DERM (by Skin Analytics)

by Skin Analytics  · Based in United Kingdom → — Building the world's most advanced skin cancer pathways, using AI.
Dermatology Oncology Pathology

Regulatory Status Disclosed

Overview

It aims to triage patients and reduce waiting times for skin cancer assessment. The AI system analyzes dermoscopic images of skin lesions, classifying them as benign or cancerous. DERM is intended for use in the screening, triage, and assessment of skin lesions suspicious for skin cancer in patients aged 18 years or over. It does not provide a definitive diagnosis for skin cancer. DERM is deployed within an imaging clinic prior to a dermatologist appointment, especially for urgent suspected skin cancer referrals. The technology has shown high accuracy in ruling out melanoma (99.7%) and can significantly reduce urgent suspected cancer referrals to secondary care.

Reviewed by Pouyan Golshani, MD — Interventional Radiologist

Key Features

  • Autonomous triage of skin lesions using AI
  • Assessment of dermoscopic images for suspected skin cancer
  • Provides suspected diagnosis and referral recommendation
  • High accuracy in ruling out melanoma (99.7%)
  • Reduces urgent suspected cancer referrals
  • Supports autonomous discharge of low-risk cases
  • Compatible with approved dermoscopic hardware systems and certain smartphones
  • Integration with third-party client software systems via API
  • Post-market surveillance and performance monitoring
  • Classifies 11 different lesion types

Use Cases

  • Triage of urgent suspected skin cancer referrals
  • Streamlining early diagnostic skin cancer assessments in community diagnostic hubs
  • Reducing waiting times for skin cancer assessment
  • Supporting clinical decision-making for primary and secondary care clinicians
  • Automated clinical management tool in skin cancer pathways
  • Remote skin assessment services

What Physicians Need to Know

Evidence Base
DERM is an AI as a Medical Device (AIaMD) that uses deep learning to assess dermoscopic images of skin lesions for suspected skin cancer. [6] It is the first and only Class III CE marked AI as a Medical Device for skin cancer, reflecting the highest level of regulatory scrutiny. [11, 19] The AI is trained on over 110,000 real-world cases from the UK. [9] Skin Analytics maintains an ISO 13485:2016 certified Quality Management System. [4, 27] The performance targets are based on the highest clinical performance published in literature and agreed upon by their Clinical Advisory Committee, which includes leading UK and international dermatologists and health economics experts. [3]
Clinical Validation Studies
Multiple independent evaluations show DERM performs at least as well as dermatologists. [11] A study published in JAMA in 2019 showed DERM identified melanoma with similar accuracy to skin cancer specialists in over 1,500 lesions. [5] Real-world evaluations funded by the Department of Health and Social Care (DHSC) as part of the AI in Health and Care Award, conducted across four NHS sites and 9,649 patients between February 2022 and April 2023, demonstrated high pathway sensitivity for malignant melanoma (97%). [3, 8] DERM achieved a Negative Predictive Value (NPV) for correctly excluding melanoma of 99.8%, compared to 98.9% for dermatologists in a matched-prevalence population. [3, 9] In real-world deployment at two NHS Trusts between July 2021 and October 2022, DERM demonstrated very high sensitivity for detecting melanoma (95.0u2013100.0%) or malignancy (96.0u2013100.0%) across 8,571 lesions. [7] The most recent post-market surveillance data (December 2023 to October 2024) shows DERM exceeding its targets with an NPV for melanoma of 99.93% and sensitivities of 97% for melanoma, 99% for invasive melanoma, 98% for SCC, and 98% for BCC. [11]
Alert Fatigue Management
DERM is designed to reduce the caseload for hospital specialists by autonomously triaging low-risk cases. [3, 7, 9] It can discharge 20-40% of caseload volume by identifying benign lesions, thereby reducing urgent skin cancer referrals. [16] This approach aims to free up dermatology capacity, allowing specialists to prioritize complex cases and reduce unnecessary biopsies. [9, 16, 26] While DERM can operate autonomously, it can also be used with a healthcare professional review (a 'second read') to decide if further assessment is needed. [14, 18]
Override Rate Data
In pathways where a 'second read' by a dermatologist was implemented for cases DERM marked as eligible for discharge, the second reviewer overturned 40-50% of these cases. However, only 1.2% of these overturned cases (for DERM-vA) and none (for DERM-vB) resulted in a skin cancer diagnosis. [6, 7] A Q4 2024 performance report indicated that second reading led to at least 17,461 avoidable dermatologist assessments, finding 22 high-risk skin cancers (including 2 invasive melanomas), which equates to a 0.1% conversion rate. [11]
Differential Diagnosis Support
DERM analyzes dermoscopic images of skin lesions and returns a suspected diagnosis and referral recommendation. [4, 6, 10] It can output a suspected diagnosis of melanoma, squamous cell carcinoma (SCC), basal cell carcinoma (BCC), intraepidermal carcinoma (IEC), actinic keratosis, atypical naevus, or benign. [6, 18] If a lesion exhibits features of more than one lesion type, DERM prioritizes riskier skin conditions by implementing a risk hierarchy in its final analysis to ensure the more severe suspected diagnosis is returned. [4, 18]
Guideline Update Frequency
DERM uses a fixed AI-based algorithm that does not update itself automatically. [18] Skin Analytics is committed to providing the best technology and being transparent about its results, with performance monitoring for AI in clinical use. [3] The company publishes post-market surveillance reports, with analysis based on lesion outcomes. [3] Skin Analytics will continue to support DERM for at least one year after the latest version update. [10, 12] Audits are conducted every 6 months with a sample size of at least 500 patients to ensure DERM continues to perform. [24]
Clinical Workflow Integration
DERM is intended to be integrated with a client system (third-party client software) through which dermoscopic images are submitted for analysis and results are displayed. [4, 10] This integration enables automated clinical management activities, such as triggering patient referral letters. [4, 10] Skin Analytics provides an onboarding process to support client system integration. [4, 10] DERM is currently integrated with existing skin cancer pathways in the NHS, triaging patients before assessment by dermatologists. [8] NHS England has published a toolkit for implementing AI in skin lesion pathways, developed based on good practice and lessons learned from existing DERM implementation sites. [17]
Decision Audit Trail
The service includes a clinical user interface for clinicians to enter case information and manage cases through the configured clinical flow. [16] An administrative interface allows Skin Analytics administrators to manage organizations and conduct administrative functions. [16] Access to user activity audit information is controlled by the client, and user audit data is stored for at least 12 months. [16] Skin Analytics also conducts post-market surveillance and publishes reports on DERM's performance over time. [3, 6, 7]
Physician Tip

