Respiratory Health
Cough Check
A quick cough into your phone reveals signs of respiratory conditions including COVID-19, bronchitis, and TB.
Skin Spot AI
Should I be worried about that skin spot?
Check your skin spots for potential signs of concern with Helfie.
Get HelfieWhat is Skin Spot AI?
Helfie's Skin Spot AI analyses images of skin lesions, classifying them into low, medium, or high-risk categories in seconds.
Skin Spot AI: accuracy by risk level.
-
Low Risk
-
Medium Risk
-
High Risk
How it works Skin Spot AI
When you photograph a skin spot or lesion, Helfie’s Skin Spot AI uses computer vision and deep learning to analyse the image.
First, a convolutional neural network (CNN) identifies the lesion and examines visual characteristics, including its shape, symmetry, borders, colour variations, and texture. The image is then processed by a vision transformer trained on thousands of images of different skin conditions. It analyses your photo to classify the lesion as low, medium, or high risk, providing a personalised assessment to help inform your next steps.
Skin Spot AI - The facts.
What is skin cancer?
Skin cancer is the most common type of cancer globally and can occur in people of all ages and skin types, with an estimated 9.9 million new cases diagnosed each year. Unfortunately, many millions more go undiagnosed.
The three main types are basal cell carcinoma, squamous cell carcinoma, and melanoma. Melanoma is the least common but most dangerous, accounting for the majority of skin cancer deaths.
The incidence of skin cancer is increasing worldwide, with rates up to three times higher than they were in the 1980s in some countries.
Risk factors include exposure to UV radiation from the sun or tanning beds, fair skin, a family history of skin cancer, and a weakened immune system. Read More…
What is skin cancer?
Skin cancer is the most common type of cancer globally and can occur in people of all ages and skin types, with an estimated 9.9 million new cases diagnosed each year. Unfortunately, many millions more go undiagnosed.
The three main types are basal cell carcinoma, squamous cell carcinoma, and melanoma. Melanoma is the least common but most dangerous, accounting for the majority of skin cancer deaths.
The incidence of skin cancer is increasing worldwide, with rates up to three times higher than they were in the 1980s in some countries.
Risk factors include exposure to UV radiation from the sun or tanning beds, fair skin, a family history of skin cancer, and a weakened immune system. Read More…
Why check skin spots?
Not all skin spots are cause for concern, but it's important to understand what they are and whether they could be a sign of something more serious.
Early detection is crucial because it allows for treatment before cancer has a chance to spread to other parts of the body. When detected and treated early, skin cancer is highly curable, but it can be deadly if left untreated or diagnosed at an advanced stage.
Regular skin checks can help identify suspicious moles, spots, or growths that may indicate skin cancer, even in people with no obvious symptoms.
The science.
In testing across a real-world dermatology dataset, Helfie's Skin Spot AI achieved an overall classification accuracy of 83.7% and an AUC of 94.8%.
A Cohen's kappa score of 0.741 indicates strong agreement with reference classifications beyond chance. Performance also remained stable across different skin tones and device conditions.
Got a question? Just ask.
Your personal Health Intelligence (HI) is always there, ready to provide clarity and deeper insights.
Whether you're concerned about a changing mole or want to understand what your risk assessment means, just type or talk to your Health Intelligence to dig deeper and learn more about your skin health.
More to know about Skin Spot AI.
How accurate is Skin Spot AI?
Helfie’s Skin Spot AI uses image-analysis technology to assess skin lesions, with performance tested across a real-world dermatology dataset.
- Accuracy
- Overall classification accuracy: 83.7%
- Low-risk lesion detection: 94.5%
- Medium-risk lesion detection: 87.7%
- High-risk lesion detection: 85.3%
- Area under the curve (AUC): 94.8%
- Cohen’s kappa: 0.741
- Algorithm
- Convolutional neural networks (CNNs), including DenseNet121, ResNet50, and EfficientNet.
- Capture mechanism
- Non-invasive image capture via smartphone camera.
- Training data
Vision transformer fine-tuned using 2,298 annotated dermatology images. - Research and testing
Testing across a real-world dermatology dataset demonstrated stable performance across different skin tones and device conditions.
How does Helfie track changes in your skin health over time?
Helfie keeps a record of your skin spot checks, helping you monitor your results over time.
By regularly snapping photos and tracking changes in your skin, you can see how skin spots evolve and recognise when something may need further attention.
This information can also help your doctor assess changes in your skin and explore potential environmental or lifestyle factors.
How does Health Intelligence work?
Helfie’s Health Intelligence (HI) brings together information from your health checks, conversations, uploads, and history, then connects it with a vast body of medical knowledge to build an increasingly informed picture of your health.
Rather than relying on a single AI model or looking at each result in isolation, HI uses multiple layers of intelligence and machine learning to interpret health signals, connect related information across different areas of your health, and understand those results in the context of you.
It also maintains an active memory of your health journey, so previous results, patterns, and interactions can inform what comes next.
The result is intelligence that is personal, contextual, and designed to help you better understand and manage your health over time.
How do my health checks and conversations work together?
A health check gives your Health Intelligence new information about you. You can then talk to your HI about those results, ask what they mean, explore possible reasons for changes, and understand them in the context of previous checks and health history.
The conversation also becomes part of that context. So when you check again later, your HI can consider both your new results and what it’s learned from earlier checks and conversations.
This is how it builds a more detailed, connected picture of your health over time.
Can I share my check results with my GP?
Helfie makes it easy to share your Skin Spot AI results and skin health trends with your doctor or healthcare provider, giving them additional information to support their assessment.
Sharing results from multiple checks, alongside your symptoms and health history, can help your healthcare provider understand changes over time and make better-informed decisions.
How does Helfie personalise my results?
Helfie’s Skin Spot AI uses key personal details, including your skin type, sun exposure history, and family medical history, to help personalise your assessment.
By considering these factors alongside your skin spot analysis, Helfie can provide more relevant insights into your skin health.
The science behind Skin Spot AI.
Helfie’s checks are backed by the latest research and science.
Explore popular Helfie prompts
Cardiovascular Health
Cardiovascular Health
Cardiovascular Health
Cardiovascular Health
Wellness & Mindfulness
Wellness & Mindfulness
Wellness & Mindfulness
Body & Weight
Body & Weight
Skin Health
Skin Health
Skin Health
Skin Health
Skin Health
Skin Health
Skin Health
Gut Health
Gut Health
Gut Health
Gut Health
Sexual Health
Sexual Health
Sexual Health
Sexual Health
Respiratory Health
Respiratory Health
Respiratory Health
Respiratory Health
