Deep Learning for Improved Precision and Reproducibility of Left Ventricular Strain in Echocardiography: A Test-Retest Study.

AIMS: Assessment of left ventricular (LV) function by echocardiography is hampered by modest test-retest reproducibility. A novel artificial intelligence (AI) method based on deep learning provides fully automated measurements of LV global longitudinal strain (GLS) and may improve the clinical utility of echocardiography by reducing user-related variability. The aim of this study was to assess within-patient test-retest reproducibility of LV GLS measured by the novel AI method in repeated echocardiograms recorded by different echocardiographers and to compare the results to manual measurements. METHODS: Two test-retest data sets (n = 40 and n = 32) were obtained at separate centers. Repeated recordings were acquired in immediate succession by 2 different echocardiographers at each center. For each data set, 4 readers measured GLS in both recordings using a semiautomatic method to construct test-retest interreader and intrareader scenarios. Agreement, mean absolute difference, and minimal detectable change (MDC) were compared to analyses by AI. In a subset of 10 patients, beat-to-beat variability in 3 cardiac cycles was assessed by 2 readers and AI. RESULTS: Test-retest variability was lower with AI compared with interreader scenarios (data set I: MDC = 3.7 vs 5.5, mean absolute difference = 1.4 vs 2.1, respectively; data set II: MDC = 3.9 vs 5.2, mean absolute difference = 1.6 vs 1.9, respectively; all P < .05). There was bias in GLS measurements in 13 of 24 test-retest interreader scenarios (largest bias, 3.2 strain units). In contrast, there was no bias in measurements by AI. Beat-to-beat MDCs were 1,5, 2.1, and 2.3 for AI and the 2 readers, respectively. Processing time for analyses of GLS by the AI method was 7.9 ± 2.8 seconds. CONCLUSION: A fast AI method for automated measurements of LV GLS reduced test-retest variability and removed bias between readers in both test-retest data sets. By improving the precision and reproducibility, AI may increase the clinical utility of echocardiography.

Automated tissue Doppler imaging for identification of occluded coronary artery in patients with suspected non-ST-elevation myocardial infarction.

PURPOSE: Identification of regional dysfunction is important for early risk stratification in patients with suspected non-ST-elevation myocardial infarction (NSTEMI). Strain echocardiography enables quantification of segmental myocardial deformation. However, the clinical use is hampered by time-consuming manual measurements. We aimed to evaluate whether an in-house developed software for automated analysis of segmental myocardial deformation based on tissue Doppler imaging (TDI) could predict coronary occlusion in patients with suspected NSTEMI. METHODS: Eighty-four patients with suspected NSTEMI were included in the analysis. Echocardiography was performed at admission. Strain, strain rate and post-systolic shortening index (PSI) were analyzed by the automated TDI-based tool and the ability to predict coronary occlusion was assessed. For comparison, strain measurements were performed both by manual TDI-based analyses and by semi-automatic speckle tracking echocardiography (STE). All patients underwent coronary angiography. RESULTS: Seventeen patients had an acute coronary occlusion. Global strain and PSI by STE were able to differentiate occluded from non-occluded culprit lesions (respectively - 15.0% vs. -17.1%, and 8.1% vs. 5.1%, both p-values < 0.05) and identify patients with an acute coronary occlusion (AUC 0.66 for both strain and PSI). Measurements of strain, strain rate and PSI based on TDI were not significantly different between occluded and non-occluded territories. CONCLUSION: Automated measurements of myocardial deformation based on TDI were not able to identify acute coronary occlusion in patients with suspected NSTEMI. However, this study confirms the potential of strain by STE for early risk stratification in patients with chest pain.

Increased deformation of the left ventricle during exercise test measured by global longitudinal strain can rule out significant coronary artery disease in patients with suspected unstable angina pectoris.

