Evolution of single-lead ECG for STEMI detection using a deep learning approach

Gibson, C. Michael; Mehta, Sameer; Ceschim, Mariana; Frauenfelder, Alejandra; Vieira, Daniel; Botelho, Roberto; Fernández, Francisco; Villagran, C; Niklitschek, Sebastian; Matheus, C; Pinto, Gladys; Vallenilla, Isabella; Lopez, Claudia; Acosta, Maria I.; Munguia, Anibal; Fitzgerald, Clara; Mazzini, J; Pisana, Lorena; Quintero, Samantha

doi:10.1016/j.ijcard.2021.11.039

Cited by 17 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, Bosson et al 13 (>97%) for detecting STEMI; however, these algorithms have not been tested in the prehospital setting and are not in widespread clinical use. 40,41 Studies are needed to determine whether using machine learning ECG algorithms in the prehospital setting will reduce false-activation rates.…”

Section: Resultsmentioning

confidence: 99%

“…This is important in STEMI systems of care where paramedics are obliged to transmit PH‐ECGs with a computer diagnosis of STEMI even if the ECG was performed for other reasons, as in our case. Studies utilizing machine learning algorithms have reported high sensitivity (>96%) and specificity (>97%) for detecting STEMI; however, these algorithms have not been tested in the prehospital setting and are not in widespread clinical use 40,41 . Studies are needed to determine whether using machine learning ECG algorithms in the prehospital setting will reduce false‐activation rates.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Utility of prehospital electrocardiogram interpretation in ST‐segment elevation myocardial infarction utilizing computer interpretation and transmission for interventional cardiologist consultation

Faour

Cherrett

Gibbs

et al. 2022

Cathet Cardio Intervent

View full text Add to dashboard Cite

Objectives: We examined the appropriateness of prehospital cardiac catheter laboratory activation (CCL-A) in ST-segment elevation myocardial infarction (STEMI) utilizing the University of Glasgow algorithm (UGA) and remote interventional cardiologist consultation. Background:The incremental benefit of prehospital electrocardiogram (PH-ECG) transmission on the diagnostic accuracy and appropriateness of CCL-A has been examined in a small number of studies with conflicting results. Methods:We identified consecutive PH-ECG transmissions between June 2, 2010 and October 6, 2016. Blinded adjudication of ECGs, appropriateness of CCL-A, and index diagnoses were performed using the fourth universal definition of MI. The primary outcome was the appropriate CCL-A rate. Secondary outcomes included rates of false-positive CCL-A, inappropriate CCL-A, and inappropriate CCL nonactivation.Results: Among 1088 PH-ECG transmissions, there were 565 (52%) CCL-As and 523 (48%) CCL nonactivations. The appropriate CCL-A rate was 97% (550 of 565 CCL-As), of which 4.9% (n = 27) were false-positive. The inappropriate CCL-A rate was 2.7% (15 of 565 CCL-As) and the inappropriate CCL nonactivation rate was 3.6% (19 of 523 CCL nonactivations). Reasons for appropriate CCL nonactivation (n = 504) included nondiagnostic ST-segment elevation (n = 128, 25%), bundle branch block (n = 132, 26%), repolarization abnormality (n = 61, 12%), artefact (n = 72, 14%), no ischemic symptoms (n = 32, 6.3%), severe comorbidities (n = 26, 5.2%), transient ST-segment elevation (n = 20, 4.0%), and others.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Utility of prehospital electrocardiogram interpretation in ST‐segment elevation myocardial infarction utilizing computer interpretation and transmission for interventional cardiologist consultation

Faour

Cherrett

Gibbs

et al. 2022

Cathet Cardio Intervent

View full text Add to dashboard Cite

show abstract

“…A recent study showed that telehealth increased the fatality rate by 13.7% in the non-treated group, compared to 4.1% in an administered group of patients with STEMI during the COVID-19 pandemic [21]. Another study reported that pre-hospital triage with a trans-telephonic electrocardiogram and direct referrals for catheter therapy were independent predictors for improved in-hospital survival and mortality in patients with STEMI [22].…”

Section: Discussionmentioning

confidence: 99%

“…In this study, we detected no significant difference in the presence or absence of SHD according to STEMI subtype classification. However, according to the Latin America Telemedicine Infarct Network (LATIN) data, the STEMI localization model provides promising results for anterior and inferior wall STEMI [22].…”

Section: Discussionmentioning

confidence: 99%

Effect of the hospital transfer of STEMI patients through the remote emergency consultation system on the emergency department length of stay and survival at hospital discharge: a single center retrospective cohort study

