scholarly journals Innovative techniques to construct powerful artificial intelligence algorithms for st-elevation myocardial infarction

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
S Mehta ◽  
S Niklitschek ◽  
F Fernandez ◽  
C Villagran ◽  
J Avila ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Myocardial Infarction ◽  
Working Environment ◽  
Ensemble Method ◽  
St Elevation Myocardial Infarction ◽  
Dense Layer ◽  
Pass Filter ◽  
Low Pass Filter ◽  
St Elevation ◽  
The Mean

Abstract Background With the sudden advent of Artificial Intelligence (AI), incorporation of these technologies into key aspects of our working environment has become an ever so delicate task, especially so when dealing with time-sensitive and potentially lethal scenarios such as ST-Elevation Myocardial Infarction (STEMI) management. By further expanding into our successful experiences with AI-guided algorithms for STEMI detection, we implemented an innovative ensemble method into our methodology as we seek to improve the algorithm's predictive capabilities. Purpose Through the ensemble method, we combined two ML techniques to boost our previous experiments' accuracy and reliability. Methods Database: EKG records obtained from Latin America Telemedicine Infarct Network (Mexico, Colombia, Argentina, and Brazil) from April 2014 to December 2019. Dataset: Two separate datasets were used to train and test two sets of AI algorithms. The first comprised of 11,567 records and the second 7,286 records, each composed of 12-lead EKG records of 10-second length with sampling frequency of 500 Hz, including the following balanced classes: unconfirmed & angiographically confirmed STEMI (first model); angiographically confirmed STEMI only (second model); and, for both models, we included branch blocks, non-specific ST-T abnormalities, normal, and abnormal (200+ CPT codes, excluding the ones included in other classes). Label per record was manually checked by cardiologists to ensure precision (Ground truth). Pre-processing: First and last 250 samples were discarded to avoid a standardization pulse. An order 5 digital low pass filter with a 35 Hz cut-off was applied. For each record, the mean was subtracted to each individual lead. Classification: The determined classes were STEMI and Not-STEMI (A combination of randomly sampled normal, branch blocks, non-specific ST-T abnormalities and abnormal records – 25% of each subclass). Training & Testing: The last dense layer outputs a probability for each record of being STEMI or Not-STEMI. These probabilities were calculated for each model (Model 1 trained with Complete STEMI dataset and Model 2 trained with confirmed STEMI only dataset) and aggregated using the mean aggregation to generate the final label for each record. A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90%/10%; respectively. Results are reported for both testing datasets (Complete and confirmed STEMI only records). Results Complete STEMI Dataset: Accuracy: 96.5% Sensitivity: 96.2% Specificity: 96.9% – Confirmed STEMI only Dataset: Accuracy: 98.5% Sensitivity: 98.3% Specificity: 98.6%' Conclusion(s) While Model 1 and Model 2 achieved similar performances with promising results on their own, applying a combination of both through the ensemble model exhibits a clear improvement in performance when applied to both datasets. This provides a blueprint for advanced automated STEMI detection through wearable devices. Funding Acknowledgement Type of funding source: None

Abstract 16700: Mineralocorticoid Receptor Antagonist Utilization in Eligible Patients Post St-elevation Myocardial Infarction

Circulation ◽  
2015 ◽  
Vol 132 (suppl_3) ◽  
Author(s):  
Hamed Nazzari ◽  
Krishnan Ramanathan ◽  
Carolyn Taylor ◽  
Marc Deyell ◽  
Jasmine Grewal ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Heart Failure ◽  
Mineralocorticoid Receptor ◽  
Left Ventricular ◽  
St Elevation Myocardial Infarction ◽  
Left Ventricular Ejection ◽  
Mineralocorticoid Receptor Antagonist ◽  
Ventricular Ejection Fraction ◽  
St Elevation ◽  
The Mean

