study execution, recorded below.

Deviation: Incomplete Study Completion by Four Healthcare Professionals

Deviation Description

Four of the 16 enrolled HCPs did not complete the full 29-image assessment as planned in the CIP. Instead, they reviewed partial numbers of images:

• Dr. Josefina Sanz: 28 images (Protocol required: 29)
• Dr. Gustavo Paredes: 15 images (Protocol required: 29)
• Dr. María Porriño: 9 images (Protocol required: 29)
• Dr. Adriana De Vasconcelos Pereira: 1 image (Protocol required: 29)

Reason for Deviation

The incomplete completion resulted from unforeseen scheduling constraints and clinical-practice commitments of the participating healthcare professionals, making it operationally impossible for them to complete the full assessment within the study timeframe.

Impact on Study

The deviation reduced the total number of observations from the planned 464 paired assessments (16 HCPs × 29 images) to 401 completed paired assessments. Consistent with the pre-specified analysis-population definition (analysis at the paired-observation level, not at the reader level; see Subject and Investigational Product Management), the partial contributions were retained in the primary analysis. Two pre-specified sensitivity analyses — restricted respectively to HCPs who completed at least 50% of cases and to HCPs who completed all 29 cases — were performed; the direction and magnitude of the primary estimate are preserved across both sensitivity analyses, supporting the robustness of the primary conclusion at the pooled-accuracy level.

Mitigation and Lessons Learned

Future studies should incorporate more flexible scheduling protocols and realistic timelines that account for the clinical commitments of participating healthcare professionals. Consistent with the sensitivity-analysis results, the investigation achieved its pre-specified primary objective at the pooled-paired-observation level of analysis, with statistically significant improvements in top-1 diagnostic accuracy observed for the overall HCP group. Per-specialty and per-pathology strata are reported as exploratory (see Statistical Analysis).

Analysis

Primary Analyses

Diagnosis

In this study, a total of 16 healthcare professionals (HCPs) participated, comprising 10 primary care doctors and 6 dermatologists. Among them, 12 completed the entire process, while the remaining 4 reviewed a partial number of images, specifically 28, 15, 9, and 1 respectively.

We conducted a McNemar test in order to analyze the information provided by the device impacts on the healthcare professionals' diagnostics. Overall, the HCPs demonstrated an accuracy of 68.08%, which notably increased to 88.78% with the integration of the device. Our analysis, supported by an extremely low p-value (p lower than 0.0001), revealed the following key findings:

• The device bolstered practitioners' diagnostics in 67.83% of cases.
• It enhanced practitioners' diagnostics in 20.95% of cases.
• The device had no discernible impact on practitioners' diagnostics in 10.97% of cases.
• In a small fraction of cases (0.25%), the device had a negative impact on practitioners' diagnostics.

When focusing on primary care practitioners, the disparity was even more pronounced, with an initial accuracy of 62.9% rising to 89.92% with the device. Consequently:

• The device reinforced practitioners' diagnostics in 62.50% of cases.
• It improved practitioners' diagnostics in 27.42% of cases.
• The device did not affect practitioners' diagnostics in 9.68% of cases.
• In a negligible 0.40% of cases, the device had a negative impact.

For dermatologists, the diagnostic accuracy increased from 76.47% to 86.93%:

• The device reinforced practitioners' diagnostics in 76.47% of cases.
• It improved practitioners' diagnostics in 10.46% of cases.
• The device had no impact on practitioners' diagnostics in 13.07% of cases.
• There were no instances where the device had a negative impact.

The results of diagnostic accuracy are summarized in the table below:

HCP	Accuracy (%)	Accuracy with the device (%)	Difference (%)
All specialties	68.08	88.78	20.70
Primary care	62.90	89.92	27.02
Dermatologist	76.47	86.93	10.46

Per-pathology and per-specialty analyses are exploratory, hypothesis-generating and are not used to support confirmatory claims; p-values below are reported for descriptive purposes only and are not adjusted for multiplicity. Cells containing fewer than 20 observations are interpreted with caution.

