False activation of the cardiac catheterization laboratory: The price to pay for shorter treatment delay

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

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.

The Effectiveness of the Smartphone-Based WeChat Platform on Reducing Time to Diagnosis and Treatment of ST-segment Elevation Myocardial Infarction

Background

This study evaluated the effectiveness of the smartphone-based WeChat platform in reducing the ischemia time of ST-segment elevation myocardial infarction (STEMI).

Methods

A total of 198 STEMI patients who underwent primary percutaneous coronary intervention (PCI) from January 2022 to August 2022 in our hospital were enrolled in this retrospective cohort study. Patients were divided into two groups according to whether their electrocardiograms (ECGs) were posted on the WeChat platform. The two groups were compared for the following: diagnosis time of first ECG, time from first medical contact (FMC) to catheterization laboratory (CL) activity, bypass emergency department (ED) or critical care unit (CCU), time of door to wire, time of door to balloon, time of FMC to wire, heart failure during hospitalization, cardiogenic shock during hospitalization, malignant arrhythmia during hospitalization, death during hospitalization, total hospital cost, and length of stay.

Results

The diagnosis time for the first ECG was 10.05 ± 3.30 mins in the control group and 2.50 ± 0.82 mins in the WeChat group (p < 0.05). The time from FMC to CL activity was significantly shorter in the WeChat group compared to the control group (p < 0.05). None of the control group patients bypassed the ED, compared to 80 (80%) of patients in the WeChat group (p < 0.05). The time from door to wire was 60.22 ± 12.73 mins in the WeChat group and 92.56 ± 20.23 mins in the control group (p < 0.05). The time of FMC to wire was also significantly shorter in the WeChat group than in the control group (p < 0.05). The WeChat group had a significantly lower rate of heart failure during hospitalization than the control group (p < 0.05). However, the two groups showed no significant differences for cardiogenic shock during hospitalization, malignant arrhythmia during hospitalization, death during hospitalization, total hospital cost, and length of stay.

Conclusions

The smartphone-based WeChat platform demonstrated high efficacy and accessibility in reducing the ischemia time for STEMI patients. Our results indicate that social media platforms such as WeChat could be a useful approach for improving the prognosis of cardiovascular disease.

Systems of Care in Cardiogenic Shock

Outcomes for cardiogenic shock (CS) patients remain relatively poor despite significant advancements in primary percutaneous coronary interventions (PCI) and temporary circulatory support (TCS) technologies. Mortality from CS shows great disparities that seem to reflect large variations in access to care and physician practice patterns. Recent reports of different models to standardize care in CS have shown considerable potential at improving outcomes. The creation of regional, integrated, 3-tiered systems, would facilitate standardized interventions and equitable access to care. Multidisciplinary CS teams at Level I centers would direct care in a hub-and-spoke model through jointly developed protocols and real-time shared decision making. Levels II and III centers would provide early access to life-saving therapies and safe transfer to designated hub centers. In regions with large geographical distances, the implementation of telemedicine-cardiac intensive care unit (CICU) care can be an important resource for the creation of effective systems of care.

Door-to-balloon time and mortality in patients with ST-elevation myocardial infarction undergoing primary angioplasty

AIMS

The evidence are not conclusive that a small incremental increase in door-to-balloon (D2B) time leads to a significant increase in death of ST-elevation myocardial infarction (STEMI) patients. In a previous study, we described a quality improvement intervention that reduced D2B time in 333 patients with STEMI. The aim of the current study was to compare mortality rates of the patients, before and after the intervention.

METHODS AND RESULTS

We examined the survival of 133 consecutive patients with STEMI treated prior to an intervention to decrease D2B time and 200 treated after the intervention. The mortality rate was the same before and after the quality intervention. The median D2B time for the entire cohort was 55 min. The number of patients with D2B time >55 min prior to the intervention was 82/133 (61%) and after the intervention 74/200 (37%) P < 0.00001. Thirty-day mortality among the patients with D2B time ≤55 min was 5/178 (2.8%) and among those with D2B time >55 min was 15/155 (9.7%), P < 0.008. The hazard ratio for 30-day mortality when the D2B time was >55 min was 3.7 (1.3-10.4).

CONCLUSION

Mortality and non-fatal complications did not differ significantly between STEMI patients before and after a quality improvement intervention. However, the number of patients treated within 55 min from arrival was significantly higher after the intervention; and coronary intervention within this time was associated with a lower death rate.