Background: Mineralocorticoid receptor antagonists (MRAs) have been shown to reduce the morbidity and mortality in patients with reduced left ventricular ejection fraction (LVEF) post myocardial infarction (MI). Canadian guidelines recommend a MRA in patients post MI with an LVEF of ≤40% and documented heart failure or diabetes before hospital discharge, in the absence of any contraindications. We sought to examine if discrepancies between guideline-based therapy and actual prescribing rates exists in the use of MRAs in acute ST-elevation myocardial infarction (STEMI) patients. Methods: Retrospective analysis of utilization rates of MRAs in eligible patients enrolled in the Vancouver Coastal Health Authority STEMI database between October 2007 and October 2014. Inclusion criteria were based on the EPHESUS trial, which included an LVEF <40% and documented heart failure or history of diabetes. Patients on dialysis or with a serum Cr >221 were excluded. Results: 2583 patients had a STEMI during the study period. 192 (7.4%) patients were determined to be eligible for MRA prescription at discharge, 32 were excluded due missing discharge prescription information. Of the remaining 160 patients, the mean age was 67.9, 71.3% were male, 72.5% had an anterior MI and the mean LVEF was 30.4%. During hospitalization 51.6% had clinical evidence of HF and 21.3% were diagnosed with cardiogenic shock. PCI was performed in 75.6% of those eligible and 11.3% underwent CABG, 11.9% were medically managed and 1.25% underwent thrombolysis as a final revascularization strategy. On discharge 98% were on ASA, 81.3% on a second anti-platelet agent, 96% were on a beta-blocker, 75.6% were on an ACEi, 15.6% were on an ARB, 99.4% were on a statin. Only 22 (13.8%) of eligible patients were discharged on an MRA. No significant clinical difference existed amongst those that received an MRA compared to those that did not. Conclusions: Despite a Class IA recommendation for the use of MRAs in this patient population, our study demonstrates that the majority of patients are not prescribed an MRA after STEMI. This demonstrates a large care gap between evidence based guidelines and clinical practice. The reasons for this discrepancy in practice patterns are unclear and will be the focus of further study.

scholarly journals 06 - Detection of ST-Elevation Myocardial Infarction Using An Artificial Intelligence-Guided Single Lead ECG

2019 ◽  
Author(s):  
Rodrigo Jacobucci ◽  
Alejandra Frauenfelder ◽  
Mariana Ceschim ◽  
Francisco Fernandez ◽  
Carlos Villagrán ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Myocardial Infarction ◽  
St Elevation Myocardial Infarction ◽  
St Elevation

scholarly journals Electrocardiographic Changes and Coronary Findings in Patients with Acute non-ST-Elevation Myocardial Infarction: A Cross-Sectional Study

2020 ◽  
Vol 9 (4) ◽  
Author(s):  
Fardin Mirbolouk ◽  
Arsalan Salari ◽  
Fatemeh Riahini ◽  
Mani Moayerifar ◽  
Sama Norouzi ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
High Risk ◽  
Significant Relationship ◽  
St Elevation Myocardial Infarction ◽  
Syntax Score ◽  
Ecg Changes ◽  
Left Circumflex Artery ◽  
Electrocardiographic Changes ◽  
St Elevation ◽  
The Mean

Background: Despite significant improvements in diagnosis and treatment, non-ST-Elevation Myocardial Infarction (NSTEMI) is still one of the health problems in developed and developing countries. Objectives: The present study was performed to assess the electrocardiographic changes and coronary findings in patients with NSTEMI. Methods: The study enrolled 158 patients with NSTEMI diagnosis at the discharge time. Demographic characteristics and electrocardiographic changes were collected using a checklist from the medical records of the patients. The angiography data were used to calculate a syntax score for each patient. Finally, patients were divided into three groups based on this score: high risk >32, intermediate risk 22-32, and low risk < 22. Involved vessels, including the left anterior descending artery, Right Coronary Artery (RCA), Left Circumflex Artery (LCX), and the left main stem, were also determined. Results: The mean age of the patients was 60.68 ± 12.15 years. The LAD, LCX, and RCA were the most common involved vessels, in sequence. About 27.73, 67.15, and 5.12% of the patients were assigned to low, moderate, and high-risk groups, respectively. Statistically significant differences were observed in the frequencies of ECG changes (P = 0.003) and types of involved vessels (P < 0.001) between low, moderate, and high-risk patients. In addition, there were statistically significant differences in the mean syntax scores between different types of involved vessels (P < 0.001). Conclusions: The findings of the present study showed a significant relationship between the types of vessel involvement and syntax score. Also, there was a high prevalence of ST changes in precordial leads that may improve the sensitivity of diagnosis. We did not find any significant relationship between the frequencies of ECG changes based on the types of involved vessels.

scholarly journals ACUTE ST ELEVATION MYOCARDIAL INFARCTION

2018 ◽  
Vol 25 (05) ◽  
pp. 777-783
Author(s):  
Munir Ahmad ◽  
Muhammad Yasir ◽  
Asif Rahmat
Keyword(s):  
Myocardial Infarction ◽  
Ventricular Arrhythmia ◽  
Cardiac Failure ◽  
Case Series ◽  
St Elevation Myocardial Infarction ◽  
Hospital Outcome ◽  
Recurrent Angina ◽  
St Elevation ◽  
The Mean ◽  
N 93

