JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, VOL. 70, NO. 18, SUPPL B, 2017
B76
8 Analytics 4 Life, Toronto, Ontario, Canada; 9Analytics 4 Life, Morrisville, North Carolina, United States
BACKGROUND Combined with machine learning, cardiac phase space tomography analysis (cPSTA) evaluates thoracic physiological signals, without the use of radiation, exercise, or pharmacological stress, to identify algorithmic signatures that are associated with the presence of flow-limiting coronary artery disease (CAD). The ongoing Coronary Artery Disease Learning & Algorithm Development (CADLAD) study is determining the diagnostic performance of cPSTA in assessing CAD among patients with chest pain, referred for coronary angiography (ANGIO). This analysis focuses on obese and elderly patients, since conventional CAD detection pathways may be less accurate in these patients. METHODS This prospective, multicenter, non-significant risk study was designed to develop and test machine-learned algorithms to assess the presence of CAD (defined as one or more 70% stenosis, or fractional flow reserve < 0.80). The overall interim results of CADLAD have been submitted elsewhere for presentation. This analysis focuses on CADLAD elderly (>65 years of age) and obese (body mass index or BMI > 30). cPSTA signals were collected at rest, prior to ANGIO. Features (mathematical and tomographic) were extracted from the signals, used for machine learning, and blindly, prospectively tested in a validation cohort. RESULTS ANGIO results were paired with cPSTA data from 513 subjects to generate a machine-learned algorithm to assess for significant CAD. A separate validation cohort of 94 subjects was used to prospectively test the accuracy. This analysis focused on subjects: > 65 vs. < 65 years of age and those with a BMI of > 30 vs. <30 (Table). Table. cPSTA Performance in elderly and obese populations
Number Sensitivity (95% CI) Specificity
Age < 65
Age > [ 65
BMI < 30
65
29
37
57
100%
86% (56%,100%)
92% (50%,
83% (46%,
63% (49%, 75%)
67% (40%, 88%)
67% (44%, 84%)
67% (51%, 79%)
0.79 (0.66, 0.88)
0.72 (0.50, 0.88)
0.80 (0.62, 0.92)
0.78 (0.64, 0.88)
100%
83% (50%,100%)
94% (68%,100%)
(100%,100%)
BMI > [ 30
100%)
100%)
(95% CI) AUC (95% CI)
Zixuan Zhang,3 Roxana Mehran,10 A. Pieter Kappetein,11 Gregg Stone12 Icahn School of Medicine at Mount Sinai, New York, New York, United States; 2Department of Thoracic and Cardiovascular Surgery, The Cleveland Clinic Foundation, Cleveland, Ohio, United States; 3 Cardiovascular Research Foundation, New York, New York, United States; 4Department of Cardiothoracic Surgery, Erasmus Medical Center, Rotterdam, Netherlands; 5Imperial College, London, United Kingdom; 6Piedmont Heart Institute, Atlanta, Georgia, United States; 7 CERC, Massy, France; 8University of Leicester, Leicester, United Kingdom; 9Columbia, new york, New York, United States; 10Zena and Michael A. Wiener Cardiovascular Institute, Mount Sinai Hospital, New York, New York, United States; 11Department of Cardiothoracic Surgery, Erasmus University Medical Center, Rotterdam, Netherlands; 12 Cardiovascular Research Foundation, Columbia University Medical Center/NewYork-Presbyterian Hospital, New York, New York, United States 1
BACKGROUND The optimal revascularization strategy for pts with left main coronary artery disease (LMCAD) and chronic kidney disease (CKD) remains unclear. METHODS We investigated the outcomes of PCI with everolimuseluting stents vs CABG in pts with LMCAD disease and low or intermediate SYNTAX scores according to baseline CKD from the multicenter randomized EXCEL trial. CKD was defined as an estimated creatinine clearance (CrCl) <60 mL/min. The primary endpoint was the composite of death, MI, or stroke at 3 years. Event rates were estimated with the Kaplan-Meier method, and hazard ratios (HR) for PCI vs CABG were generated using Cox regression models. RESULTS Of 1869 randomized pts with baseline CrCl data, 308 (16.5%) had CKD. Continuously worse baseline renal function was associated with an increasing risk of death, stroke, or MI at 3-year follow-up (Figure). Compared with CABG, PCI was associated with lower rates of in-hospital major adverse events in both CKD and no-CKD patients. At 3 years, there were no significant differences in the rates of death, stroke, or MI between PCI and CABG in pts with CKD (24.3% vs 19.2%; absolute risk difference [ARD] 5.1%; HR 1.23; 95%CI 0.75–2.04) or without CKD (13.4% vs 13.7%; ARD -0.3%; HR 0.94; 95%CI 0.71–1.23) (Pinteraction¼0.34).
(Area Under the receiveroperator characteristic Curve) NPV (95% CI) (Negative
(100%,100%)
94% (79%,100%)
Predictive Value) TP (True
11
12
12
10
34
10
16
30
20
5
8
15
0
2
1
2
Positive) TN (True Negative) FP (False Positive) FN (False Negative)
CONCLUSION These initial data, while of limited power, suggest that resting cPSTA imaging performs well overall, and in both the elderly and obese subgroups. The study is ongoing and is designed to test the utility of cPSTA in a large population and other important subgroups. CATEGORIES IMAGING: Imaging: Non-Invasive
LMCA: CABG VS PCI
Abstract nos: 178, 180–182, 835 TCT-178 Everolimus-Eluting Stents versus Coronary Artery Bypass Graft Surgery for Left Main Coronary Artery Disease in Patients with and without Chronic Kidney Disease Gennaro Giustino,1 Joseph Sabik,2 Bjorn Redfors,3 Milan Milojevic,4 Patrick Serruys,5 David Kandzari,6 Marie-Claude Morice,7 Anthony Gershlick,8 Philippe Genereux,9 Ovidiu Dressler,3
CONCLUSION In the EXCEL trial, worse baseline renal function was associated with an increased risk of adverse events in pts with LMCAD undergoing PCI or CABG. The effect of PCI vs CABG on the 3-year rates of death, stroke, or MI was consistent in pts with and without CKD. CATEGORIES OTHER: Renal Insufficiency and Contrast Nephropathy TCT-180 Impact of Chronic Obstructive Pulmonary Disease in Patients with Left Main Disease Randomized to PCI vs. CABG: A Propensity Score Matched Analysis From the EXCEL Trial Xin Huang,1 Bjorn Redfors,2 Shmuel Chen,3 Yangbo Liu,2 Ori Ben-Yehuda,4 David Kandzari,5 Roxana Mehran,6 Ad van Boven,7 Piet Willem Boonstra,8 Joseph Sabik,9 Patrick Serruys,10 A. Pieter Kappetein,11 Gregg Stone12 1 Cardiovascular Research Foundation, NY, Armenia; 2Cardiovascular Research Foundation, New York, New York, United States; 3CRF, New