BACKGROUND: Noninvasive identification of significant coronary artery disease (CAD) in patients with unstable angina pectoris (UAP) is challenging. Exercise stress testing has been used for years in patients with suspected CAD but has low diagnostic accuracy. The use of Global longitudinal strain (GLS) by speckle tracking echocardiography is a highly sensitive and reproducible parameter for detection of myocardial ischemia. Our aim was to study if identification of normal or ischemic myocardium by measurement of GLS immediately after an ordinary bicycle exercise stress testing in patients with suspected UAP could identify or rule out significant CAD. METHODS: Seventy-eight patients referred for coronary angiography from outpatient clinics and the emergency department with chest pain, inconclusive ECG and normal values of Troponin-T was included. All patients underwent echocardiographic examination at rest and immediately after maximum stress by exercise on a stationary bicycle. Significant CAD was defined by diameter stenosis > 90% by coronary angiography. In patients with coronary stenosis between 50-90%, fractional flow reserve (FFR) was measured and defined abnormal < .80. Analysis of echocardiographic data were performed blinded for angiographic data. Patients were discharged diagnosed with CAD (n = 34) or non-coronary chest pain (NCCP, n = 44). RESULTS: In patients with NCCP, GLS at rest was -21.1 ± 1.7% and -25.5 ± 2.6% at maximum stress (P < .01). In patients with CAD, GLS at rest was -16.8 ± 4.0% and remained unchanged at maximum stress (-16.6 ± 4.6%, P = .69). In patients with NCCP, LVEF was 56.1% ± 6.0 and increased to 61.8% 5.2, P < .01. In CAD patients, LVEF at rest was 54.7% ± 8.6 and increased to 58.2% ± 9.5 during stress, P = .16. In NCCP patients, Wall Motion Score index decreased .02 ± .07, P = .03 during stress and was without significant changes in patients with CAD. Area under the curve (AUC) for distinguishing CAD for was .97 (.95-1.00), .63 (.49-.76), and .71 (.59-.83) for GLS, LVEF, and WMSi, respectively. CONCLUSION: In patients with suspected UAP, increased deformation of the left ventricle measured by GLS immediately after exercise stress testing identified normal myocardium without CAD. Reduced LV contractile function by GLS without increase after exercise identified significant CAD.

Strain echocardiography improves prediction of arrhythmic events in ischemic and non-ischemic dilated cardiomyopathy.

BACKGROUND: Recent evidence suggests that an implantable cardioverter defibrillator (ICD) in non-ischemic cardiomyopathy (NICM) may not offer mortality benefit. We aimed to investigate if etiology of heart failure and strain echocardiography can improve risk stratification of life threatening ventricular arrhythmia (VA) in heart failure patients. METHODS: This prospective multi-center follow-up study consecutively included NICM and ischemic cardiomyopathy (ICM) patients with left ventricular ejection fraction (LVEF) <40%. We assessed LVEF, global longitudinal strain (GLS) and mechanical dispersion (MD) by echocardiography. Ventricular arrhythmia was defined as sustained ventricular tachycardia, sudden cardiac death or appropriate shock from an ICD. RESULTS: We included 290 patients (67 ± 13 years old, 74% males, 207(71%) ICM). During 22 ± 12 months follow up, VA occurred in 32(11%) patients. MD and GLS were both markers of VA in patients with ICM and NICM, whereas LVEF was not (p = 0.14). MD independently predicted VA (HR: 1.19; 95% CI 1.08-1.32, p = 0.001), with excellent arrhythmia free survival in patients with MD <70 ms (Log rank p < 0.001). Patients with NICM and MD <70 ms had the lowest VA incidence with an event rate of 3%/year, while patients with ICM and MD >70 ms had highest VA incidence with an event rate of 16%/year. CONCLUSION: Patients with NICM and normal MD had low arrhythmic event rate, comparable to the general population. Patients with ICM and MD >70 ms had the highest risk of VA. Combining heart failure etiology and strain echocardiography may classify heart failure patients in low, intermediate and high risk of VA and thereby aid ICD decision strategies.

Long-term ECG recording: findings and implications. / Funn og konsekvenser ved langtidsregistrering av EKG.

