#AI melanoma good clinical practice

[jcmarchi]

AI’s role in helping to prevent skin cancer through behaviour change - AI News

New Post has been published on https://thedigitalinsider.com/ais-role-in-helping-to-prevent-skin-cancer-through-behaviour-change-ai-news/

AI’s role in helping to prevent skin cancer through behaviour change - AI News

.pp-multiple-authors-boxes-wrapper display:none; img width:100%;

In the past year, we’ve seen remarkable achievements across AI-assisted cancer diagnosis as more and more clinicians test, use and integrate AI companions into daily practice.

Skin cancer is no exception, and we expect AI diagnostic tools to be widely implemented across this clinical arena in the future. What does AI assistance look like for skin cancer? A 2024 study led by researchers at Stanford Medicine compared the performance of clinicians diagnosing at least one skin cancer with and without deep learning-based AI assistance. In an experimental environment, clinicians without AI assistance achieved an average sensitivity of 74.8% while for AI-assisted clinicians, sensitivity was around 81.1%.

What’s intriguing is AI helped medical professionals at all levels, with the largest improvement seen among non-dermatologists.

AI for skin cancer can impact behaviour change

Cancer is on the rise among younger people. According to a study published in BMJ Oncology, the number of under-50s worldwide being diagnosed with cancer has risen by nearly 80% in three decades. And, over the last decade melanoma skin cancer incidence rates have increased by almost two-fifths (38%) with Spain seeing a steady incidence increase of 2.4% during this time.

If detected early enough, skin cancer is easily treated and prognosis is very good. But busy lives and competing concerns mean fewer people are getting checked out, resulting in delays to diagnosis and treatment, which is dramatically changing the survival rates. Those who do, often wait to speak to a doctor. In fact, new research from Bupa, Attitudes Towards Digital Healthcare, indicates only 9% of people would immediately go to get a mole they were concerned about examined by a professional.

However, the same research found that if people were able to have a mole assessed by an AI-powered phone app at the time of their choosing, that percentage increases more than threefold (33%). This signifies emerging technology can have a significant impact on positive behaviour change in healthcare and improve clinical outcome of a potentially severe disease.

Bupa now offer an at-home dermatology tool

At Bupa, we see lots of opportunities to use AI and are exploring its use to enhance patient care, improve operational efficiency, and help our customers to live longer, healthier and happier lives. We know that people want their healthcare partner to be by their side, not just when they are sick, but supporting them constantly to keep them well.

That’s why we launched Blua, our digital healthcare service that’s available in over 200 countries. Blua provides access to three lifechanging healthcare innovations that drive convenience and accessibility. They are virtual consultations so that a customer can connect to a health professional from wherever they choose. Digital health programmesthat allow customers to proactively manage their health and remote healthcare services such as prescription delivery and at home monitoring equipment.  

For customers in Spain, we offer an at-home dermatology assessment service through Blua. How does this work? Customers who’re worried about a skin lesion can take high resolution photos of it using their smartphone. Once taken, the photos are uploaded to Blua and using AI are compared with a database of millions of other images of skin lesions to check for signs of malignancy.

The tool’s algorithms are able to discern between 302 different skin pathologies. If the tool suspects that there is a cause for concern it will let the customer know to book a follow up appointment with a doctor so that it can be looked at further and preventative action can be taken if needed.

The future of healthcare means early detection

Digital healthcare, together with AI, is going to play a crucial role in removing the barriers that stop people from getting health concerns like moles checked out in a timely manner, promoting positive behaviour change that can save lives. This is why Blua is especially useful in today’s fast-paced world where convenience is paramount and virtual consultations and at home tests will empower individuals to prioritise their health, without the need to sacrifice their time. 

(Photo by Nsey Benajah)

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is co-located with other leading events including Intelligent Automation Conference, BlockX, Digital Transformation Week, and Cyber Security & Cloud Expo.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

Tags: AI assistance, Bupa, cancer, healthcare, research

[skinteam]

AI Standards for Healthcare

Are we on the verge of releasing skynet on the world? Not even close, but a set of standards for the application of AI to healthcare is overdue.

Would then stifle innovation or provide us with the landscape to deliver real value to the healthcare industry? That was the question I asked myself time and again after we were recently invited to an event run by Nesta and BSI and attended by other small firms such as the NHS, Google Deep Mind and Babylon Health.

We were all sitting in a rather dreary room along Victoria Embankment here in London debating the role of regulation and standards for AI used in healthcare. At Skin Analytics we’re generally advocates for proportional regulation based on the risks and associated impacts. The new Medical Device regulations are a great step I believe as many Class I products, such as ours, are outside the risk profile that was originally envisaged software was capable being.

Ultimately, the last thing we want to see is innovation being suppressed under volumes of red tape. At the same time, we’re trying to change healthcare, meaning that we’re dealing with people’s health and that’s not an area to “move fast and break things” for fairly obvious reasons.

Back to our dreary room however, and we proposed a number of areas that need to be part of any standards developed in this area but there are two I feel quite strongly about

The first is the requirement for a well designed clinical evaluation that is suitable for the approach and intended use of any AI service. Desk based research just doesn’t cut it in the world of AI. Too often we see the real world performance of an AI system to be significantly below expectations. Only a prospective clinical study can meet this requirement.

The second is defining an algorithm update process that ensures that no AI system in healthcare is evolving without a clear set of acceptance criteria for any modifications to the algorithm. In our world this means building a test set that is held apart from the training data and enables new versions to be benchmarked against the old. 

These shouldn’t stifle innovation in any way. Good clinical evidence is the lifeblood of evidence based medicine and there is simply no way around it. Services that go around the medical community should be closely scrutinised by the regulatory authorities to ensure adequate evidence exists. 

Dispelling the myth that all AI is updating itself in unknown ways is important and defining the release of improved versions of any solution is a core part of any well designed software process. 

Delivering value in healthcare requires any innovator to ensure that they are delivering a quality solution that enhances or improves the health outcomes in a cost effective way. 

That may take longer to deliver and consequently more blood, sweat and tears from founders but it if those principles are at the core of the idea, you will be more likely to achieve your goal. Unless skynet takes over that is.