Machine learning assessment of myocardial ischemia using angiography: Development and retrospective validation.

BACKGROUND: Invasive fractional flow reserve (FFR) is a standard tool for identifying ischemia-producing coronary stenosis. However, in clinical practice, over 70% of treatment decisions still rely on visual estimation of angiographic stenosis, which has limited accuracy (about 60%-65%) for the prediction of FFR < 0.80. One of the reasons for the visual-functional mismatch is that myocardial ischemia can be affected by the supplied myocardial size, which is not always evident by coronary angiography. The aims of this study were to develop an angiography-based machine learning (ML) algorithm for predicting the supplied myocardial volume for a stenosis, as measured using coronary computed tomography angiography (CCTA), and then to build an angiography-based classifier for the lesions with an FFR < 0.80 versus ≥ 0.80. METHODS AND FINDINGS: A retrospective study was conducted using data from 1,132 stable and unstable angina patients with 1,132 intermediate lesions who underwent invasive coronary angiography, FFR, and CCTA at the Asan Medical Center, Seoul, Korea, between 1 May 2012 and 30 November 2015. The mean age was 63 ± 10 years, 76% were men, and 72% of the patients presented with stable angina. Of these, 932 patients (assessed before 31 January 2015) constituted the training set for the algorithm, and 200 patients (assessed after 1 February 2015) served as a test cohort to validate its diagnostic performance. Additionally, external validation with 79 patients from two centers (CHA University, Seongnam, Korea, and Ajou University, Suwon, Korea) was conducted. After automatic contour calibration using the caliber of guiding catheter, quantitative coronary angiography was performed using the edge-detection algorithms (CAAS-5, Pie-Medical). Clinical information was provided by the Asan BiomedicaL Research Environment (ABLE) system. The CCTA-based myocardial segmentation (CAMS)-derived myocardial volume supplied by each vessel (right coronary artery [RCA], left anterior descending [LAD], left circumflex [LCX]) and the myocardial volume subtended to a stenotic segment (CAMS-%Vsub) were measured for labeling. The ML for (1) predicting vessel territories (CAMS-%LAD, CAMS-%LCX, and CAMS-%RCA) and CAMS-%Vsub and (2) identifying the lesions with an FFR < 0.80 was constructed. Angiography-based ML, employing a light gradient boosting machine (GBM), showed mean absolute errors (MAEs) of 5.42%, 8.57%, and 4.54% for predicting CAMS-%LAD, CAMS-%LCX, and CAMS-%RCA, respectively. The percent myocardial volumes predicted by ML were used to predict the CAMS-%Vsub. With 5-fold cross validation, the MAEs between ML-predicted percent myocardial volume subtended to a stenotic segment (ML-%Vsub) and CAMS-%Vsub were minimized by the elastic net (6.26% ± 0.55% for LAD, 5.79% ± 0.68% for LCX, and 2.95% ± 0.14% for RCA lesions). Using all attributes (age, sex, involved vessel segment, and angiographic features affecting the myocardial territory and stenosis degree), the ML classifiers (L2 penalized logistic regression, support vector machine, and random forest) predicted an FFR < 0.80 with an accuracy of approximately 80% (area under the curve [AUC] = 0.84-0.87, 95% confidence intervals 0.71-0.94) in the test set, which was greater than that of diameter stenosis (DS) > 53% (66%, AUC = 0.71, 95% confidence intervals 0.65-0.78). The external validation showed 84% accuracy (AUC = 0.89, 95% confidence intervals 0.83-0.95). The retrospective design, single ethnicity, and the lack of clinical outcomes may limit this prediction model's generalized application. CONCLUSION: We found that angiography-based ML is useful to predict subtended myocardial territories and ischemia-producing lesions by mitigating the visual-functional mismatch between angiographic and FFR. Assessment of clinical utility requires further validation in a large, prospective cohort study.

Intravascular ultrasound assessment of cobalt chromium versus stainless steel drug-eluting stent expansion.

It is not clear whether the thin struts and different alloy of a cobalt chromium stent will cause greater acute stent recoil compared to conventional stainless steel stents. We used postintervention intravascular ultrasound (IVUS) examinations to study 99 patients with 116 stented lesions: 61 Xience/Promus stents (cobalt chromium stent group) and 27 Taxus Liberté and 28 Cypher stents (stainless steel stent group). The IVUS images were obtained before and immediately after stent implantation with only the stent-delivery balloon. The ratio of the IVUS-measured to manufacturer-predicted stent diameter and area was the measure of acute stent recoil and expansion. The baseline patient characteristics, lesion morphology, and procedural details were comparable between the 2 groups. The ratio of the IVUS-measured to manufacturer-predicted stent diameter and area was 0.74 versus 0.73 (p = 0.57) and 0.63 versus 0.63 (p = 0.69), respectively, for the cobalt chromium and stainless steel stents. In conclusion, the acute performance of Xience/Promus was similar to that of previous stainless steel stents, and the thinner cobalt chromium metallic platform did not compromise the radial strength of the stent.

Assessment of intraventricular systolic asynchrony in patients with atrial fibrillation using triplane tissue Doppler imaging.

BACKGROUND: Triplane tissue Doppler imaging (TDI) makes it possible to simultaneously obtain three apical view images and to measure the dyssynchrony index (DS) for 12 segments in patients with atrial fibrillation (AF). We evaluated the feasibility of using triplane TDI to assess intraventricular asynchrony in AF. METHODS: In 50 patients with AF, triplane TDI was used for the analysis of myocardial velocity curves of 12 (six basal and six mid) left ventricular (LV) segments by apical two-, three-, and four-chamber views. Time to peak systolic velocity (Ts) was measured, and DS was calculated as the standard deviation (SD) of Ts over 12 segments. The DS(avg) was defined as the average of DS of eight consecutive cycles. To assess the cyclic variability of DS, the coefficient of variation of DS (CoV(DS)) was calculated as the SD of DS for eight cycles divided by DS(avg) [SD(DS)/DS(avg)]. CoV(RR), representing the variability of RR intervals, was defined as [SD(RR)/RR(avg)]. Patients with a left ventricular ejection fraction (LVEF) of 45% or more were classified as group A, and patients with an LVEF less than 45% as were classified as group B. RESULTS: The mean LVEF was 47% +/- 12%. Group B showed larger LV volume and lower sphericity index compared with group A. Intraobserver and interobserver variability of DS(avg) were 6% and 9%, respectively. More severe dyssynchrony was observed in group B (DS(avg); 23.5 +/- 8.5 ms in group B vs. 17.7 +/- 6.1 ms in group A, P = .008). DS(avg) was not related to RR(avg) or CoV(RR). DS(avg) negatively correlated with ejection fraction (r = -0.404, P = .004) and sphericity index (r = -0.317, P = .025) and showed positive correlation with LV volume. CONCLUSION: Analysis of asynchrony by triplane TDI was feasible in patients with AF. DS(avg) correlated with echocardiographic parameters of systolic function.