DERM is a powerful AI tool for triaging suspected skin cancer, but it's crucial to remember it does not provide a definitive diagnosis. Always integrate DERM's output with all other clinical information for patient management. While DERM can autonomously discharge low-risk cases, consider local pathway guidelines and patient anxiety when communicating results. Ensure images submitted for analysis are captured using approved dermoscopic hardware for optimal accuracy. Stay informed about the latest performance reports and updates from Skin Analytics.

DERM requires integration with a client system via an API. Skin Analytics offers an onboarding process to facilitate this. The system is designed to integrate into existing teledermatology and urgent suspected skin cancer pathways, enabling automated clinical management activities like referral letter generation. It's important to note that DERM is a standalone software device and cannot be white-labeled.

Details

Category Clinical Decision Support & Reference, Dermatology AI, Oncology AI
Pricing Unknown
DeploymentCloud-based, integrated with third-party client software systems
Compliance
BAA AvailableUnknown
HIPAA CompliantUnknown
FDA Status Pending AI-estimated
Integrations
EHR Not specified
Specialties Dermatology, Oncology, Pathology

Ratings & Reviews

No reviews yet. Be the first to review this tool!

Rate DERM (by Skin Analytics)

Clinical Value
Ease of Use
Integration
Support & Docs
Value for Money
No press coverage or publications on file yet. Know of some? Suggest an edit →

Videos

Product demos, reviews, and walkthroughs for DERM (by Skin Analytics).

View all on YouTube

Frequently Asked Questions

DERM is designed to be a seamless addition to your practice. You would typically use DERM to image suspicious lesions during a patient visit, and the AI analysis provides a risk assessment to aid your decision-making regarding biopsy or referral. This can help streamline your diagnostic process and prioritize cases.
Clinical studies have shown DERM to have high sensitivity and specificity in detecting melanoma, often performing comparably to or exceeding the accuracy of general practitioners and even some dermatologists in specific contexts. It acts as a decision support tool, augmenting your expertise rather than replacing it, by providing an objective, AI-driven analysis.
While highly effective, DERM has limitations. It may be less accurate on certain lesion types, such as those on acral or mucosal surfaces, or in patients with very dark skin tones where image quality can be challenging. It's crucial to remember it's a support tool, and clinical judgment remains paramount, especially for ambiguous cases.
Several AI-powered tools are emerging in dermatology. DERM differentiates itself through its extensive validation data, user-friendly interface, and integration capabilities. Its focus on providing clear, actionable risk assessments directly within the clinical workflow is also a key differentiator.
The pricing model for DERM typically involves a subscription or per-use fee, varying based on practice size and usage volume. Reimbursement by insurance can vary by region and specific payer policies, and it's advisable to check with local coding and billing guidelines.
Skin Analytics provides comprehensive training for DERM users, covering device operation, image acquisition best practices, and interpretation of AI results. Ongoing support is also available through dedicated customer service channels, ensuring you can maximize the tool's benefits in your practice.
DERM can enhance patient compliance by providing a clear, objective assessment that can be easily communicated to the patient, fostering a better understanding of the need for follow-up or further action. The digital record-keeping also facilitates organized tracking of suspicious lesions over time.

Related Tools

Stanford University
Stanford University
Clinical Decision Support & Reference
Stanford Online's "AI in Healthcare" program provides a comprehensive overview of artificial intelligence's applications and implications within the medical field.
RADIN Health
RADIN Health
Clinical Decision Support & Reference
RADINA is an AI-powered platform by RADIN Health designed to optimize radiology workflows, enhance diagnostic accuracy, and streamline reporting.
Med-PaLM 2
Google
Clinical Decision Support & Reference
Med-PaLM 2 is a large language model from Google, fine-tuned for healthcare to provide high-quality answers to medical questions and support clinical decision-making.
Pacmed Critical Discharge
Pacmed
Clinical Decision Support & Reference
Pacmed Critical Discharge is an AI tool that predicts the probability of death or readmission within seven days of ICU discharge, providing explainable insights for physicians.
AiZtech Labs
AiZtech Labs
Clinical Decision Support & Reference
AiZtech Labs provides enterprise-grade AI solutions for healthcare, focusing on operational efficiency, diagnostic accuracy, and patient care workflows for providers and health systems.
Stethophone Pro
Sparrow Acoustics
Cardiology AI
Stethophone Pro transforms smartphones into advanced cardiac screening tools, enabling clinicians to capture, interpret, and visualize heart sounds for early detection of cardiovascular diseases.

See all Clinical Decision Support & Reference tools →

Suggest an Edit → | Report an issue | Last Verified: 2026-07-26 | First Added: 2026-07-26
AI Tool Finder
AI-powered search. Results may not be comprehensive.