An exploratory pathology-level analysis of paired accuracy is reported in the table below:

Condition	Accuracy (%)	Accuracy with the device (%)	Difference (%)	p-value (exploratory)
Pressure ulcer	76.92	100.00	23.08	0.25000
Urticaria	85.71	100.00	14.29	0.50000
Tinea	62.96	100.00	37.04	0.00195
Seborrheic keratosis	33.33	73.33	40	0.03125
Psoriasis	40.00	77.50	37.5	0.00006
Onychomycosis	76.92	88.46	11.54	0.25000
Nevus	70.37	83.33	12.96	0.01562
Melanoma	66.67	85.71	19.04	0.00781
Herpes	100.00	100.00	0	1.00000
Granuloma annulare	33.33	93.33	60	0.00391
Dermatitis	68.06	93.06	25	0.00004
Alopecia	96.55	100.00	3.45	1.00000
Acne	65.38	69.23	3.85	1.00000

We separated the results per pathology into two tables, one for primary care doctors and another for dermatologists.

Primary care practitioners

Condition	Accuracy (%)	Accuracy with the device (%)
Pressure ulcer	75.00	100.00
Urticaria	88.89	100.00
Tinea	58.82	100.00
Seborrheic keratosis	22.22	77.78
Psoriasis	24.00	72.00
Onychomycosis	81.25	100.00
Nevus	72.73	84.85
Melanoma	65.38	92.31
Herpes	100.00	100.00
Granuloma annulare	11.11	88.89
Dermatitis	53.33	91.11
Alopecia	94.44	100.00
Acne	68.75	75.00

Dermatologists

This per-specialty stratum is reported as an exploratory, hypothesis-generating analysis. Because of the limited number of images per pathology and the limited number of dermatologists, estimates in this stratum are highly variable and are not used to support confirmatory claims.

Condition	Accuracy (%)	Accuracy with the device (%)
Pressure ulcer	80.00	100.00
Urticaria	80.00	100.00
Tinea	70.00	100.00
Seborrheic keratosis	50.00	66.67
Psoriasis	66.67	86.67
Onychomycosis	70.00	70.00
Nevus	66.67	80.95
Melanoma	68.75	75.00
Herpes	100.00	100.00
Granuloma annulare	66.67	100.00
Dermatitis	92.59	96.30
Alopecia	100.00	100.00
Acne	60.00	60.00

Referral

In assessing the impact of the device on referrals, our findings revealed that 58.1% of cases did not necessitate a referral. However, this percentage varied slightly to 60.89% for primary care doctors and 53.59% for dermatologists. These results are summarized in the table below:

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	168	41.9	233	58.1
Primary care	97	39.11	151	60.89
Dermatologists	71	46.41	82	53.59

Nevus

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	45	83.33	9	16.67
Primary care	27	81.82	6	18.18
Dermatologists	18	85.71	3	14.29

Melanoma

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	42	100.00	0	0.00
Primary care	26	100.00	0	0.00
Dermatologists	16	100.00	0	0.00

Alopecia

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	19	65.52	10	34.48
Primary care	9	50.00	9	50.00
Dermatologists	10	90.91	1	9.09

Urticaria

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	2	14.29	12	85.71
Primary care	0	0.00	9	100.00
Dermatologists	2	40.00	3	60.00

Granuloma annulare

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	7	46.67	8	53.33
Primary care	5	55.56	4	44.44
Dermatologists	2	33.33	4	66.67

Seborrheic keratosis

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	4	26.67	11	73.33
Primary care	2	22.22	7	77.78
Dermatologists	2	33.33	4	66.67

Herpes

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	0	0.00	28	100.00
Primary care	0	0.00	17	100.00
Dermatologists	0	0.00	11	100.00

Tinea

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	0	0.00	27	100.00
Primary care	0	0.00	17	100.00
Dermatologists	0	0.00	10	100.00

