IMPORTANCE Machine learning algorithms enable the automatic classification of cardiovascular diseases based on raw cardiac ultrasound imaging data. However, the utility of machine learning in... Show moreIMPORTANCE Machine learning algorithms enable the automatic classification of cardiovascular diseases based on raw cardiac ultrasound imaging data. However, the utility of machine learning in distinguishing between takotsubo syndrome (TTS) and acute myocardial infarction (AMI) has not been studied.Objectives To assess the utility of machine learning systems for automatic discrimination of TTS and AMI.Design, Settings, and Participants This cohort study included clinical data and transthoracic echocardiogram results of patients with AMI from the Zurich Acute Coronary Syndrome Registry and patients with TTS obtained from 7 cardiovascular centers in the International Takotsubo Registry. Data from the validation cohort were obtained from April 2011 to February 2017. Data from the training cohort were obtained from March 2017 to May 2019. Data were analyzed from September 2019 to June 2021.Exposure Transthoracic echocardiograms of 224 patients with TTS and 224 patients with AMI were analyzed.Main Outcomes and Measures Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the machine learning system evaluated on an independent data set and 4 practicing cardiologists for comparison. Echocardiography videos of 228 patients were used in the development and training of a deep learning model. The performance of the automated echocardiogram video analysis method was evaluated on an independent data set consisting of 220 patients. Data were matched according to age, sex, and ST-segment elevation/non-ST-segment elevation (1 patient with AMI for each patient with TTS). Predictions were compared with echocardiographic-based interpretations from 4 practicing cardiologists in terms of sensitivity, specificity, and AUC calculated from confidence scores concerning their binary diagnosis.Results In this cohort study, apical 2-chamber and 4-chamber echocardiographic views of 110 patients with TTS (mean [SD] age, 68.4 [12.1] years; 103 [90.4%] were female) and 110 patients with AMI (mean [SD] age, 69.1 [12.2] years; 103 [90.4%] were female) from an independent data set were evaluated. This approach achieved a mean (SD) AUC of 0.79 (0.01) with an overall accuracy of 74.8 (0.7%). In comparison, cardiologists achieved a mean (SD) AUC of 0.71 (0.03) and accuracy of 64.4 (3.5%) on the same data set. In a subanalysis based on 61 patients with apical TTS and 56 patients with AMI due to occlusion of the left anterior descending coronary artery, the model achieved a mean (SD) AUC score of 0.84 (0.01) and an accuracy of 78.6 (1.6%), outperforming the 4 practicing cardiologists (mean [SD] AUC, 0.72 [0.02]) and accuracy of 66.9 (2.8%).Conclusions and Relevance In this cohort study, a real-time system for fully automated interpretation of echocardiogram videos was established and trained to differentiate TTS from AMI. While this system was more accurate than cardiologists in echocardiography-based disease classification, further studies are warranted for clinical application. Show less
Veltman, C.E.; Graaf, F.R. de; Schuijf, J.D.; Werkhoven, J.M. van; Jukema, J.W.; Kaufmann, P.A.; ... ; Wall, E.E. van der 2012
AimsLimited information is available regarding the relationship between coronary vessel dominance and prognosis. Therefore, the purpose of this study was to determine the prognostic value of... Show moreAimsLimited information is available regarding the relationship between coronary vessel dominance and prognosis. Therefore, the purpose of this study was to determine the prognostic value of coronary vessel dominance in relation to significant coronary artery disease (CAD) in patients referred for computed tomography coronary angiography (CTA).Methods and resultsThe study population consisted of 1425 patients (869 men, 57 ± 12 years) referred for CTA. To evaluate the impact of vessel dominance and significant CAD on CTA on outcome, patients were followed during a median period of 24 months for the occurrence of non-fatal myocardial infarction and all-cause mortality. The presence of a left dominant system was identified as a significant predictor for non-fatal myocardial infarction and all-cause mortality (HR: 3.20; 95% CI: 1.67-6.13, P < 0.001) and had incremental value over baseline risk factors and severity of CAD on CTA. In addition, in the subgroup of patients with significant CAD on CTA, patients with a left dominant system had a worse outcome compared with patients with a right dominant system (cumulative event rates: 9.5% and 35% at 3-year follow-up for a right and left dominant coronary artery system, respectively, log-rank P < 0.001).ConclusionsThe presence of a left dominant system was identified as an independent predictor of non-fatal myocardial infarction and all-cause mortality, especially in patients with significant CAD on CTA. Therefore, the assessment of coronary vessel dominance on CTA may further enhance risk stratification beyond the assessment of significant CAD on CTA. Show less
