Comment by Unklejoe | Hacker News Reader

Comment by Unklejoe | Hacker News Reader

On a somewhat related note:

The Apple Watch gave me a false positive for atrial fibrillation. I was having premature ventricular contractions (PVCs), which are _generally_ benign as long as your heart has no structural abnormalities. Basically, your left ventricle contracts spontaneously on its own in beteeen regular beats, which throws off the timing of the next beat. The end result is an irregular heart beat, similar to that of atrial fibrillation, but can be easily distinguished by human inspection of the EKG.

Needless to say, the result scared the crap out of me. I made an appointment at the cardiologist the next day, and I couldn’t sleep until I was finally able to see him. The stress from this actually made the PVCs more frequent...

The cardiologist took one look at the EKG strip from the watch and was able to identify the abnormalities as PVCs rather than afib. He still had me wear a holter monitor for 48 hours though. It turns out I had over 38,000 PVCs in two days, which is a large enough amount to cause concern about the risk of cardiomyopathy (“they” say under 10,000 per day is okay as long as they’re not bothering you).

So, at the end of the day, I’m glad I got the alert. I probably wouldn’t have gone to the doctor if not.

I do hope they improve the classification though so that it can distinguish between afib and PVCs.

I am working on algorithms related to PVC and AFib detection. I can see why the app might make that mistake. PVCs and AFib are not mutually exclusive, and AFib can be "paroxysmal", meaning it doesn't occur all the time. Basically the way AFib "works" is that instead of steady and constant p-waves, where all the cells in the atria contract in one swoop (as they should), the excitation of the cells spreads chaotically without a clear beginning and end.

Of course, as a Human watching an ECG you can recognize the PVCs at one glance. AFib can be a lot harder to see, and it can start and stop. Also, AFib seems to be less of a problem than high PVC counts, speaking in general terms. Of course, don't take this as medical advice, I'm just a Veterinarian...

> PVCs and AFib are not mutually exclusive

Right. I didn’t mean to imply that they were, just that the watch misinterpreted frequent PVCs as being afib.

In my case, it was easy to determine that they were PVCs with a normal underlying rhythm because the underlying rhythm was steady like clockwork, and the PVCs were occurring in a telltale bigeminal pattern for a few seconds at a time.

> Also, AFib seems to be less of a problem than high PVC counts

I’m no doctor, but this doesn’t align with what I’ve been reading. It seems like they don’t even recommend treatment for PVCs most of the time unless they’re symptomatic. In extreme cases like mine (20,000/day), there’s a chance that it can weaken the heart over time, but I’m not sure how this compares to the risk of stroke for untreated afib sufferers. I’ve heard mentions of PVCs being an indicator for increased sudden cardiac death risk, but I can’t find any reference for this pertaining to people with otherwise normal hearts. I think it may be the case for people who have just had a heart attack or something though.

From what I gather, occasional singleton PVCs are generally harmless and occur in almost everyone. Apparently, the issue arises when you start having multiple PVCs in a row without a regular beat in between. After three in a row, it’s considered non-sustained ventricular tachycardia, which is very dangerous, I guess because there’s a chance it might never stop?

Once again, not a doctor, so please correct me if I’m wrong. This will probably show up in someone’s Google search one day.

I think PVCs in high counts can accompany more serious problems, like AV Block etc. I had read somewhere that AFib is often not treated. Maybe a statement about what is more serious in general isn't possible because both symptoms can be found in serious conditions.

Afib itself is hard to fix, but persistent Afib causes clotting which can lead to strokes, and sufferers are often put on blood thinners to help minimise their stroke risk.

There are medications to achieve "cardioversion", meaning transitioning the atria to a coordinated rhythm. Another way is to insert a catheter and use electric shocks to reset the myocardium.

But yes, it's not easy.

For AFib, is there likely to be much predictive ability for the watch? Would the watch be able to warn of an onset of AFib before the wearer is aware of it? I was wondering if it was worth buying one for my dad, who has AFib attacks about 3-4 times a year.

The watch is probably not completely reliable, and I don't know how good it is, but from my preliminary experiments in detecting AFib I would guess the detection should be quite useful.

Such a watch is probably faster and easier than any other option. Probably not as reliable as 24H ECG for catching transient AFib or a doctor-assessed ECG for manifest AFib, but a lot better than nothing.

I like your username

You are probably the first...

But thank you ;-)

For what it’s worth I was told at one point that PVCs are the leading indicator for sudden cardiac death, so it may have been worthwhile to get checked out either way.

