** **ACUTE MI/STEMI** **: Activate the cath lab if the patient has chest pain?

Written by Willy Frick

I was reviewing our institutional PMcardio account which we are using to improve early identification of patients with electrocardiographically subtle OMI. 

I came across this ECG:

What do you think?

Even before we have clinical context, this ECG simply does not appear concerning for OMI, notwithstanding the machine's interpretation ** ** ACUTE MI / STEMI ** **. 

I sent this ECG to Dr. Smith with no clinical context, and he immediately replied "Fake." 

I suspect most blog readers did not struggle with this one. But in the world of STEMI, this is a challenging ECG to most.

Furthermore, how many clinicians are truly comfortable setting aside the machine interpretation and sticking with their gut that this ECG does not look ischemic. Fortunately, the physicians seeing the patient were using the Queen of Hearts PM Cardio AI ECG OMI Model, and she had absolutely no concerns.

When the Queen has some suspicion of OMI, she asks if the patient has ACS Symptoms.  She did not even need to ask in this case, because even if the patient presented with chest pain, she would call it NEGATIVE.

When I reviewed the chart, I learned that the patient had presented with syncope. The emergency physician does cautiously (correctly) note that the ECG meets STEMI criteria in V3 and V4, but goes on to document absence of ACS symptoms. The patient ruled out for MI with serial troponin testing.

Most impressively, cardiology was never consulted! This reassuring assistance from AI improved the patient's care by preventing unneeded additional testing and involvement of specialists.

The Queen of Hearts not only is extremely sensitive for subtle OMI, but is also great at recognizing false positive ECGs.

The Queen decreases false positive cath lab activations.

We published this study, showing that false positive prehospital cath lab activations would be decreased by 58% if they used the Queen:

https://www.tandfonline.com/doi/abs/10.1080/10903127.2024.2399218

Artificial Intelligence Driven Prehospital ECG Interpretation for the Reduction of False Positive Emergent Cardiac Catheterization Lab Activations: A Retrospective Cohort Study

Peter O. Baker

,

Shifa R. Karim

,

Stephen W. Smith

,

H. Pendell Meyers

,

Aaron E. Robinson

,

Ishmam Ibtida

,

Rehan M. Karim

,

Gabriel A. Keller

,

Kristie A. Royce

 &

Michael A. Puskarich

Abstract

Objectives

Data suggest patients suffering acute coronary occlusion myocardial infarction (OMI) benefit from prompt primary percutaneous intervention (PPCI). Many emergency medical services (EMS) activate catheterization labs to reduce time to PPCI, but suffer a high burden of inappropriate activations. Artificial intelligence (AI) algorithms show promise to improve electrocardiogram (ECG) interpretation. The primary objective was to evaluate the potential of AI to reduce false positive activations without missing OMI.

Methods

Electrocardiograms were categorized by (1) STEMI criteria, (2) ECG integrated device software and (3) a proprietary AI algorithm (Queen of Hearts (QOH), Powerful Medical). If multiple ECGs were obtained and any one tracing was positive for a given method, that diagnostic method was considered positive. The primary outcome was OMI defined as an angiographic culprit lesion with either TIMI 0–2 flow; or TIMI 3 flow with either peak high sensitivity troponin-I > 5000 ng/L or new wall motion abnormality. The primary analysis was per-patient proportion of false positives.

Results

A total of 140 patients were screened and 117 met criteria. Of these, 48 met the primary outcome criteria of OMI. There were 80 positives by STEMI criteria, 88 by device algorithm, and 77 by AI software. All approaches reduced false positives, 27% for STEMI, 22% for device software, and 34% for AI (p < 0.01 for all). The reduction in false positives did not significantly differ between STEMI criteria and AI software (p = 0.19) but STEMI criteria missed 6 (5%) OMIs, while AI missed none (p = 0.01).

Conclusions

In this single-center retrospective study, an AI-driven algorithm reduced false positive diagnoses of OMI compared to EMS clinician gestalt. Compared to AI (which missed no OMI), STEMI criteria also reduced false positives but missed 6 true OMI. External validation of these findings in prospective cohorts is indicated.

===================================

MY Comment, by KEN GRAUER, MD (2/12/2025):  

===================================

As per Dr. Frick — the ST elevation and T wave inversion in today's ECG is not the result of an acute OMI. Instead — it is almost certain to be a longstanding finding in this patient with marked LVH.