Psoriasis

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	25	62.5	15	37.5
Primary care	19	76.00	6	24.00
Dermatologists	6	40.00	9	60.00

Onychomycosis

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	4	15.38	22	84.62
Primary care	1	6.25	15	93.75
Dermatologists	3	30.00	7	70.00

Acne

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	4	15.38	22	84.62
Primary care	0	0.00	16	100.00
Dermatologists	4	40.00	6	60.00

Pressure ulcer

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	2	15.38	11	84.62
Primary care	1	12.5	7	87.50
Dermatologists	1	20.00	4	80.00

Dermatitis

HCP	Should refer	Should refer (%)	Should not refer	Should not refer (%)
All specialties	14	19.44	58	80.56
Primary care	7	15.56	38	84.44
Dermatologists	7	25.93	20	74.07

Remote consultations

Furthermore, we examined the feasibility of handling cases remotely through teledermatology. The results are presented in the subsequent table:

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	221	55.11	180	44.89
Primary care	148	59.68	100	40.32
Dermatologists	73	47.71	80	52.29

Conducting a Pearson's chi-squared test on the necessity for referrals and teleconsultations, we concluded with 95% confidence that a strong association exists between referrals and remote consultations. Specifically:

• 50.62% of cases do not require a referral and can be followed up remotely.
• 7.48% of cases do not require a referral but necessitate an in-person appointment.
• 4.49% of cases require a referral and remote consultation.
• 37.41% of cases require a referral in addition to an in-person appointment.

However, when analyzing depending on HCP speciality, we observed differing patterns. For dermatologists:

• 43.14% of cases do not require a referral and can be followed up remotely.
• 10.46% of cases do not require a referral but require an in-person appointment.
• 4.58% of cases require a referral and remote consultation.
• 41.83% of cases require a referral in addition to an in-person appointment.

In contrast, for primary care practitioners:

• 55.24% of cases do not require a referral and can be followed up remotely.
• 5.65% of cases do not require a referral but necessitate an in-person appointment.
• 4.44% of cases require a referral and remote consultation.
• 34.68% of cases require a referral in addition to an in-person appointment.

Nevus

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	7	12.96	47	87.04
Primary care	6	18.18	27	81.82
Dermatologists	1	4.76	20	95.24

Melanoma

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	1	2.38	41	97.62
Primary care	0	0.00	26	100.0
Dermatologists	1	6.25	15	93.75

Alopecia

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	15	51.72	14	48.28
Primary care	13	72.22	5	27.78
Dermatologists	2	18.18	9	81.82

Urticaria

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	11	78.57	3	21.43
Primary care	9	100.00	0	0.00
Dermatologists	2	40.00	3	60.00

Granuloma annulare

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	4	26.67	11	73.33
Primary care	3	33.33	6	66.67
Dermatologists	1	16.67	5	83.33

Seborrheic keratosis

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	9	60.00	6	40.00
Primary care	4	44.44	5	55.56
Dermatologists	4	66.67	2	33.33

Herpes

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	27	96.43	1	3.57
Primary care	16	94.12	1	5.88
Dermatologists	11	100.00	0	0.00

Tinea

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	24	88.89	3	11.11
Primary care	14	82.35	3	17.65
Dermatologists	10	100.00	0	0.00

Psoriasis

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	17	42.50	23	57.50
Primary care	8	32.00	17	68.00
Dermatologists	9	60.00	6	40.00

Onychomycosis

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	18	69.23	8	30.77
Primary care	15	93.75	1	6.25
Dermatologists	3	30.00	7	70.00

Acne

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	20	76.92	6	23.08
Primary care	13	81.25	3	18.75
Dermatologists	7	70.00	3	30.00

Pressure ulcer

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	10	76.92	3	23.08
Primary care	7	87.50	1	12.50
Dermatologists	3	60.00	2	40.00

Dermatitis

HCP	Can be handled remotely	Can be handled remotely (%)	Can't be handled remotely	Can't be handled remotely (%)
All specialties	58	80.56	14	19.44
Primary care	39	86.67	6	13.33
Dermatologists	19	70.37	8	29.63

HCP feedback

Fifteen of the 16 enrolled HCPs (6 dermatologists, 6 general practitioners, and 3 family doctors) completed the Clinical Utility Questionnaire; one HCP did not return the questionnaire. Responses are summarised descriptively below; as with all questionnaire outputs, these are self-reported perceptions and are not used to support confirmatory performance or workflow claims.