BACKGROUND: Long-term ECG recording is a commonly used test. However, there are no clear guidelines on who should be examined using this method, and we lack an overview of the results of testing and their therapeutic implications. MATERIAL AND METHOD: All long-term ECG recordings performed at Sørlandet Hospital Arendal in the period 2017-18 were included in the study. The tests were identified by searching the medical records system for relevant procedure codes, and all medical records related to the test were subsequently reviewed. Patient characteristics, referrer, indication, results, further assessment, and treatment were recorded. RESULTS: A total of 1 262 long-term ECG recordings were performed at Sørlandet Hospital Arendal in the period 2017-18. The median age of those tested was 60 years, and 48 % of tests were performed in women. A total of 253 (20 %) recordings revealed arrhythmias and 168 (13 %) had therapeutic implications. For patients without known heart disease or a history of stroke (n = 619 (49 %)), the test had therapeutic implications in 32 (5 %) cases. INTERPRETATION: Long-term ECG recording was often used to test patient populations with limited cardiac arrhythmia, and the results rarely had therapeutic implications. The findings of the study may indicate that long-term ECG recording should be used to a greater extent in patients for whom positive findings would have therapeutic and prognostic implications, such as those in whom stroke prophylaxis would be indicated if they were found to have atrial fibrillation.

Global longitudinal strain is a more reproducible measure of left ventricular function than ejection fraction regardless of echocardiographic training.

BACKGROUND: Left ventricular ejection fraction (LVEF) is an established method for evaluation of left ventricular (LV) systolic function. Global longitudinal strain (GLS) by speckle tracking echocardiography seems to be an important additive method for evaluation of LV function with improved reproducibility compared with LVEF. Our aim was to compare reproducibility of GLS and LVEF between an expert and trainee both as echocardiographic examiner and analyst. METHODS: Forty-seven patients with recent Acute Coronary Syndrome (ACS) underwent echocardiographic examination by both an expert echocardiographer and a trainee. Both echocardiographers, blinded for clinical data and each other's findings, performed image analysis for evaluation of intra- and inter- observer variability. GLS was measured using speckle tracking echocardiography. LVEF was calculated by Simpson's biplane method. RESULTS: The trainee measured a GLS of - 19.4% (±3.5%) and expert - 18.7% (±3.2%) with an Intra class correlation coefficient (ICC) of 0.89 (0.74-0.95). LVEF by trainee was 50.3% (±8.2%) and by expert 53.6% (±8.6%), ICC coefficient was 0.63 (0.32-0.80). For GLS the systematic difference was 0.21% (- 4.58-2.64) vs. 4.08% (- 20.78-12.62) for LVEF. CONCLUSION: GLS is a more reproducible method for evaluation of LV function than LVEF regardless of echocardiographic training.

Early assessment of strain echocardiography can accurately exclude significant coronary artery stenosis in suspected non-ST-segment elevation acute coronary syndrome.

BACKGROUND: Many patients with suspected non-ST-segment elevation acute coronary syndrome (NSTE-ACS) do not have significant coronary artery disease. The current diagnostic approach of repeated electrocardiography and cardiac biomarker assessment requires observation for >6 to 12 hours. This strategy places a heavy burden on hospital facilities. The objective of this study was to investigate whether myocardial strain assessment by echocardiography could exclude significant coronary artery stenosis in patients presenting with suspected NSTE-ACS. METHODS: Sixty-four patients presenting to the emergency department with suspected NSTE-ACS without known coronary artery disease, inconclusive electrocardiographic findings, and normal cardiac biomarkers at arrival were enrolled. Twelve-lead electrocardiography, troponin T assay, and echocardiography were performed at arrival, and all patients underwent coronary angiography. Significant coronary stenosis was defined as >50% luminal narrowing. Global myocardial peak systolic longitudinal strain was measured using speckle-tracking echocardiography. Left ventricular ejection fraction and wall motion score index were calculated. RESULTS: No significant stenosis in any coronary artery was found in 35 patients (55%). Global peak systolic longitudinal strain was superior to conventional echocardiographic parameters in distinguishing patients with and without significant coronary artery stenosis (area under the curve, 0.87). Sensitivity and specificity were calculated as 0.93 and 0.78, respectively, and positive predictive value and negative predictive value as 0.74 and 0.92, respectively. Feasibility of the strain measurements was excellent, with 97% of segments analyzed. CONCLUSIONS: Myocardial strain by echocardiography may facilitate the exclusion of significant coronary artery stenosis among patients presenting with suspected NSTE-ACS with inconclusive electrocardiographic findings and normal cardiac biomarkers.

