Anecdotally, when I had a potential skin cancer checked at a London hospital they were completely ill-prepared.<p>When I came back to Australia, it was checked and immediately removed as an obvious melanoma.<p>Perhaps the idea of Comparative Advantage also applies to healthcare between countries with natural variances to types of disease?
<p><pre><code> 99% accuracy in diagnosing benign case
</code></pre>
This is meaningless. The only thing that matters in this kind of application is false negative rate at some acceptable false positive rate.<p>I assume whoever is working on this knows that, so this is mostly a criticism of the article. That said, this is a horrible use of AI.
> The hospital gets about 7,000 urgent skin cancer referrals each year, but only 5% turn out to be cancer.<p>It seems to be that you could be doing a _much_ better job of filtering this pipeline before it gets to this point. How can so many _urgent_ cases end up being negative?<p>They're using AI to solve a problem that probably shouldn't exist.
This reminds me of Machine Learning techniques being used at the Policlinico of Bari in collaboration with the Politecnico of Bari, detective cancer, more than 10 years ago
This is ML. I guess AI term can apply here but I think it's a bit disingenuous to advertise as such. People will conflate the term with llm chat bots.<p><a href="https://skin-analytics.com/wp-content/uploads/2024/06/Artificial-intelligence-in-cutaneous-lesions-where-do-we-stand-and-what-is-next.pdf" rel="nofollow">https://skin-analytics.com/wp-content/uploads/2024/06/Artifi...</a>
> "At the moment that technology is limited because you need a dermoscopic lens which the public wouldn't necessarily have access to, but I'm sure with time the technology will advance and we will have effective apps that patients can access from the comfort of their own home."