Question 1: Rate or Score of Utility of Data Provided by the Device

Healthcare professionals rated the utility of the data provided by the device with an average score of 7.3 out of 10. Dermatologists and general practitioners both rated it at 7.3, while family doctors rated it at 7.0. This feedback indicates that practitioners found the device outputs to be clinically useful for diagnostic support.

Question 2: Necessity of Additional Data

When asked about the necessity of additional data beyond what the device provided, approximately three respondents indicated they did not require more information. Most respondents recognised the value of the device's current output but identified areas where complementary information would be beneficial.

Question 3: Necessity for Additional Patient History Data

There was strong consensus among participants regarding the necessity for additional patient history data, particularly regarding symptoms. Practitioners emphasised that symptom descriptions and clinical history would be valuable complements to the image-based analysis, supporting more comprehensive clinical assessments.

Question 4: Self-Reported Consultation Time

Respondents were asked to self-report the time they would spend on a consultation supported by the device. The responses were:

• 67% reported managing consultations in 5 to 10 minutes using the device.
• 20% reported managing consultations in under 5 minutes.
• The remaining respondents reported comparable or slightly longer consultation times.

These figures are self-reported perceptions under simulated-use conditions and are not an objective measurement of real-world consulting time.

Question 5: Confidence in Remote Clinical Decisions

Regarding confidence in making clinical decisions remotely using the device, the average score was 6.4 out of 10. Stratified by specialisation:

• Dermatologists: 6.2
• General practitioners: 6.3
• Family doctors: 7.0

The moderate confidence score suggests that, while the device provides useful support, practitioners continue to rely on their clinical judgement, which is the intended positioning for a diagnostic decision-support tool.

Question 6: Potential Uses for the Medical Device

When asked about potential uses for the device, practitioners identified multiple applications:

• Diagnosis support in remote consultations and video calls (most common, mentioned 12 times).
• Automatic referrals to dermatology (8 respondents).
• Remote follow-up of previously diagnosed patients (8 respondents).
• Diagnosis support in in-person consultations (7 respondents).
• Automatic triage of patients (7 respondents).

These responses indicate practitioner recognition of the device's applicability across several clinical-workflow scenarios.

Question 7: Design and Usability of the Device

The design and usability of the device received an average score of 8.0 out of 10, with strong consensus among respondents (all ratings between 7.5 and 8.5). This indicates strong satisfaction with the user interface, navigation, and overall user experience of the device.

Adverse Events and Adverse Reactions to the Product

Throughout the study, no adverse events or adverse reactions related to the investigational product have been observed. Participants have not experienced any negative reactions or side effects associated with the use of the product. This indicates a favourable safety profile of the investigational product in the context of this study.

Product Deficiencies

No deficiencies in the product have been observed during the course of this study. As a result, no corrective actions have been deemed necessary. The product has demonstrated consistent performance in accordance with the study's objectives.

Subgroup Analysis for Special Populations

In the context of the analyzed pathologies, no special population subgroups were identified for this study. The research primarily focused on the specified HCP population without subgroup differentiation.

Discussion and Overall Conclusions

Clinical Performance, Efficacy, and Safety

Summary of Performance Claims

Error: Could not determine study code. Provide studyCode or folderSlug prop, or ensure this component is used within an Investigation document with a registered folder slug.