Objective: To determine the frequency of in-hospital outcomes in patients ofacute ST elevation myocardial infarction (STEMI) within five days of hospitalization with .70ST segment resolution 90 minutes post thrombolysis. Study Design: Case series. Place andDuration of Study: Department of Cardiology, Faisalabad Institute of Cardiology, Faisalabad,from April, 2016 to October, 2016. Methodology: In 370 patients fulfilling the inclusion andexclusion criteria a baseline 12 lead electrocardiogram was recorded before initiation ofthrombolysis and at 90 minutes thereafter. Conventional contraindications to thrombolysis wereobserved and streptokinase 1.5 mu was administered by intravenous infusion over 60 minutes.Successful thrombolysis was taken as 70% or more ST elevation resolution at 90 minutes frombaseline electrocardiogram measured 80ms from J-point. Patients with successful thrombolysiswere observed for in-hospital clinical outcomes of recurrent angina, congestive cardiac failure,ventricular arrhythmia and death within five days of hospitalization. Results: Out of 370 cases,51.35 %( n=190) were male while 48.65 %( n=180) were female, 25.14 %( n=93) were between30-50 years of age while 74.86 %( n=277) were between 51-65 years of age, the mean agewas 54.98+5.96 years. Frequency of in-hospital outcome was recorded as 10.67 %( n=38) forcongestive cardiac failure, 14.59 %( n=54) for ventricular arrhythmia, 5.40 %( n=20) for mortalitywhile no case had recurrent angina. Conclusion: In-hospital outcome is better in patients of.70% ST resolution at 90 minutes post thrombolysis .This might assist in identification of lowrisk patients who can be discharged early and should not be considered for early invasivestrategy.

scholarly journals The impact of frailty on the management and outcome of ST-elevation myocardial infarction in older patients

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
M Bennett ◽  
J A Batty
Keyword(s):  
Myocardial Infarction ◽  
High Risk ◽  
Management Strategy ◽  
St Elevation Myocardial Infarction ◽  
Frail Patients ◽  
Icd 10 ◽  
St Elevation ◽  
The Mean ◽  
The Impact ◽  
Invasive Management

Abstract Background Frailty is a clinical syndrome of increased vulnerability, resulting from age-associated decline in physiological reserve, compromising the ability to cope with acute stressors. Despite an increasing number of older, frail patients presenting with ST-elevation myocardial infarction (STEMI), there remains a paucity of guidance on how to approach the management of this complex group. Purpose To evaluate the impact of frailty on the management strategy and outcomes in older patients presenting with ST-elevation myocardial infarction. Methods A retrospective cohort study was performed, using linked patient records in The Nationwide Readmission Database. All patients aged ≥75 years that presented with STEMI (2015 – 2018) were included. International Classification of Disease (10th Edition; ICD-10) codes were used to ascertain exposures and outcomes. Frailty was quantified using the Hospital Frailty Risk Score (HFRS): an ICD-10-based scoring system that has been validated against established clinical frailty indices. Outcomes included: (i) management strategy (coronary angiography ± percutaneous coronary intervention, vs. conservative management), length of stay and 30-day mortality. Outcomes were modelled using multivariable binary logistic regression. Continuous variables are presented as: mean (standard deviation). Odds ratios (OR) are given with corresponding 95% confidence intervals (CI). Results From an overall dataset of 57,133,894 admissions, 368,201 patients presenting with STEMI were identified, of which 92,067 were aged ≥75 years. The mean age was 82.4 (5.1) years; 45,768 (49.7%) were female. The mean frailty score was 5.9 (SD 4.9, range 0 - 37.7). Patients were categorised by frailty status: low (HFRS &lt;5; n=46,336 [50.3%]), intermediate (HFRS 5 - 15; n=40,493 [44.0%]) and high risk (HFRS &gt;15; n=5,238 [5.7%]). Characteristics of the cohort are presented in Figure 1. Frail patients were less likely to undergo invasive management: 1,873 (35.5%) of the high risk group underwent coronary angiography vs. 36,888 (79.6%) of the low risk group; OR 0.14 (95% CI 0.13 - 0.15), P&lt;0.001. Length of stay in hospital increased proportionately with frailty: a 2-unit increase in HRFS was associated with one additional day in hospital (p&lt;0.001). 30-day mortality increased non-linearly with increasing HFRS and was markedly higher among patients at high risk for frailty, compared with those at low risk; OR 3.70 (95% CI 3.47 - 3.94; p&lt;0.001). The relationship between frailty score and outcomes is presented in Figure 2. Frailty remained the greatest single predictor of outcome following adjustment for other covariates, including age. Conclusions Frail patients presenting with STEMI are less likely to undergo invasive management and more likely to experience adverse outcomes. Quantification of frailty offers an opportunity to identify and address modifiable risk factors to improve post-STEMI outcomes in this vulnerable group. FUNDunding Acknowledgement Type of funding sources: None.

Sign in / Sign up

Export Citation Format

Share Document