Hacker News Reader

Comment by crdioptnt | Hacker News Reader

The first sign of trouble was chest pains while playing tennis. The pain subsided after a couple of minutes and I was fine. EKG showed no sign of heart attack or major blockage. Prior to that I had no symptoms whatsoever, exercised regularly, never smoked, 57yo male, 6 ft, 175lbs. A CAC scan revealed a calcium score of 411 and a stress test indicated a major lack blood flow to the front of the heart. A cardiac catheterization revealed 95% blockage of the Left Anterior Descending artery, the widowmaker. After placing two stents in the LAD I’m back to normal. It’s a small miracle I didn’t die that day on the tennis court. The CAC definitively diagnosed the life threatening blockage when I had absolutely no symptoms. I recommend everyone get this simple scan to find out if you have this killer inside of you.

View on HN

63, no history of heart disease, all my numbers in the "normal" range, fit, don't smoke, not overweight, good diet, etc. I was building a greenhouse in the back yard and went from feeling kind of "shitty" to classic left chest and back of arm pain.

It's amazing how fast you get into the ER when you come in like that. I got an angiogram within 45 minutes and also had 2 stents in the LAD with 90-95% blockage.

Glad you’re ok. Stories like this are good to rebase myself and remember how important it is to enjoy life now while I can. No matter how healthy I try to keep myself, luck can change things in an instant.

I'm sure your doc already told you this but chest pain while playing tennis that goes away quickly sounds more like angina than a heart attack. IOW your episode was not a heart attack but rather a strong indicator that a future heart attack was likely and that further tests were warranted.

A real heart attack (MI) -- the kind that can kill you quickly -- is usually not exercise related and the pain continues for many tens of minutes without going away.

PSA: If you experience either type of symptom above, call 911. Don't wait around and don't drive yourself to the hospital. Take an aspirin if you have one handy and you're not allergic to it. Real aspirin, not ibuprofen or tylenol.

Since you mentioned take asprin, just curious , how does that help ?

Blood thining characteristics

Aspirin is not a blood thinner per se. It interferes with platelet action so it reduces the likelihood of clots forming.

It prevents platelets from clotting further[1].

[1]: https://www.fda.gov/drugs/safe-use-aspirin/aspirin-questions...

>when I had absolutely no symptoms

Chest pain during excretion is a symptom in my book.

>Recommend everyone to get it

A calcium scan is a ECG gated CT scan(a heart CT). It takes time from the CT machine schedule and it requires radiologists to describe it, meaning it's not infinitely accessible.

> excretion

Heh, I think you mean exertion

I wish cardiovascular monitoring was better. It's not uncommon for cardiologist to discharge you saying 'all fine, EKG ok' even though reality says otherwise.

Happy you got stents at the right time.

EKGs should be extremely easy for AI to identify every disease with a range of probabilities and even some humans can’t identify from EKGs. Do we have the labelled dataset for this?

"It should be very easy for an AI to look at an x-ray, CT, ultrasound or MRI image and tell what disease a human got, even some that humans don't know of.

Are there any labeled datasets "

-Some Software dude, every month since 1971

No the examples you give are extremely difficult compared to the 2D graphs of an EKG. The Apple Watch is clearly doing some fairly accurate inference with a single lead around arrhythmias, for example. I’m really sorry for being enthusiastic about machine learning, I just finished doing an intensive ML bootcamp and it was fun getting results. I also actually have some heart issues so I’d love to see if I could get a result. Thanks for your constructive comment though, I’ve never seen ones like this here before!

>I just finished doing an intensive ML bootcamp

Then maybe learn a bit more about the domain before posting silly things.

I'm not talking about me successfully building an AI that can do better than humans or identify all the worlds heart diseases I'm more looking to have fun and play around with some data (and yes learn more about the domain by doing!). I was maybe a bit too excited about seeing what would happen with a real dataset like this, but it's a hacker news comment not a PhD defence, no need to be so negative. Thanks.

I wonder if all symptoms would show on an EKG though. Would reduced coronary blood flow alter electrical signals ?

That’s what’s fascinating about AI it might find patterns with enough data that we don’t see.

That’s a stress test.

Attach an EKG, have the patient ride a bike with significant exertion.

If there is a lack of blood flow, it will show up in the EKG as alteration of the electrical signals through the heart.

Well I've been subjected to these tests and I fell between the lines, I was clearly below normal health (had trouble walking) but they said there was no issues. So I wondered if there's not more subtleties. Like lag between effort and signals showing up, or vascular issues like micro clotting impeding flow.

EKG changes are a late sign. You need structural imaging like CAC or CCTA or echo.

There is a decent looking dataset available here, let's see my model can generate random numbers from this for each of the diseases: https://www.nature.com/articles/s41597-022-01403-5

Eric Topol has a cool post on "machine eyes" -- using deep learning to identify subtle signals in ECGs and medical images that would be invisible to the naked eye: https://erictopol.substack.com/p/the-amazing-power-of-machin...

There are still regulatory/deployment/reimbursement barriers to cross, but this is happening.

You're assuming EKG is definitive.

I had an EKG last week, the analysis comes back "borderline". Running down every abnormality listed (I know my cardiologist has seen it, didn't consider it notable) has a range of possible causes, including the changes that come with good endurance.

What were your lipids? Was a stress test not conducted?

When did you previously have a stress test before this? Would you also mind sharing what your blood pressure levels were at?

> EKG showed no sign of heart attack

What about troponin? I was told by a Dr that it's more accurate than an EKG.

Edit: I had the word tryptophan before.

Did you mean Troponin? Troponin shows up in the blood when there's been damage to heart muscle.

Yes I meant that! I spelled it wrong on Google, then copy/pasted the wrong word from the suggested replacement.

It’s only if heart muscle dies does that show up, you can have an important artery narrow without symptoms until suddenly a bit of plaque breaks off completely blocking a path causing bits of muscle to actually die.

What I was told in the ER is that troponin basically only shows up when there's been heart muscle damage so is a pretty clear sign. It doesn't show up immediately though - typically a rise within a few hours of the heart attack.

RE: EKGs. There are clear signs in the more detailed 12 lead EKG that can show irregularities in the electrical patterns and specifically help pinpoint the location of the active problem.

For me, it was different.

A cardiologist told me (after a calcium test showed 95th percentile for calcium) that what I was looking for was a rapid drop in ability. Not over a decade, but over a couple weeks or a month. Well, I play ultimate, and one day I realized "I didn't get this winded a month ago". So I got a stress test, and it showed "abnormal motion of the heart wall under stress" (that is, not enough oxygen getting to all the heart muscles). They did a catheterization, and I wound up with two stents.

I mean, look, if you get the chest pains, don't ignore that. But it doesn't have to be that way. If you lose athletic ability, or wind, or endurance, in a short amount of time, get a stress test.

Reply on news.ycombinator.com