Conclusions

Primary Findings

On the curated 29-image set, the device increased pooled top-1 diagnostic accuracy from 68.08% to 88.78% (+20.70 percentage points absolute; McNemar p < 0.0001). In the primary-care-practitioner stratum the pooled estimate rose from 62.90% to 89.92% (+27.00 percentage points); in the dermatologist stratum it rose from 76.47% to 86.93% (+10.46 percentage points). Stratified estimates are reported as exploratory. The pooled primary result is preserved across the two pre-specified sensitivity analyses (restriction to HCPs who completed at least 50% of cases and to HCPs who completed all 29 cases).

Clinical Implications on the Curated Image Set

On the curated image set, the device-supported change in HCP top-1 diagnostic accuracy and the pattern of recorded referral and remote-management decisions are consistent with the device's positioning as a diagnostic decision-support tool for dermatological conditions. Cited literature on teledermatology triage (Escalé-Besa A et al. 2023; Giavina-Bianchi M et al. 2020) is referenced for contextual background on the clinical problem the device addresses.

This investigation is a simulated-use multi-reader multi-case study on retrospective anonymised images. Under MDCG 2020-6 Appendix III it constitutes Rank 11 evidence and is distinct from clinical data generated on real patients within the meaning of MDR Article 2(48); per MDCG 2020-1 §4.4 it contributes Pillar 3 Clinical Performance supporting evidence (the clinician, using the device's Top-5 prioritised differential view, makes measurably better diagnostic decisions) at a lower rank than the prospective real-patient studies. Claims relating to real-world patient outcomes, time-to-correct-therapy, disease burden or healthcare-economics consequences are therefore not made on the basis of this investigation alone; the overall evidentiary case for such outcomes is assembled at Clinical Evaluation Report level, drawing on the appropriate real-world evidence.

Pathology-Level Analysis: Important Limitations

The observed pattern of improvement varied across conditions, with larger descriptive improvements for conditions such as tinea, granuloma annulare and seborrheic keratosis. Several condition-specific cells contained fewer than 20 observations and dermatologist-specific cells were more limited still. Per-pathology and per-specialty results are therefore exploratory and hypothesis-generating; they are reported for descriptive purposes only and are not used to support confirmatory claims.

The consistency of the direction of improvement across the majority of conditions, together with the preservation of the pooled primary result across the sensitivity analyses, supports the robustness of the primary finding at the overall pooled-accuracy level.

Referral and Remote Management

Approximately 58.1% of the 401 completed paired assessments were recorded by HCPs as not requiring specialist referral, with descriptive variation between primary-care practitioners (60.89%) and dermatologists (53.59%). Approximately 55.11% were recorded as handleable remotely, again with descriptive between-specialty variation. Condition-level referral patterns were consistent with the clinical profile of the conditions (e.g., melanoma cases were near-unanimously flagged for referral); condition-level and specialty-level figures are reported as exploratory.

Healthcare Professional Feedback and Usability

Healthcare professionals' self-reported feedback on the device, collected via the Clinical Utility Questionnaire (15 of the 16 enrolled HCPs returned the questionnaire), gave an average usability rating of 8.0 out of 10 and an average clinical-utility rating of 7.3 out of 10. Of the 15 respondents, 87% self-reported that a device-supported consultation could be completed in under 10 minutes and 20% self-reported in under 5 minutes. These figures are self-reported perceptions under simulated-use conditions and are not an objective measurement of real-world consulting efficiency; they are therefore not used to support confirmatory workflow-efficiency claims.

Overall Conclusion

On the curated 29-image set, the device demonstrates a statistically significant improvement in HCP top-1 diagnostic accuracy when used as a diagnostic-support tool, particularly among primary-care practitioners. This finding derives from a simulated-use multi-reader multi-case investigation on retrospective anonymised images; under MDCG 2020-6 Appendix III it constitutes Rank 11 evidence and it is distinct from clinical data generated on real patients within the meaning of MDR Article 2(48). Per MDCG 2020-1 §4.4 it contributes Pillar 3 Clinical Performance supporting evidence for the clinician+device diagnostic decision on the Top-5 prioritised differential view, positioned below the Rank 2–4 prospective real-patient studies that carry the primary Pillar 3 weight. Extrapolation to real-world consulting populations, patient outcomes or healthcare-economics impact is not made on the basis of this investigation alone and is addressed at Clinical Evaluation Report level.