• As I emphasized in My Comment at the bottom of the page in the December 14, 2022 post — We have reviewed many cases that illustrate the challenge posed by distinguishing between marked LVH — vs LVH + superimposed acute OMI.
• PEARL #1: In general, it is rare to see both marked LVH and acute OMI in the same tracing. It is for this reason — that we can get a "head start" in our interpretation of a patient with symptoms in which there is obvious LVH. This is because statistically (supported by our experience) — in the vast majority of cases, such tracings may mimic acute OMI, but acute coronary occlusion will rarely be seen.
• PEARL #2: The above said — Remember the rule of "N = 1". By this I mean that even though it is rare to see an acute anterior OMI in a patient with marked LVH — this can occur — so that we want to be prudent and avoid overlooking the rare OMI in a patient with marked LVH (See the above mentioned December 14, 2022 post for a case in which marked LVH and acute OMI coexist).
• BOTTOM Line: Awareness of the criteria for ECG diagnosis of LVH goes a long way toward facilitating interpretation. Toward this end — we've conveniently added a LINK for "LVH Criteria" in the Menu at the top of every page in Dr. Smith's ECG Blog. This link takes you to My Comment in the June 20, 2020 post — in which I review a user-friendly approach to ECG recognition of LVH and "Strain".

Figure-1: I've labeled today's ECG.

Regarding Today's CASE:

For clarity in Figure-1 — I've labeled today's tracing. 

• The diagnosis of marked LVH should be obvious in Figure-1. That said — overlap of R waves with S waves in multiple leads (especially with the long lead rhythm strips at the bottom of the tracing) — complicates accurate determination of QRS amplitudes (See my color-coding in Figure-1 for my best effort at calculating R wave and S wave amplitudes in the various leads).
• PEARL #3: The easiest way to avoid confusing lead overlap — is simply to repeat the ECG at half standardization. This was not done in today's tracing.
• The most difficult beats to assess QRS amplitude on are beats #7,8,9 — because there is overlap with each of the 3 simultaneously-recorded long lead rhythm strips (of leads V1,II,V5). For example — true amplitude of the S wave in lead V3 is almost entirely concealed by overlap of both the lead V1 and lead II rhythm strips below it. In such cases of multiple lead overlap — I look elsewhere for leads with less overlap (ie, in leads II and V1, which are outlined in YELLOW and PINK) to determine the true amplitude of the S and R waves in these leads. This allowed me to determine that the S wave in lead V3 (in light BLUE) measures 36 mm deep!
• PEARL #4: The KEY for determining that rather than "fulfilling STEMI millimeter-based criteria" for the amount of ST elevation in lead V3 — given the 36 mm deep S wave in this lead — this is in no way an "abnormal" amount of ST elevation (ie, the principle of "proportionality" reigns supreme for qualitative assessment of ST-T wave changes in a patient with marked LVH).
• As to the straightened shape of the ST segment takeoff in lead V3 — this shape is completely consistent with the appearance of LV "strain" in an anterior lead in a patient with extremely deep anterior S waves (See My Comment in the February 6, 2020 post).

What About ST-T Wave Changes in Other Leads in Figure-1?

At 1st glance — the ST segment coving with seemingly "deep", symmetric T wave inversion in lead V5 might be of concern. That said — there are several reasons why I felt this ST-T wave appearance in lead V5 was not of concern:

• Again, by the principle of "proportionality" — the 38mm tall R wave in lead V5 suggests the relative size of the inverted T wave in this lead is not as deep as one might initially think.
• The slow downsloping, more rapid upsloping ST depression seen in lead V6 is absolutely typical for LV "strain" in this left-sided lead in which R wave amplitude is significantly increased (measuring 22 mm).
• Patients with marked LVH (especially those with longstanding hypertension) often manifest not only ST-T wave changes that are typical for LV "strain" — but also symmetric T wave inversion as seen here in lead V5.
• Finally — I interpreted the ST-T wave appearance in lead V5 as a "transition" lead that lies in between the ST coving and elevation seen in lead V4 — and the "strain"-like ST depression seen in lead V6. This ST-T wave pattern in lead V5 is not seen in other leads, as would be expected if this was truly a change of acute ischemia.

What about the R = S Phenomenon in the Inferior Leads?

I found the surprisingly tall R = S Waves in each of the inferior leads an interesting and unusual feature (R waves and S waves each ≥15 mm in leads II,III and aVF). I cannot remember the last time I saw this pattern in each of the 3 inferior leads.

• This R=S pattern of tall RS complexes brings to mind the Katz-Wachtel phenomenon described in pediatric patients — in which the finding of biphasic RS complexes of ≥50 mm in mid-chest leads V2, V3 or V4 suggests biventricular hypertrophy, especially in children with VSD (Ventricular Septal Defect).
• Clearly, the R=S waves in today's tracing are not as deep as occurs with the Katz-Wachtel phenomenon. That said, given the association of these inferior lead R=S waves with marked increase in chest lead amplitude — I would love to see an Echo on this patient, so as to correlate Echo findings with today's interesting ECG.

Conclusion:

The ECG in today's case is notable for marked LVH. As per Dr. Frick — this ECG is not suggestive of acute OMI. I attributed the diffuse ST-T wave changes to LV "strain" and not ischemia.