Citation needed.

Most people have dozens of PVCs every day.

Dozens != 20k. At a normal heart rate of 60 bpm, that's 1/4 beats in a day. And that's only an average. You might be getting strings of consecutive PVCs, which has some risk of sudden cardiac death.

One day, I got one out of four PVCs, regular as clockwork. That was... rather alarming. I knew what they were, but that was a ton more than I was used to. Yeah, I went to the ER for that...

What was the end result? Did they go away?

They went away that day after a few hours. They went away in general when I quit taking Claritin.

The classifier can't get better with only one or two contacts.

"The cardiologist took one look at the EKG strip from the watch and was able to identify the abnormalities as PVCs rather than afib"

Sounds like the data is there.

Determining PVCs vs afib is very trivial when you actually look at the strip. However, if Apple is only analyzing rate regularity and not actually doing analysis on the waveforms themselves they would be very difficult to differentiate.

If you're having so many PVCs that the watch thinks you're in afib, you should probably still see a doctor. As the grandparent noted, tens of thousands of PVCs in a couple day period is very unusual and should probably be seen by a specialist.

To be clear, you're transitioning to a related topic, not arguing for "The classifier can't get better with only one or two contacts", right?

Right.

I would argue it is possible for better classification; I don't have a reason why apple chose not to do this (especially if they're capturing the data) other than the algorithms are not as guaranteed as we would like and they don't want to assume that kind of liability. (ECG printouts include the computer's interpretation; a standard way of reading them is to completely ignore whatever the computer says, because it is not infrequently completely wrong. And those are the professional grade machines with 12-leads capturing 10 different points on the body)

Edit; As I thought more about this, I realized that analyzing QRS duration or presence of p-waves can be lead dependent, which can change based on which parts of the body are being used to generate the lead.

Yeah, I’m currently going through the rounds of testing - just had the echocardiogram a week ago. Fortunately, that turned out normal. They gave me metoprolol, but that doesn’t seem to help. My potassium was kind of low, so they gave me a supplement for that, but it didn’t help either. If these PVCs keep up at the current rate, I suspect they will suggest ablation. Not really looking forward to that...

Anyway, I’m not sure exactly how Apple is analyzing the data. I’ve performed probably 15 EKGs with only one or two PVCs present, and it reported a normal sinus rhythm every time. It only reported afib once, and there were quite a few PVCs in that capture. I can email it to anyone interested.

Apparently, occasional (a few a day) PVCs are very common, so I imagine Apple had to encounter this situation during development.

So it's worthwhile to make sure we all understand that we're talking about two different things: atrial fibrillation and sinus rhythm are two options in the same bucket: rhythm. You can have PVCs with afib, you can have PVCs with sinus rhythm. You can't simultaneously be in afib and sinus rhythm.

I'm guessing Apple is just looking at rhythm - it would be the most reliable datapoint, as opposed to trying to measure QRS duration or analyzing for presence of P-waves, both of which differ depending on which lead you're looking at. The lead being looked at depends on which two points on the body are used to produce the tracing as well, which is not something Apple can guarantee, so perhaps that's where the explanation lies, but I have no evidence or data to back up that conclusion.

No it's not. It's trivial to recognize a PVC if you see one, but it's a lot harder to rule out AFib.

To recognize a PVC at the frequency mentioned, you'd need to see much less than a minute of ECG data. You could see AFib in the same length of data, if the data is of good quality, but it can occur episodically, so the 24 Hour ECG is the right call.

I have only limited cardiological knowledge, especially regarding Humans, but at least in my model of cardiac pathology PVCs and AFib aren't mutually exclusive.

Sorry, I may not have been clear.

The point I was trying to make is that PVCs and afib are not mutually exclusive - they're just not related entities. The parent brought up sinus rhythm, and I wanted to make sure everyone was on the same page regarding the fact that PVCs and afib are very different things that can seem similar if the only data point you look at is regularity of the rhythm.

Yes, maybe just looking at RR intervals maybe. Otherwise AFib leads to irregular undulations, at about the amplitude of a p-wave, whereas PVCs are longer and weird looking QRS complexes.

AFib is a "supraventricular" Tachycardia, whereas PVCs are more of a ventricular Tachycardia. Though I'm not sure if AFib always leads to significant Tachycardia at all.

The reason I brought up “normal sinus rhythm” and “atrial fibrillation” a few posts up is because those are two of the four possible results produced by the Apple Watch EKG app, the other two being “low and high heart rate” and “inconclusive”.

Reply on news.ycombinator.com