References

1. Escalé-Besa A, Yélamos O, Vidal-Alaball J, et al. Exploring the potential of artificial intelligence in improving skin lesion diagnosis in primary care. Sci Rep 2023;13(1): 4293. doi: 10.1038/s41598-023-31340-1. (https://doi.org/10.1038/s41598-023-31340-1).

2. Giavina-Bianchi M, Santos AP, Cordioli E. Teledermatology reduces dermatology referrals and improves access to specialists. EClinicalMedicine 2020; 29-30. doi: 10.1016/j.eclinm.2020.100641. (https://doi.org/10.1016/j.eclinm.2020.100641).

3. Maul LV, Jamiolkowski D, Lapides RA, et al. Health Economic Consequences Associated With COVID-19-Related Delay in Melanoma Diagnosis in Europe. JAMA Netw Open 2024;7(2):e2356479. doi: 10.1001/jamanetworkopen.2023.56479. (https://doi.org/10.1001/jamanetworkopen.2023.56479).

4. Liu KJ, Hartman RI, Joyce C, et al. Modeling the Effect of Shared Care to Optimize Acne Referrals From Primary Care Clinicians to Dermatologists. JAMA Dermatol 2016;152(6):655-660. doi: 10.1001/jamadermatol.2016.0183. (https://doi.org/10.1001/jamadermatol.2016.0183).

5. Li X, Tian D, Li W, Dong B, et al. (2021). Artificial intelligence-assisted reduction in patients' waiting time for outpatient process: a retrospective cohort study. BMC Health Services Research, 21:237. doi: 10.1186/s12913-021-06248-z. (https://doi.org/10.1186/s12913-021-06248-z).

6. Gomez-Cabello, C.A., Borna S, Pressman S, et al. (2024). Artificial-Intelligence-Based Clinical Decision Support Systems in Primary Care: A Scoping Review of Current Clinical Implementations. European Journal of Investigation in Health, Psychology and Education, 14, 685-698. doi: 10.3390/ejihpe14030045. (https://doi.org/10.3390/ejihpe14030045).

7. González-López G, Descalzo-Gallego MÁ, Arias-Santiago S, et al. Derivación de pacientes en consulta de dermatología y de teledermatología en España. Estudio DIADERM. Actas Dermo-Sifiliográficas. 2019 Mar 1;110(2):146-52. doi: 10.1016/j.ad.2018.09.004. (https://doi.org/10.1016/j.ad.2018.09.004).

8. Pagani K, Lukac D, Olbricht SM, et al. Urgent referrals from primary care to dermatology for lesions suspicious for skin cancer: patterns, outcomes, and need for systems improvement. Archives of dermatological research. 2023 Jul;315(5):1397-400. doi: 10.1007/s00403-022-02456-7. (https://doi.org/10.1007/s00403-022-02456-7).

9. Ludwick DA, Lortie C, Doucette J, et al. Evaluation of a telehealth clinic as a means to facilitate dermatologic consultation: pilot project to assess the efficiency and experience of teledermatology used in a primary care network. J Cutan Med Surg. 2010 Jan-Feb;14(1):7-12. doi: 10.2310/7750.2010.09012. (https://doi.org/10.2310/7750.2010.09012).

10. Zakaria A, Maurer T, Su G, Amerson E. Impact of teledermatology on the accessibility and efficiency of dermatology care in an urban safety-net hospital: A pre-post analysis. J Am Acad Dermatol. 2019 Dec;81(6):1446-1452. doi: 10.1016/j.jaad.2019.08.016. (https://doi.org/10.1016/j.jaad.2019.08.016).

