Prognosis and first diagnostic ECG in STEMI patients referred to the emergency medical system for primary PCI

Meloni, Luigi; Marchetti, Maria Francesca; Cacace, Cristina; Congia, Michela; Scotto, Riccardo; Caddeo, Piero; Montisci, Roberta

doi:10.1016/j.jelectrocard.2018.09.003

Cited by 5 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This issue can be solved using visualization techniques such as Grad-CAM [ 32 ], which can display image areas that contribute to classification. In addition, it is important to present scores based on ECG indices as proposed in the previous research [ 7 , 8 , 9 , 33 ]. Such scores can provide important information regarding fast triage and prognostic effects for MI patients.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

End-to-End Convolutional Neural Network Model to Detect and Localize Myocardial Infarction Using 12-Lead ECG Images without Preprocessing

et al. 2022

View full text Add to dashboard Cite

In recent years, many studies have proposed automatic detection and localization techniques for myocardial infarction (MI) using the 12-lead electrocardiogram (ECG). Most of them applied preprocessing to the ECG signals, e.g., noise removal, trend removal, beat segmentation, and feature selection, followed by model construction and classification based on machine-learning algorithms. The selection and implementation of preprocessing methods require specialized knowledge and experience to handle ECG data. In this paper, we propose an end-to-end convolutional neural network model that detects and localizes MI without such complicated multistep preprocessing. The proposed model executes comprehensive learning for the waveform features of unpreprocessed raw ECG images captured from 12-lead ECG signals. We evaluated the classification performance of the proposed model in two experimental settings: ten-fold cross-validation where ECG images were split randomly, and two-fold cross-validation where ECG images were split into one patient and the other patients. The experimental results demonstrate that the proposed model obtained MI detection accuracies of 99.82% and 93.93% and MI localization accuracies of 99.28% and 69.27% in the first and second settings, respectively. The performance of the proposed method is higher than or comparable to that of existing state-of-the-art methods. Thus, the proposed model is expected to be an effective MI diagnosis tool that can be used in intensive care units and as wearable technology.

show abstract

Section: Discussionmentioning

confidence: 99%

“…To date, many research groups have attempted to predict the prognosis from ECG progression in patients with MI [ 7 , 8 , 9 ]. In these studies, the prognostic prediction was performed using parameter values calculated from ECG signals.…”

Section: Introductionmentioning

confidence: 99%

End-to-End Convolutional Neural Network Model to Detect and Localize Myocardial Infarction Using 12-Lead ECG Images without Preprocessing

et al. 2022

View full text Add to dashboard Cite

show abstract

“…17 A recent study reported that prehospital diagnosis can also provide data regarding pathologic Q wave in STEMI patients, which is associated with a risk of mortality and adverse outcomes. 18 Prehospital factors can increase the time to PCI, which is associated with increased mortality. 19 The results of our study indicated that indirect referral and emergency referral had a difference in in-hospital, sixmonths, one, and three-year mortality rates in STEMI patients, however, the difference was not statistically significant.…”

Section: Discussionmentioning

confidence: 99%

<p>Effects of Prehospital Traige and Diagnosis of ST Segment Elevation Myocardial Infarction on Mortality Rate</p>

Alizadeh¹,

Aghsaeifard²,

Sadeghi³

et al. 2020

IJGM

View full text Add to dashboard Cite

Introduction: Adverse outcomes and mortality associated with STEMI (ST segment elevation myocardial infarction) are associated with the management and diagnosis time. The aim of this study is to evaluate the outcomes of prehospital diagnosis of STEMI via emergency medical service (EMS) on mortality, in comparison to the patients who did not receive EMS. Methods: This retrospective study included STEMI patients, who underwent primary angioplasty. The patients were categorized as group A: referred without emergency service, group B: patients who did not receive PPCI and group C: patients referred via ambulance and received telecardiology. Medical records of these patients were evaluated for the diagnosis time, door-to-balloon time, in-hospital, six months, one year and three-year mortality, left ventricular ejection fraction and previous history of cardiovascular conditions and surgeries. The data were recorded and statistically analyzed using SPSS v21. Results: Of 424 patients studied, 79 were referred without emergency service (group A), 52 patients did not receive PPCI (group B) and 293 patients were referred via ambulance with telecardiology (group C). Door-to-balloon time was least in group C (57.78 min) compared to group A (141.70 min). In-hospital, six months, one year and three-year mortality was least in group C, however, the difference was not statistically significant. The left ventricular ejection fraction was significantly greater in group C. Conclusion: The results of our study indicate that prehospital diagnosis and telecardiology significantly reduce door-to-balloon time in STEMI patients referred for percutaneous intervention and might have an influence on short-term and long-term mortality rates.

show abstract

A privacy-preserving group decision making expert system for medical diagnosis based on dynamic knowledge base

Zong

Liu

et al. 2020

Wireless Netw

View full text Add to dashboard Cite

Prognosis and first diagnostic ECG in STEMI patients referred to the emergency medical system for primary PCI

Cited by 5 publications

References 15 publications

End-to-End Convolutional Neural Network Model to Detect and Localize Myocardial Infarction Using 12-Lead ECG Images without Preprocessing

End-to-End Convolutional Neural Network Model to Detect and Localize Myocardial Infarction Using 12-Lead ECG Images without Preprocessing

<p>Effects of Prehospital Traige and Diagnosis of ST Segment Elevation Myocardial Infarction on Mortality Rate</p>

A privacy-preserving group decision making expert system for medical diagnosis based on dynamic knowledge base

Contact Info

Product

Resources

About