Aims Computed tomography coronary angiography (CTA) is an important non-invasive imaging modality increasingly used for the diagnosis and prognosis of coronary artery disease (CAD). The purpose of... Show moreAims Computed tomography coronary angiography (CTA) is an important non-invasive imaging modality increasingly used for the diagnosis and prognosis of coronary artery disease (CAD). The purpose of the current study was to determine the influence of smoking status on the prognostic value of CTA in patients with suspected or known CAD. Methods and results In 1207 patients (57% male, age 57 +/- 12 years) referred for CTA, the presence of significant CAD (>= 50% stenosis) was determined. During follow-up (FU) the following events were recorded: all cause mortality, and non-fatal infarction. The prognostic value of CTA in smokers and non-smokers was compared using an interaction term in the Cox proportional hazard regression analysis. Significant CAD was observed in 327 patients (27%), and 273 patients (23%) were smokers. During a median FU time of 2.2 years, an event occurred in 50 patients. After correction for baseline characteristics including smoking in a multivariate model, significant CAD remained an independent predictor of events. Furthermore, a significant interaction (P < 0.05) was observed between significant CAD and smoking. The annualized event rate in smokers with significant CAD was 8.78% compared with 0.99% in smokers without significant CAD (P < 0.001). In non-smokers with significant CAD the annualized event rate was 2.07% compared with 1.01% in non-smokers without significant CAD (P = 0.058). Conclusion The prognostic value of CTA was significantly influenced by smoking status. The event rates in patients with significant CAD were approximately four-fold higher in smokers compared with non-smokers. These findings suggest that smoking cessation needs to be aggressively pursued, especially in smokers with significant CAD. Show less
Aims Computed tomography coronary angiography (CTA) is an important non-invasive imaging modality increasingly used for the diagnosis and prognosis of coronary artery disease (CAD). The purpose of... Show moreAims Computed tomography coronary angiography (CTA) is an important non-invasive imaging modality increasingly used for the diagnosis and prognosis of coronary artery disease (CAD). The purpose of the current study was to determine the influence of smoking status on the prognostic value of CTA in patients with suspected or known CAD. Methods and results In 1207 patients (57% male, age 57 ± 12 years) referred for CTA, the presence of significant CAD (≥50% stenosis) was determined. During follow-up (FU) the following events were recorded: all cause mortality, and non-fatal infarction. The prognostic value of CTA in smokers and non-smokers was compared using an interaction term in the Cox proportional hazard regression analysis. Significant CAD was observed in 327 patients (27%), and 273 patients (23%) were smokers. During a median FU time of 2.2 years, an event occurred in 50 patients. After correction for baseline characteristics including smoking in a multivariate model, significant CAD remained an independent predictor of events. Furthermore, a significant interaction (P < 0.05) was observed between significant CAD and smoking. The annualized event rate in smokers with significant CAD was 8.78% compared with 0.99% in smokers without significant CAD (P < 0.001). In non-smokers with significant CAD the annualized event rate was 2.07% compared with 1.01% in non-smokers without significant CAD (P= 0.058). Conclusion The prognostic value of CTA was significantly influenced by smoking status. The event rates in patients with significant CAD were approximately four-fold higher in smokers compared with non-smokers. These findings suggest that smoking cessation needs to be aggressively pursued, especially in smokers with significant CAD. Show less
Background-Previous studies have shown that the presence of stenosis alone on multislice computed tomography (MSCT) has a limited positive predictive value for the presence of ischemia on... Show moreBackground-Previous studies have shown that the presence of stenosis alone on multislice computed tomography (MSCT) has a limited positive predictive value for the presence of ischemia on myocardial perfusion imaging (MPI). The purpose of this study was to assess which variables of atherosclerosis on MSCT angiography are related to ischemia on MPI. Methods and Results-Both MSCT and MPI were performed in 514 patients. On MSCT, the calcium score, degree of stenosis (>= 50% and >= 70% stenosis), and plaque extent and location were determined. Plaque composition was classified as noncalcified, mixed, or calcified. Ischemia was defined as a summed difference score (>= 2 on a per-patient basis. Ischemia was observed in 137 patients (27%). On a per-patient basis, multivariate analysis showed that the degree of stenosis (presence of (>= 70% stenosis, odds ratio=3.5), plaque extent and composition (mixed plaques (>= 3, odds ratio=1.7; calcified plaques >= 3, odds ratio=2.0), and location (atherosclerotic disease in the left main coronary artery and/or proximal left anterior descending coronary artery, odds ratio=1.6) were independent predictors for ischemia on MPI. In addition, MSCT variables of atherosclerosis, such as plaque extent, composition, and location, had significant incremental value for the prediction of ischemia over the presence of >= 70% stenosis. Conclusions-In addition to the degree of stenosis, MSCT variables of atherosclerosis describing plaque extent, composition, and location are predictive of the presence of ischemia on MPI. (Circ Cardiovasc Imaging. 2010; 3: 718-726.) Show less