Are the guidelines for treatment of myocardial infarction complied with?

BACKGROUND: New guidelines recommend early invasive evaluation and treatment for most patients with acute myocardial infarction--including patients with myocardial infarction without ST elevation in the ECG. This study examines compliance with the new guidelines at Sørlandet Hospital Arendal. MATERIAL AND METHOD: All patients admitted to Sørlandet Hospital Arendal with acute myocardial infarction in 2012 were registered in the Norwegian Myocardial Infarction Register. Data from the register were used to analyse the time that passed from symptom onset to coronary angiography and revascularisation. RESULTS: In 2012, 788 patients were admitted to Sørlandet Hospital Arendal with acute myocardial infarction. Of these, 269 (34.1%) had ST elevation mycardial infarction (STEMI) and 519 (65.9%) had non-ST elevation myocardial infarction (NSTEMI). Most patients with ST elevation infarction (220 (81.8%)) were admitted directly to Sørlandet Hospital Arendal, and the median time from admission to revascularisation was 31 minutes. 347 (66.9%) of the patients with non-ST elevation infarction were first admitted to a local hospital before being transferred to Sørlandet Hospital Arendal. Only four (1.2%) of them underwent angiography within two hours of admission to the first hospital. 13 (9.0%) of the patients with non-ST elevation infarction who were admitted directly and underwent angiography (n = 144) had an angiogram within two hours of admission. Angiography was performed within 24 hours in 119 (34.3%) of those transferred (n = 347) and in 82 (56.9%) of the directly admitted patients who underwent angiography (n = 144). INTERPRETATION: Many patients with non-ST elevation infarction did not receive revascularisation with percutaneous coronary intervention (PCI) within the recommended time frame. Where there is a strong clinical suspicion of acute myocardial infarction, more patients should be admitted directly to hospitals with PCI preparedness.

Risk assessment of ventricular arrhythmias in patients with nonischemic dilated cardiomyopathy by strain echocardiography.

BACKGROUND: Indications for prophylactic implantable cardioverter-defibrillator implantation in patients with nonischemic dilated cardiomyopathy (DCM) are based on left ventricular (LV) ejection fraction (LVEF), although LVEF has limited ability to predict arrhythmias. It has recently been shown that strain echocardiography can predict ventricular arrhythmias in patients after myocardial infarction. The aim of this study was to evaluate whether strain echocardiography may help in the risk stratification of ventricular arrhythmias in patients with DCM. METHODS: Ninety-four patients with nonischemic DCM were prospectively included. By speckle-tracking strain echocardiography, global longitudinal strain was calculated as the average of peak longitudinal strain from a 16-segment LV model. The time interval from electrocardiographic peak R to peak negative strain was assessed in each LV segment. Mechanical dispersion was defined as the standard deviation of time to peak negative strain from 16 LV segments. RESULTS: After a median of 22 months of follow-up (range, 1-46 months), 12 patients (13%) had experienced arrhythmic events, defined as sustained ventricular tachycardia or cardiac arrest. LVEF and global longitudinal strain were reduced in patients with DCM with arrhythmic events compared with those without (28 ± 10% vs 38 ± 13%, P = .01, and -6.4 ± 3.3% vs -12.3 ± 5.2%, P < .001, respectively). Global longitudinal strain showed greater area under the curve than LVEF to identify arrhythmic events in receiver operating characteristic curve analyses (P = .05). Patients with arrhythmic events had increased mechanical dispersion (98 ± 43 vs 56 ± 18 ms, P < .001). Mechanical dispersion predicted arrhythmias independently of LVEF (hazard ratio, 1.28; 95% confidence interval, 1.11-1.49; P = .001). CONCLUSIONS: Global longitudinal strain is a promising marker of arrhythmias. Mechanical dispersion predicted arrhythmic events in patients with DCM independently of LVEF. Strain echocardiography may help in the risk stratification of patients with DCM not fulfilling current implantable cardioverter-defibrillator indications.

