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.

DeepHeart: A Neural Network for Predicting Cardiac Health

149 pointsby jisaacsoalmost 9 years ago

10 comments

nharadaalmost 9 years ago
Applying convolutional nets to one dimensional time series data is a fairly common problem in medicine, and the techniques here can certainly transfer to other medical domains. Besides the plethora of opportunities in one dimensional signals (ECG, PCG, PPG, EEG, etc), many medical problems pose similar challenges to machine learning techniques. For example:<p>* Massive class imbalance -- we have much more data for healthy patients than for sick patients, especially at the scales required for deep learning.<p>* Heavy amounts of noise -- Medical imaging is a difficult feat and noise is a fact of life. Not only that, but data is hard to come by and some noise in the labels is likely.<p>* Long term outcomes -- trying to predict diseases or other long term results from signals is very difficult, especially when the outcome is not immediately obvious by looking at the input.<p>TLDR: Imagine that you have to compete in ImageNet, but the images are full of noise, half of the ones labeled &quot;dog&quot; are actually some sort of bird, and instead of guessing what&#x27;s in the image, you&#x27;re given an image and then asked to guess if that image, when painted in watercolor, will make a baby smile.
评论 #12165738 未加载
评论 #12164109 未加载
visargaalmost 9 years ago
It would have been interesting if it were able to do prediction based off a mobile phone sensor (like the heart rate apps).
评论 #12160584 未加载
ascheareralmost 9 years ago
People may also be interested in the Framingham Heart Study[1] which among other things generated the following calculator:<p><a href="http:&#x2F;&#x2F;cvdrisk.nhlbi.nih.gov&#x2F;calculator.asp" rel="nofollow">http:&#x2F;&#x2F;cvdrisk.nhlbi.nih.gov&#x2F;calculator.asp</a><p>[1]: <a href="http:&#x2F;&#x2F;www.framinghamheartstudy.org&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.framinghamheartstudy.org&#x2F;</a>
shas3almost 9 years ago
I know I may be asking to go down a rabbit hole, but:<p>(1) Does the NN use a deep architecture?<p>(2) How does the CNN performance compare with other algorithms?<p>(3) Have you looked at how performance varies with different features, frequency cut-offs, etc.?
评论 #12165847 未加载
knownalmost 9 years ago
Check ST elevation&#x2F;ST depression in <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;ST_segment" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;ST_segment</a>
sscarduzioalmost 9 years ago
This is a great idea. Well done!<p>Can&#x27;t wait we figure out a way to collect these kind of signals in a scalable way.<p>Technology is great, but data is king.
评论 #12160779 未加载
dookahkualmost 9 years ago
How did you find this data, or this competition? I wouldn&#x27;t mind trying my hand at this, either.
评论 #12165850 未加载
andrewfromxalmost 9 years ago
this reminds me of <a href="http:&#x2F;&#x2F;rindexmedical.com" rel="nofollow">http:&#x2F;&#x2F;rindexmedical.com</a> and they have some device like this or some patent...
et2oalmost 9 years ago
I hate to be a jerk, but... what is the point of this entire competition? Physionet audio recordings of heart murmurs? Stethoscopes are on their way out.<p>Cool model, I guess. Does it get us anywhere new? I don&#x27;t know.
评论 #12165871 未加载
signa11almost 9 years ago
why not just use the ecg samples ? that would remove most sources of environmental noise that you have ?