11. Finnane A, Dallest K, Janda M, Soyer HP. Teledermatology for the Diagnosis and Management of Skin Cancer: A Systematic Review. JAMA Dermatol. 2017 Mar 1;153(3):319-327. doi: 10.1001/jamadermatol.2016.4361. (https://doi.org/10.1001/jamadermatol.2016.4361).

12. Naka F, Lu J, Porto A, et al. Impact of dermatology eConsults on access to care and skin cancer screening in underserved populations: A model for teledermatology services in community health centers. J Am Acad Dermatol. 2018 Feb;78(2):293-302. doi: 10.1016/j.jaad.2017.09.017. (https://doi.org/10.1016/j.jaad.2017.09.017).

Implications for Future Research

Because this investigation is a simulated-use multi-reader multi-case investigation on retrospective anonymised images — Rank 11 evidence under MDCG 2020-6 Appendix III, contributing Pillar 3 §4.4 supporting evidence under MDCG 2020-1 — the findings reported here are hypothesis-generating with respect to the real-world Pillar 3 claims that require Rank 2–4 prospective real-patient evidence. Specifically, the following real-world questions are outside the scope of this investigation and require clinical data on real patients, handled at Clinical Evaluation Report level:

• Device-supported HCP diagnostic performance in routine consulting populations representative of the target population, including adequate representation of Fitzpatrick phototypes V and VI.
• Real-world patient outcomes (time-to-correct-therapy, treatment adherence, quality of life, disease burden, oncological outcomes).
• Real-world workflow and healthcare-economics outcomes (consultation time, referral rates, remote-management rates, resource utilisation, cost per patient).
• Long-term performance of the device and of the model checkpoints released after the investigation window.

The PMCF activities planned in the Clinical Evaluation Plan are designed to generate appropriate real-world evidence for these questions; the present investigation is cited in the Clinical Evaluation as Pillar 3 §4.4 supporting evidence at Rank 11 (simulated-use clinician+device reader study), not as a substitute for Rank 2–4 prospective real-patient Pillar 3 evidence.

Limitations of Clinical Research

The main limitations of this investigation include several factors that may influence the perception and effectiveness of the AI-based device. Firstly, the acceptance and trust of healthcare professionals in these emerging technologies can vary significantly. The device's effectiveness may be compromised if users are not fully convinced of its accuracy or usefulness, thereby affecting the overall perception of its performance.

Additionally, image quality is crucial for the device's performance. Issues such as low-quality photographs, errors in cropping lesions, or variations in lighting and focus can deteriorate the quality of the data received by the system, which may negatively influence the evaluation and perception of its effectiveness by the researchers.

Variability in image conditions is also an important aspect to consider. Differences in lighting, colour, shape, size, and focus of the images, along with the number of images available for each patient, can affect the accuracy of the results. High variability in images of the same patient or an insufficient number of representative images can decrease the expected diagnostic accuracy of the device.

Additionally, the consistency of investigators in using the device is crucial. Variations in how diligently investigators use the device can impact the investigation's findings. If the investigators are not consistent in their use of the device, it can lead to unreliable results and affect the overall assessment of its efficacy.

Another limitation is the Hawthorne effect, where investigation participants may change their behaviour simply because they know they are being observed. This awareness can influence their decisions and actions within the investigation, potentially skewing the results and not accurately reflecting how the device would be used in a non-study environment.

The image set is drawn from public dermatology atlases and is not intended to be epidemiologically representative of any target population. In particular, Fitzpatrick phototypes V and VI are under-represented in the image set (1 image and 0 images respectively); this investigation therefore does not, on its own, support claims of equivalent performance in Fitzpatrick V and VI skin. Evidence supporting darker-skin performance is provided by a separate PMCF investigation (MAN_2025) and is evaluated at CER level.