Human-Computer Agreement of Electrocardiogram Interpretation for Patients Referred to and Declined for Primary Percutaneous Coronary Intervention: Retrospective Data Analysis Study

Background

When a patient is suspected of having an acute myocardial infarction, they are accepted or declined for primary percutaneous coronary intervention partly based on clinical assessment of their 12-lead electrocardiogram (ECG) and ST-elevation myocardial infarction criteria.

Objective

We retrospectively determined the agreement rate between human (specialists called activator nurses) and computer interpretations of ECGs of patients who were declined for primary percutaneous coronary intervention.

Methods

Various features of patients who were referred for primary percutaneous coronary intervention were analyzed. Both the human and computer ECG interpretations were simplified to either “suggesting” or “not suggesting” acute myocardial infarction to avoid analysis of complex heterogeneous and synonymous diagnostic terms. Analyses, to measure agreement, and logistic regression, to determine if these ECG interpretations (and other variables such as patient age, chest pain) could predict patient mortality, were carried out.

Results

Of a total of 1464 patients referred to and declined for primary percutaneous coronary intervention, 722 (49.3%) computer diagnoses suggested acute myocardial infarction, whereas 634 (43.3%) of the human interpretations suggested acute myocardial infarction (P<.001). The human and computer agreed that there was a possible acute myocardial infarction for 342 out of 1464 (23.3%) patients. However, there was a higher rate of human–computer agreement for patients not having acute myocardial infarctions (450/1464, 30.7%). The overall agreement rate was 54.1% (792/1464). Cohen κ showed poor agreement (κ=0.08, P=.001). Only the age (odds ratio [OR] 1.07, 95% CI 1.05-1.09) and chest pain (OR 0.59, 95% CI 0.39-0.89) independent variables were statistically significant (P=.008) in predicting mortality after 30 days and 1 year. The odds for mortality within 1 year of referral were lower in patients with chest pain compared to those patients without chest pain. A referral being out of hours was a trending variable (OR 1.41, 95% CI 0.95-2.11, P=.09) for predicting the odds of 1-year mortality.

Conclusions

Mortality in patients who were declined for primary percutaneous coronary intervention was higher than the reported mortality for ST-elevation myocardial infarction patients at 1 year. Agreement between computerized and human ECG interpretation is poor, perhaps leading to a high rate of inappropriate referrals. Work is needed to improve computer and human decision making when reading ECGs to ensure that patients are referred to the correct treatment facility for time-critical therapy.

Peculiarities and Consequences of Different Angiographic Patterns of STEMI Patients Receiving Coronary Angiography Only: Data from a Large Primary PCI Registry

Background. Inappropriate cardiac catheterization lab activation together with false-positive angiographies and no-culprit found coronary interventions are now reported as costly to the medical system, influencing STEMI process efficiency. We aimed to analyze data from a high-volume interventional centre (>1000 primary PCIs/year) exploring etiologies and reporting characteristics from all "blank" coronary angiographies in STEMI.

METHODS

In this retrospective observational single-centre cohort study, we reported two-year data from a primary PCI registry (2035 patients). "Angio-only" cases were assigned to one of these categories: (a) Takotsubo syndrome; (b) coronary embolisation; (c) myocardial infarction with nonobstructive coronary arteries; (d) myocarditis; (e) CABG-referred; (f) normal coronary arteries (mostly diagnostic errors); and (g)others (refusals and death prior angioplasty). Univariate analysis assessed correlations between each category and cardiovascular risk factors.

RESULTS

412 STEMI patients received coronary angiography "only," accounting for 20.2% of cath lab activations. Barely 77 patients had diagnostic errors (3.8% from all patients) implying false-activations. 40% of "angio-only" patients (n = 165) were referred to surgery due to severe atherosclerosis or mechanical complications. Patients with diagnostic errors and normal arteries displayed strong correlations with all cardiovascular risk factors. Probably, numerous risk factors "convinced" emergency department staff to call for an angio.

CONCLUSIONS

STEMI network professionals often confront with coronary angiography "only" situations. We propose a classification according to etiologies. Next, STEMI guidelines should include audit recommendations and specific thresholds regarding "angio-only" patients, with specific focus on MINOCA, CABG referrals, and diagnostic errors. These measures will have a double impact: a better management of the patient, and a clearer perception about the usefulness of the investments.