Anna Kotsia

Automated Diagnosis of Coronary Artery Disease Based on Data Mining and Fuzzy Modeling

A fuzzy rule-based decision support system (DSS) is presented for the diagnosis of coronary artery disease (CAD). The system is automatically generated from an initial annotated dataset, using a four stage methodology: 1) induction of a decision tree from the data; 2) extraction of a set of rules from the decision tree, in disjunctive normal form and formulation of a crisp model; 3) transformation of the crisp set of rules into a fuzzy model; and 4) optimization of the parameters of the fuzzy model. The dataset used for the DSS generation and evaluation consists of 199 subjects, each one characterized by 19 features, including demographic and history data, as well as laboratory examinations. Tenfold cross validation is employed, and the average sensitivity and specificity obtained is 62% and 54%, respectively, using the set of rules extracted from the decision tree (first and second stages), while the average sensitivity and specificity increase to 80% and 65%, respectively, when the fuzzification and optimization stages are used. The system offers several advantages since it is automatically generated, it provides CAD diagnosis based on easily and noninvasively acquired features, and is able to provide interpretation for the decisions made.

The efficacy of "hybrid" percutaneous coronary intervention in chronic total occlusions caused by in-stent restenosis: insights from a US multicenter registry.

To examine the success and complication rates in percutaneous coronary intervention (PCI) for chronic total occlusions (CTO) caused by in‐stent restenosis (ISR).

Transradial approach for coronary chronic total occlusion interventions: Insights from a contemporary multicenter registry

To examine the impact of transradial access on the procedural outcomes of chronic total occlusion (CTO) percutaneous coronary interventions (PCI).

Procedural failure of chronic total occlusion percutaneous coronary intervention: Insights from a multicenter US registry

The hybrid approach to chronic total occlusion (CTO) percutaneous coronary intervention (PCI) has significantly increased procedural success rates, yet some cases still fail. We sought to evaluate the causes of failure in a contemporary CTO PCI registry.

Percutaneous Intervention of Circumflex Chronic Total Occlusions Is Associated With Worse Procedural Outcomes: Insights From a Multicentre US Registry

BACKGROUND We sought to determine whether outcomes of chronic total occlusion (CTO) percutaneous coronary intervention (PCI) vary according to CTO target vessel: left anterior descending artery (LAD), left circumflex artery (LCX), and right coronary artery (RCA). METHODS We evaluated the clinical and angiographic characteristics and procedural outcomes of 636 patients who underwent CTO PCI at 6 high-volume centres in the United States between January 2012 and March 2014. RESULTS The CTO target vessel was the RCA in 387 cases (61%), LAD in 132 (21%), and LCX in 117 (18%). LCX lesions were more tortuous and RCA lesions had greater occlusion length and Japanese Chronic Total Occlusion (J-CTO) score, but were less likely to have a side branch at the proximal cap and had more developed collateral circulation. The rate of procedural success was lower in LCX CTOs (84.6%), followed by RCA (91.7%), and LAD (94.7%) CTOs (P = 0.016). Major complications tended to occur more frequently in LCX PCI (4.3% vs 1.0% for RCA vs 2.3% for LAD; P = 0.07). LCX and RCA CTO PCI required longer fluoroscopy times (45 [interquartile range (IQR), 30-74] minutes vs 45 [IQR, 21-69] minutes for RCA vs 34 [IQR, 20-60] minutes for LAD; P = 0.018) and LCX CTOs required more contrast administration (280 [IQR, 210-370] mL vs 250 [IQR, 184-350] mL for RCA and 280 [IQR, 200-400] mL for LAD). CONCLUSIONS In a contemporary, multicentre CTO PCI registry, LCX was the least common target vessel. Compared with LAD and RCA, PCI of LCX CTOs was associated with a lower rate of procedural success, less efficiency, and a nonsignificant trend for higher rates of complications.

Anatomically correct three-dimensional coronary artery reconstruction using frequency domain optical coherence tomographic and angiographic data: head-to-head comparison with intravascular ultrasound for endothelial shear stress assessment in humans.

AIMS To develop a methodology that permits accurate 3-dimensional (3D) reconstruction from FD-OCT and angiographic data enabling reliable evaluation of the ESS distribution, and to compare the FD-OCT-derived models against the established models based on angiography/IVUS. METHODS AND RESULTS Fifteen patients (17 coronary arteries) who underwent angiography, FD-OCT and IVUS examination during the same procedure were studied. The FD-OCT and IVUS lumen borders were placed onto the 3D luminal centreline derived from angiographic data. Three-dimensional geometry algorithms and anatomical landmarks were used to estimate the orientation of the borders appropriately. ESS was calculated using computational fluid dynamics. In 188 corresponding consecutive 3-mm segments, FD-OCT- and IVUS-derived models were highly correlated for lumen area (r=0.96) and local ESS (r=0.89) measurements. FD-OCT-based 3D reconstructions had a high diagnostic accuracy for detecting regions exposed to proatherogenic low ESS identified on the IVUS-based 3D models, considered as the gold standard (receiver operator characteristic area under the curve: 94.9%). CONCLUSIONS FD-OCT-based 3D coronary reconstruction provides anatomically correct models and permits reliable ESS computation. ESS assessment in combination with the superior definition of plaque characteristics by FD-OCT is expected to provide valuable insights into the effect of the haemodynamic environment on the development and destabilisation of high-risk plaques.