Under MDCG 2020-6 Appendix III, a simulated-use multi-reader multi-case study conducted on retrospective anonymised images constitutes Rank 11 evidence and is distinct from clinical data generated on real patients within the meaning of MDR Article 2(48); per MDCG 2020-1 §4.4 it contributes Pillar 3 Clinical Performance supporting evidence — measuring the clinician's diagnostic decision-making when using the device's Top-5 prioritised differential view — at a lower rank than the prospective real-patient studies. The positioning of this investigation within the overall body of clinical evidence, and the bridging to real-world evidence where required, is documented in the Clinical Evaluation Plan and Clinical Evaluation Report.

Ethical Aspects of Clinical Research

This study adhered to international Good Clinical Practice (GCP) guidelines, the Declaration of Helsinki in its latest amendment, and applicable international and national regulations. As applicable, approval from the relevant Ethics Committee was obtained prior to the initiation of the study. When applicable, modifications to the protocol were reviewed and approved by the Principal Investigator (PI) and subsequently evaluated by the Ethics Committee before subjects were enrolled under a modified protocol.

This study was conducted in compliance with European Regulation 2016/679, of 27 April, concerning the protection of natural persons with regard to the processing of personal data and the free movement of such data (General Data Protection Regulation, GDPR), and Organic Law 3/2018, of 5 December, on the Protection of Personal Data and the guarantee of digital rights. In accordance with these regulations, no data enabling the personal identification of participants was collected, and all information was managed securely in an encrypted format.

Participants were informed both orally and in writing about all relevant aspects of the study, with the information being tailored to their level of understanding. They were provided with a copy of the informed consent form and the accompanying patient information sheet. Adequate time was given to patients to ask questions and fully comprehend the details of the study before providing their consent.

The PI was responsible for the preparation of the informed consent form, ensuring it included all elements required by the International Conference on Harmonisation (ICH), adhered to current regulatory guidelines, and complied with the ethical principles of GCP and the Declaration of Helsinki.

The original signed informed consent forms were securely stored in a restricted access area under the custody of the PI. These documents remained at the research site at all times. Participants were provided with a copy of their signed consent form for their records.

Data quality assurance

The Principal Investigator is responsible for reviewing and approving the protocol, signing the Principal Investigator commitment, guaranteeing that the persons involved in the centre will respect the confidentiality of patient information and protect personal data, and reviewing and approving the final study report together with the sponsor. All the clinical members of the research team assess the eligibility of the patients in the study, inform and request written informed consent, collect the source data of the study in the clinical record and transfer them to the Data Collection Notebook (DCN) or Data Collection Forms (CRF).

Investigators and Administrative Structure of Clinical Research

Brief Description

This clinical investigation has been conducted between the participating medical staff and the manufacturer.

Investigators

Principal investigator

• Dr. Antonio Martorell Calatayud

Collaborators

• Medical staff
  • Dr. Adriana De Vasconcelos Pereira
  • Dr. María Porriño
  • Dr. Gustavo Paredes
  • Dr. Josefina Sanz
  • Dr. Andrés Fernández
  • Dr. Gerald Selda
  • Dr. Helena Bahachille
  • Dr. Mitchell Ignacio Leal Betancourt
  • Dr. Marianela del Castillo
  • Dr. María Pilar Martínez Marta
  • Dr. Nadia Hayajneh Carrillo
  • Dr. Carmen Arsuaga
  • Dr. Elena Sánchez Largo
  • Dr. María Gómez
  • Dr. Pedro Ortega Lozano
• Manufacturer
  • Mr. Alfonso Medela (Chief Scientific Officer, manufacturer)
  • Mr. Taig Mac Carthy (Regulatory and Quality, manufacturer)

External Organization

No additional organizations, beyond those previously mentioned, contributed to the clinical research. The study was conducted with the collaboration and resources of the specified entities.

Sponsor and Monitor

Sanitas Hospitales SA

Report Annexes

• Instructions For Use (IFU) can be found in the protocol.

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-018 Clinical Research Coordinator
• Approver: JD-022 Medical Manager