Item — HN Reader

For non-invasive heart disease risk prediction nothing beat ECG, period.

Somehow American Heart Association and its European counterpart are in denial, and still pushing dinasour screening mechanism with very low accuracy for heart disease risk prediction.

The standard risk model for CVD based on PREVENT (US) and SCORE-2 (Europe) like parameters are very poor as reported in the recently published paper on the their accuracy performance by the Swedish team [1]. As all CVD risk stratification with cardiologist review (expert-in-the-loop), the most important accuracy metric is sensivity/recall (avoiding false negative that will escape review) of PREVENT and SCORE-2, 26% and 48%, respectively.

The paper alternative proposal increased the sensitivity to 58% by performing clustering instead of conventional regression models as practiced in the PREVENT and SCORE-2.

These type of models including the latest proposal performed very poorly as indicated by their otherwise excellent and intuitive display of graphical abstract results [1].

[1] Risk stratification for cardiovascular disease: a comparative analysis of cluster analysis and traditional prediction models:

https://academic.oup.com/eurjpc/advance-article/doi/10.1093/...

5 comments

I'm not sure how ECG relates, how would ECG predict heart disease risk? I don't see any evidence of that, it's not even mentioned in the article you linked, which is odd considering the whole approach of clustering is gathering as many risk factors and relevant test results as are available.

That's the main contention point, believe it or not current standard for heart diseases risk prediction method do not include the 'elephant in the room' ECG.

There are many related research work with excellent results, patent, etc by biomedical researchers around the world that I'd care to mention, including yours truly. Biomedical researchers even has yearly global competition organized so called CINC that used ECG as one of the main input for heart disease risk prediction since it's readily available [1].

In particular check out work by Prof. Friedman on ECG [2]. Somehow his excellent work is mostly being ignored by AHA and their counterparts because apparently these standard risk prediction models in US and Europe are not including it as part of their parameters.

[1] Computing in cardiology (CINC):

https://cinc.org/

[2] The Electrocardiogram at 100 Years: History and Future:

https://www.ahajournals.org/doi/pdf/10.1161/CIRCULATIONAHA.1...

There are lots of different types of heart disease. An ECG can be useful for diagnosing some of them but you're overstating the relative value. For many patients, a CT coronary calcium score or CT angiogram may be more valuable in terms of detecting the type of arterial plaques that might require medical management or major lifestyle modifications in order to prevent a heart attack. These are also non-invasive, although they do involve some radiation exposure.

https://www.mayoclinic.org/tests-procedures/heart-scan/about...

https://www.mayoclinic.org/tests-procedures/ct-coronary-angi...

Having a CAC done is fairly cheap, ~$100 in the US. Insurance typically doesn’t cover it, but if anyone is concerned, it’s worth calling to set one up.

My dad’s doctor said he should get one, Medicare denied it, but he paid out of pocket to get one anyway. He found out he was 95% blocked pretty much everywhere and had a quadruple bypass. It likely added many years to his life and avoided a heart attack.

If you’re under a certain age (I want to say somewhere in your 50s), there isn’t any guidance for what normal is. If you’re in your 20s or 30s, I wouldn’t run out and get one. But if you’re in your 40s with a family history, or up into your 50s and beyond, it’s worth thinking about. I’ve also heard you’re only supposed to get them every 2-3 years, it’s not a yearly thing, due to the radiation.

(I am not a doctor)

It was just added to the recommended screenings list and my doctor expects that insurance will cover it soon because of that. Still at under $100, it was well worth knowing that i don't need aggressive treatment. (Though a quadruple bypass beats a heart attack)

Then again, CAC measures end-stage calcified plaque, not the soft plaque it started as, equally clogged arteries but also able to break off to cause strokes until the body calcified it.

The time to take action is long before you have a CAC score. e.g. Start tracking ApoB regularly, see if you have genetic LPa exposure, and avoid the foods that increase your exposure while ignoring the grifters telling you it's a nonissue.

> diagnosing

GP was talking about screening though, not diagnosis. Coronary angiography are specialized, expensive and require intravenous constrast. Doctors aren't going to order them for everyone who shows up for a routine consult.

>For non-invasive heart disease risk prediction nothing beat ECG, period.

Emphasis on non-invasive diagnostic screening as invasive testing like angiogram need to be operated by specialist and can take months to be arranged, and only done after incidents e.g heart attack.

ECG is excellent for generic top level CVD anomaly conditions for examples arrhythmia and ischemia.

CT scans are non-invasive. In most US cities you can schedule one quickly. Screening tests are generally not time critical.

How many ECGs can you sell vs how many other snake-oil products? :)

(Edit: This is intended to be sarcastic. I agree 100% with the comment)

(Edit 2: Added the smiley face)

>How many ECGs can you sell vs how many other snake-oil products?

A lot, probably. You could sell people on the idea that it should be a part of your yearly health screening.

"And if you really care about your health you should do them every 3 months to catch problems early!"

or some such.

> "And if you really care about your health you should do them every 3 months to catch problems early!"

When I moved to Houston just after law school, I found a doctor and made an appointment to get a routine physical exam; I hadn't had one since getting out of the Navy three years earlier.

Doctor: So what brings you here?

Me: A triennial physical exam.

Doctor (incredulously): You get a physical exam three times a year?

Me: No ....

This will work short-term sure, but after about lets say, 3 years of no adverse findings, the average person will not take it seriously anymore.

Huh? I get a blood panel every year and 90% of the things it looks for are normal year after year. But there is always 1 or 2 things flagged that I need to pay attention to.

An ECG if it was just part of the normal yearly panel of things that get looked at I don't think ppl will stop doing it just because it doesn't find something right away

> the average person

I do not consider the average HN commenter to be average.

What does that have to do anything. The recommendation is to do a blood panel every year I don’t see anything worse about adding ecg to that

Nobody said anything is worse. Half this thread is satire. But on a serious note. ECG is really time prohibitive, drawing 3ml of blood is relatively quick, and doesn't require specialist training like an ECG does.

“You’re waiting 3 months between ECGs?”

Whistle: Hope you didn't burn those arteries there mate :)

You can still sell snake oil that's purported to improve ECGs.

We should talk, if you can't beat 'em, join 'em :)

Poe's law in a full swing.

I didn't know... Thank you

This paper is.. not great. Their clusters and risk model were developed and validated on the same sample. There’s no train/test splitting, no cross-validation anywhere. As a result, all the performance metrics they report for their model are optimistically biased. The comparator models weren’t refit to this sample, either, so the comparison between their model and PREVENT et al. is really an internal validation versus an external validation, which isn’t apples-to-apples and disadvantages the existing models from the get-go.

You could say that it’s almost as if their model has a home-field advantage. Because of that fact alone, you can’t really conclude anything about the comparative performance of their models versus the existing ones from this paper.

Get as many scans you can under insurance. Data is king and Claude happens to chew it all pretty well. Apple Health data by itself and family history is enough to make a starter PDF for your cardiologist.

Getting an ECG, EKG, TTE, CAC, carotid duplex US, lipid panel, CMP, TSH, 25-OH Vit D, B12 + folate were what my cardio recommended before appointment #2 on hypertension. Both of us are data guys.

You don't even necessarily need insurance. Some of those tests you listed are pretty cheap so most people reading this can afford to pay out of pocket even if they're not covered by insurance.

What would an uninsured person do if the tests suggested they needed an medical intervention?

> ECG, EKG

Those are the same thing, did you mean to type something else?