Optimizing Radiation Safety in the Cardiac Catheterization Laboratory: A Practical Approach.

Reducing radiation exposure during cardiovascular catheterization is of paramount importance for both patient and staff safety. Over the years, advances in equipment and application of radiation safety protocols have significantly reduced patient dose and operator exposure. This review examines the current status of radiation protection in the cardiac and vascular catheterization laboratory and summarizes best practices for minimizing radiation exposure.

Accuracy of remote electrocardiogram interpretation with the use of Google Glass technology.

We sought to investigate the accuracy of remote electrocardiogram (ECG) interpretation using Google Glass (Google, Mountain View, California). Google Glass is an optical head mounted display device with growing applications in medicine. We compared interpretation of 10 ECGs with 21 clinically important findings by faculty and fellow cardiologists by (1) viewing the electrocardiographic image at the Google Glass screen; (2) viewing a photograph of the ECG taken using Google Glass and interpreted on a mobile device; (3) viewing the original paper ECG; and (4) viewing a photograph of the ECG taken with a high-resolution camera and interpreted on a mobile device. One point was given for identification of each correct finding. Subjective rating of the user experience was also recorded. Twelve physicians (4 faculty and 8 fellow cardiologists) participated. The average electrocardiographic interpretation score (maximum 21 points) as viewed through the Google Glass, Google Glass photograph on a mobile device, on paper, and high-resolution photograph on a mobile device was 13.5 ± 1.8, 16.1 ± 2.6, 18.3 ± 1.7, and 18.6 ± 1.5, respectively (p = 0.0005 between Google Glass and mobile device, p = 0.0005 between Google Glass and paper, and p = 0.002 between mobile device and paper). Of the 12 physicians, 9 (75%) were dissatisfied with ECGs viewing on the prism display of Google Glass. In conclusion, further improvements are needed before Google Glass can be reliably used for remote electrocardiographic analysis.

Effect of a Real-Time Radiation Monitoring Device on Operator Radiation Exposure During Cardiac Catheterization The Radiation Reduction During Cardiac Catheterization Using Real-Time Monitoring Study

Background—The Radiation Reduction During Cardiac Catheterization Using Real-Time Monitoring study sought to examine the effect of a radiation detection device that provides real-time operator dose reporting through auditory feedback (Bleeper Sv; Vertec Scientific Ltd; Berkshire, UK) on patient dose and operator exposure during cardiac catheterization. Methods and Results—Between January 2012 and May 2014, 505 patients undergoing coronary angiography, percutaneous coronary intervention, or both were randomized to use (n=253) or no use (n=252) of the Bleeper Sv radiation monitor. Operator radiation exposure was measured in both groups using a second, silent radiation exposure monitoring device. Mean patient age was 65±8 years, most patients (99%) were men, and 30% had prior coronary artery bypass graft surgery. Baseline clinical characteristics were similar in the 2 study groups. Radial access was used in 18% and chronic total occlusion percutaneous coronary intervention constituted 7% of the total procedures. Median procedure time was 17 (12–27) minutes for diagnostic angiography, 42 (28–70) minutes for percutaneous coronary intervention, and 27 (14–51) minutes in the overall study population, with similar distribution between the study groups. First (9 [4–17] versus 14 [7–25] &mgr;Sv; P<0.001) and second (5 [2–10] versus 7 [4–14] &mgr;Sv; P<0.001) operator radiation exposure was significantly lower in the Bleeper Sv group. Use of the device did not result in a significant reduction in patient radiation dose. The effect of the Bleeper Sv device on operator radiation exposure was consistent among various study subgroups. Conclusions—Use of a real-time radiation monitoring device that provides auditory feedback can significantly reduce operator radiation exposure during cardiac catheterization. Clinical Trial Registration—URL: http://www.clinicaltrials.gov. Unique identifier: NCT01510353.

Paradoxical protective effect of central obesity in patients with suspected stable coronary artery disease

Increased body mass index (BMI) has been paradoxically inversely associated with the presence of angiographic coronary artery disease (CAD). Central obesity measures, considered to be more appropriate for assessing obesity‐related cardiovascular risk, have been little studied in relation to the presence of CAD. The aim was to investigate the association of central obesity with the presence of angiographic CAD as well as the prognostic significance of obesity measures in CAD prediction when added to other cardiovascular risk factors.