The goal of this observational study is to learn if an artificial intelligence (AI) tool helps primary care practitioners better identify skin conditions. The study focuses on adults with suspected skin pathologies, including tumor, inflammatory, and infectious diseases. The main questions it aims to answer are: * Does using the AI tool help doctors make more accurate diagnoses for multiple skin conditions? * Does the tool help doctors better decide which patients need a referral to a dermatologist and which can be managed in primary care? * Are doctors satisfied with how well the tool works and how easy it is to use in their daily work? * Can the tool help doctors more accurately differentiate between benign lesions and skin cancer? Participants will: * Visit their primary care doctor for a regular skin checkup. * Have photos taken of their skin condition using a smartphone or a dermatoscope. * Provide informed consent for their photos and basic health information (such as age and sex) to be analyzed by the AI tool. * Receive standard care from their doctor, with the tool providing a second opinion to assist in the clinical decision-making process.
This prospective, observational study evaluates the clinical utility of an artificial intelligence (AI)-based computational software device designed to support primary care practitioners (PCPs) and dermatologists in managing skin pathologies. The research explores whether the device can enhance diagnostic accuracy and optimize the referral process from primary care to specialized dermatology services. Study Methodology and Design The investigation is designed as an analytical study of a clinical case series. Key technical aspects include: * Investigational Tool: A software-only medical device using computer vision algorithms to analyze images of the epidermis and dermis to provide clinical data for assessment. * Participant Roles: 15 HCPs (including PCPs and dermatologists) evaluated with a cohort of over 100 patients. * Procedural Workflow: PCPs captured skin images using smartphones or mobile dermatoscopes, uploaded them to the platform, and provided a diagnosis guided by the AI results. * Evaluation Baseline: HCPs acted as their own controls, allowing for a comparison of diagnostic performance with and without the AI tool. Quality Assurance and Registry Procedures To ensure the integrity of the data collected within this organized system, several quality control measures were implemented: * Data Validation and Checks: The database utilized consistency rules and logical ranges to control errors during tabulation. Computerized validation filters automatically identified missing values or inconsistencies based on predefined rules. * Source Data Verification (SDV): A designated independent clinical monitor performed verification of anonymized source documents (e.g., image files and clinical records) against Case Report Forms (CRFs) to ensure accuracy and completeness. * Monitoring Plan: The research team held quarterly meetings to address data collection issues, while the monitor conducted remote and, if necessary, on-site visits to ensure compliance with the Clinical Investigation Plan (CIP) and ISO 14155 standards. * Missing Data Management: Manual editing and exploratory statistical techniques were used to detect and resolve logical errors or inconsistent values before the database was considered closed. Sample Size and Statistical Principles The study was powered to detect a 10% improvement in diagnostic accuracy. * Assessment Power: A sample size of 100 patients was determined to provide a 95% confidence level with an 80% power and a margin of error between 9% and 10%. * Analytical Techniques: Central tendency and variability statistics (mean, SD) were used for quantitative variables, while qualitative variables were analyzed through frequency distributions. * In addition to parametric tests, the McNemar test was used to analyze the specific impact of AI on HCP diagnostic choices. Statistical significance was set at alpha = 0.05. For qualitative data, Fisher's exact or Chi-square tests were employed. Statistical significance was set at alpha = 0.05. Safety and Ethical Standards The study complied with Regulation (EU) 2017/745 (MDR) and ISO 14155:2021. Data protection followed GDPR and Spanish Organic Law 3/2018, utilizing encrypted patient information and alphanumeric identification codes to maintain participant anonymity. All clinical data stored on the device is permanently deleted upon study conclusion.
Study Type
OBSERVATIONAL
Enrollment
131
The device is a computer vision software designed to assist healthcare practitioners in assessing skin structures through the analysis of digital images. Primary care practitioners utilize the device by capturing photographs of affected skin areas with a smartphone or mobile dermatoscope and uploading them to the platform. The software processes images of the epidermis and dermis to quantify visible clinical signs-including intensity, count, and extent-and provides an interpretive distribution of possible International Classification of Diseases (ICD) categories. Practitioners use the platform's results as a second medical opinion to guide diagnosis, triage, and referral decisions for pathologies including tumoral (benign and malignant), inflammatory, and infectious conditions. The intervention also provides clinicians with access to specific referral criteria, clinical questionnaires, and basic treatment
Puerta de Hierro Majadahonda University Hospital
Majadahonda, Madrid, Spain
Referral appropriateness
This metric evaluates the appropriateness of patient referrals from primary care to specialized dermatology services. A referral is classified as "avoidable" or "unnecessary" when both the primary care practitioner and the expert dermatologist agree that the case can be effectively managed within primary care without a specialist consultation. The study's primary target for this metric was a minimum increase in referral adequacy of 15%. This threshold represents the minimum clinically important difference required to demonstrate the device's utility in optimizing clinical workflows and reducing healthcare costs.
Time frame: Baseline
Area Under the ROC Curve (AUC) for Malignancy Detection
This measure utilizes the Area Under the ROC Curve (AUC) to evaluate the device's discriminatory performance in differentiating between malignant lesions (including melanoma and basal cell carcinoma) and benign lesions. The AUC provides a comprehensive assessment of the tool's ability to correctly classify skin pathologies across various decision thresholds. The predefined acceptance criterion for this metric was an AUC $\\ge$ 80%. This threshold ensures that the device provides clinically meaningful support in identifying high-risk cases that require urgent specialist intervention.
Time frame: Baseline
Healthcare Professional Satisfaction (CUS Score)
Satisfaction is evaluated using the Clinical Utility and Satisfaction (CUS) Questionnaire. This validated assessment tool measures practitioners' perspectives on the device's diagnostic support, ease of use, data utility, and overall clinical applicability within their workflow. Results from the questionnaire are quantified either as a percentage of affirmative responses or as a mean score on a 10-point scale. This dual approach allows for both a qualitative understanding of practitioner consensus and a quantitative measure of perceived value.
Time frame: 4 months (practitioners completed the questionnaire twice: once at 2 months and again at 4 months after starting the study).
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.