TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

AI used for skin cancer checks at London hospital

103 pointsby chris_overseasabout 1 month ago

9 comments

floppydiscenabout 1 month ago
This would be such a beautiful use of AI
评论 #43685805 未加载
评论 #43689702 未加载
评论 #43690762 未加载
ircshottyabout 1 month ago
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?
评论 #43686989 未加载
评论 #43686299 未加载
评论 #43686271 未加载
评论 #43687404 未加载
评论 #43687164 未加载
评论 #43730532 未加载
评论 #43687560 未加载
andy99about 1 month ago
<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.
评论 #43686681 未加载
评论 #43688016 未加载
评论 #43685732 未加载
评论 #43687738 未加载
评论 #43686232 未加载
评论 #43688158 未加载
评论 #43686326 未加载
rplntabout 1 month ago
This doesn&#x27;t seem like nothing new? I remember a talk about this being done some 12+ years ago. Just without the AI label to generate hype.
评论 #43687159 未加载
评论 #43687470 未加载
timewizardabout 1 month ago
&gt; 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&#x27;re using AI to solve a problem that probably shouldn&#x27;t exist.
评论 #43686207 未加载
评论 #43686222 未加载
madduciabout 1 month ago
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
xenospnabout 1 month ago
Why go to the hospital at all? Just take the photo at home.
评论 #43685617 未加载
评论 #43686767 未加载
评论 #43686252 未加载
评论 #43686256 未加载
评论 #43685609 未加载
评论 #43685580 未加载
评论 #43688476 未加载
评论 #43685980 未加载
greazyabout 1 month ago
This is ML. I guess AI term can apply here but I think it&#x27;s a bit disingenuous to advertise as such. People will conflate the term with llm chat bots.<p><a href="https:&#x2F;&#x2F;skin-analytics.com&#x2F;wp-content&#x2F;uploads&#x2F;2024&#x2F;06&#x2F;Artificial-intelligence-in-cutaneous-lesions-where-do-we-stand-and-what-is-next.pdf" rel="nofollow">https:&#x2F;&#x2F;skin-analytics.com&#x2F;wp-content&#x2F;uploads&#x2F;2024&#x2F;06&#x2F;Artifi...</a>
评论 #43686380 未加载
lamenameabout 1 month ago
&gt; &quot;At the moment that technology is limited because you need a dermoscopic lens which the public wouldn&#x27;t necessarily have access to, but I&#x27;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.&quot;