Mean strain throughout the heart cycle by longitudinal two-dimensional speckle-tracking echocardiography enables early prediction of infarct size.

BACKGROUND: Early prediction of infarct size directs therapy in patients with acute myocardial infarction (AMI). Global strain by echocardiography describes myocardial deformation and correlates with infarct size. However, peak strain measures deformation at a single time point, whereas ischemia and necrosis influence deformation throughout the heart cycle. It was hypothesized that the measurement of myocardial deformation throughout the heart cycle by mean strain is a more comprehensive expression of myocardial deformation. The aim of this study was to assess the ability of mean strain to predict infarct size and to identify large infarctions at admission and after revascularization in patients with AMI. METHODS: Seventy-six patients with AMI were included. Echocardiographic measurements were performed at admission and after revascularization. Myocardial strain was calculated using speckle-tracking echocardiography. Infarct size was measured using contrast-enhanced magnetic resonance imaging ≥3 months after revascularization. RESULTS: There were significant correlations between infarct size and longitudinal global mean strain, longitudinal global strain, and left ventricular ejection fraction (P < .0001), both at admission and after revascularization. The correlations improved after revascularization. Longitudinal global mean strain had the best correlation with infarct size and the best ability to discriminate between different infarct size categories. At admission, a cutoff value of -7.6 had 89% sensitivity, 88% specificity, and an area under the receiver operating characteristic curve of 0.92 for the identification of large infarctions. Prediction of infarct size improved for all parameters after revascularization. CONCLUSIONS: Longitudinal global mean strain provides improved early prediction of infarct size in patients with AMI compared with longitudinal global strain and left ventricular ejection fraction.

Acute coronary occlusion in non-ST-elevation acute coronary syndrome: outcome and early identification by strain echocardiography.

OBJECTIVES: To compare infarct size and left ventricular ejection fraction in patients with non-ST-elevation myocardial infarction (NSTEMI) with and without acute coronary occlusions, and determine if myocardial strain by speckle-tracking echocardiography can identify acute occlusions in patients presenting with non-ST-elevation acute coronary syndrome (NSTE-ACS). METHODS: 111 patients with suspected NSTE-ACS were enrolled shortly after admittance. Echocardiographic measurements were performed a median of 1 h (interquartile range 0.5-4) after admittance, and coronary angiography 36 ± 21 h after onset of symptoms. Territorial longitudinal and circumferential strain was calculated based on the perfusion territories of the three major coronary arteries in a 16-segment model of the left ventricle, and compared with traditional echocardiographic parameters. Long-term follow-up was by echocardiography and contrast-enhanced magnetic resonance imaging (ceMRI). RESULTS: Patients with NSTEMI due to acute coronary occlusion had higher peak troponin T than patients with NSTEMI without acute occlusions (4.9 ± 4.7 vs 0.9 ± 1.1 µg/l, p<0.001), larger infarct size by ceMRI (13 ± 8% vs 3 ± 3%, p<0.001) and poorer left ventricular ejection fraction (48 ± 6% vs 57 ± 6%, p<0.001) at follow-up. Territorial circumferential strain was the best parameter for predicting acute coronary occlusion. A territorial circumferential strain value >-10.0% had 90% sensitivity, 88% specificity and area under the curve=0.93 for identification of acute occlusions. CONCLUSIONS: Patients with NSTEMI due to acute coronary occlusions develop larger infarcts and more impaired left ventricular function than patients with NSTEMI without occlusions, regardless of infarct-related territory. Territorial circumferential strain by echocardiography enables very early identification of acute coronary occlusions in patients with NSTE-ACS and may be used for detection of patients requiring urgent revascularisation.