2023

View full text Add to dashboard Cite

This study aimed to analyze and determine the effects of emergency department (ED) length of stay (LOS) and survival at hospital discharge (SHD) on patients with ST-segment elevation myocardial infarction (STEMI) treated by the Remote Emergency Consultation System (RECS), a government-led teleconsultation project. This was a retrospective cohort chart review performed at a single center. The study period was from 01 May 2015, to 31 December 2020. The RECS group was set as the intervention group among the total transferred STEMI patients, and the No-RECS group was set as the control group. Ninety-eight patients with STEMI were collectively included in the No-RECS (n = 56) and RECS (n = 42) groups. The median value of ED LOS was 31 (21, 46.5) min in the No-RECS group and 21.5 (13.25, 37.25) min in the RECS group (p = 0.0329). The variables (odds ratio (95% confidence interval (CI)); p-value) predictive of SHD in the patients with STEMI were systolic blood pressure (SBP) (1.09 (1.003, 1.19); p = 0.0413) and total hospital days (2.95 (1.05, 8.26); p = 0.0399). The optimal cut-off points (sensitivity and specificity) of the receiver operating characteristic (ROC) curve of the SBP and total hospital days to predict SHD in the patients with STEMI were (0.742, 1) 105 and (0.753, 1) 3.5, respectively. RECS was associated with a decrease in EDLOS in patients with STEMI, but showed no association with SHD. SBP at the time of the ED visit and total hospital days were positively correlated with SHD.

show abstract

“…They achieved accuracy rates of 99.55% and 98.74% for convolutional neural networks and Gabor convolutional neural networks, respectively. Gibson et al [ 17 ] proposed a one-dimensional convolutional neural network for the detection of MI using single-lead ECG signals. They attained 90.50% accuracy for binary classification of ST-elevation versus non-ST-elevation MI.…”

Section: Introductionmentioning

confidence: 99%

Multilevel hybrid accurate handcrafted model for myocardial infarction classification using ECG signals

Barua

Aydemir

Doğan

et al. 2022

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Myocardial infarction (MI) is detected using electrocardiography (ECG) signals. Machine learning (ML) models have been used for automated MI detection on ECG signals. Deep learning models generally yield high classification performance but are computationally intensive. We have developed a novel multilevel hybrid feature extraction-based classification model with low time complexity for MI classification. The study dataset comprising 12-lead ECGs belonging to one healthy and 10 MI classes were downloaded from a public ECG signal databank. The model architecture comprised multilevel hybrid feature extraction, iterative feature selection, classification, and iterative majority voting (IMV). In the hybrid handcrafted feature (HHF) generation phase, both textural and statistical feature extraction functions were used to extract features from ECG beats but only at a low level. A new pooling-based multilevel decomposition model was presented to enable them to create features at a high level. This model used average and maximum pooling to create decomposed signals. Using these pooling functions, an unbalanced tree was obtained. Therefore, this model was named multilevel unbalanced pooling tree transformation (MUPTT). On the feature extraction side, two extractors (functions) were used to generate both statistical and textural features. To generate statistical features, 20 commonly used moments were used. A new, improved symmetric binary pattern function was proposed to generate textural features. Both feature extractors were applied to the original MI signal and the decomposed signals generated by the MUPTT. The most valuable features from among the extracted feature vectors were selected using iterative neighborhood component analysis (INCA). In the classification phase, a one-dimensional nearest neighbor classifier with ten-fold cross-validation was used to obtain lead-wise results. The computed lead-wise results derived from all 12 leads of the same beat were input to the IMV algorithm to generate ten voted results. The most representative was chosen using a greedy technique to calculate the overall classification performance of the model. The HHF-MUPTT-based ECG beat classification model attained excellent performance, with the best lead-wise accuracy of 99.85% observed in Lead III and 99.94% classification accuracy using the IMV algorithm. The results confirmed the high MI classification ability of the presented computationally lightweight HHF-MUPTT-based model.

show abstract

Evolution of single-lead ECG for STEMI detection using a deep learning approach

Cited by 17 publications

References 25 publications

Utility of prehospital electrocardiogram interpretation in ST‐segment elevation myocardial infarction utilizing computer interpretation and transmission for interventional cardiologist consultation

Utility of prehospital electrocardiogram interpretation in ST‐segment elevation myocardial infarction utilizing computer interpretation and transmission for interventional cardiologist consultation

Effect of the hospital transfer of STEMI patients through the remote emergency consultation system on the emergency department length of stay and survival at hospital discharge: a single center retrospective cohort study

Multilevel hybrid accurate handcrafted model for myocardial infarction classification using ECG signals

Contact Info

Product

Resources

About