Data-driven models for the prediction of coronary atherosclerotic plaque progression/regression.

Coronary artery disease is defined by the existence of atherosclerotic plaque on the arterial wall, which can cause blood flow impairment, or plaque rupture, and ultimately lead to myocardial ischemia. Intravascular ultrasound (IVUS) imaging can provide a detailed characterization of lumen and vessel features, and so plaque burden, in coronary vessels. Prediction of the regions in a vascular segment where plaque burden can either increase (progression) or decrease (regression) following a certain therapy, has remained an elusive major milestone in cardiology. Studies like IBIS-4 showed an association between plaque burden regression and high-intensity rosuvastatin therapy over 13 months. Nevertheless, it has not been possible to predict if a patient would respond in a favorable/adverse fashion to such a treatment. This work aims to (i) Develop a framework that processes lumen and vessel cross-sectional contours and extracts geometric descriptors from baseline and follow-up IVUS pullbacks; and to (ii) Develop, train, and validate a machine learning model based on baseline/follow-up IVUS datasets that predicts future percent of atheroma volume changes in coronary vascular segments using only baseline information, i.e. geometric features and clinical data. This is a post hoc analysis, revisiting the IBIS-4 study. We employed 140 arteries, from 81 patients, for which expert delineation of lumen and vessel contours were available at baseline and 13-month follow-up. Contour data from baseline and follow-up pullbacks were co-registered and then processed to extract several frame-wise features, e.g. areas, plaque burden, eccentricity, etc. Each pullback was divided into regions of interest (ROIs), following different criteria. Frame-wise features were condensed into region-wise markers using tools from statistics, signal processing, and information theory. Finally, a stratified 5-fold cross-validation strategy (20 repetitions) was used to train/validate an XGBoost regression models. A feature selection method before the model training was also applied. When the models were trained/validated on ROI defined by the difference between follow-up and baseline plaque burden, the average accuracy and Mathews correlation coefficient were 0.70 and 0.41 respectively. Using a ROI partition criterion based only on the baseline's plaque burden resulted in averages of 0.60 accuracy and 0.23 Mathews correlation coefficient. An XGBoost model was capable of predicting plaque progression/regression changes in coronary vascular segments of patients treated with rosuvastatin therapy in 13 months. The proposed method, first of its kind, successfully managed to address the problem of stratification of patients at risk of coronary plaque progression, using IVUS images and standard patient clinical data.

Prevalence and Characteristics of Patients With Systemic Sclerosis Fulfilling the 2019 EULAR/American College of Rheumatology Classification Criteria for Systemic Lupus Erythematosus.

OBJECTIVE: There is limited literature describing the overlap of systemic sclerosis (SSc) and systemic lupus erythematosus (SLE), and the studies have employed a range of case definitions. Our study used the new EULAR/American College of Rheumatology (ACR) SLE classification criteria to define SSc-SLE cases among our center's SSc cohort. METHODS: This is a single-center, retrospective study of a previously described cohort of patients with SSc. Patient data were re-abstracted to evaluate for fulfillment of the 2019 EULAR/ACR classification criteria for SLE. Demographic, laboratory, clinical features, and mortality were compared among patients with SSc-SLE and patients with SSc alone. RESULTS: Among the 402 patients with SSc that were analyzed, 40 (10%) fulfilled the 2019 EULAR/ACR SLE classification criteria. Neuropsychiatric and renal involvement were rare. An initial SLE diagnosis was purported in 43% of the patients with SSc-SLE and 7% of patients with SSc alone (P < 0.001). Patients with SSc-SLE were more likely to be female, African American, and with limited cutaneous SSc. Anti-U1-RNP antibody positivity prevalence was 30% among patients with SSc-SLE and 6.6% among patients with SSc alone (P < 0.001). Death during follow-up occurred in 12 patients (30%) with SSc-SLE and in 81 patients (22%) with SSc alone, but there was no difference in survival among the groups per log rank test (P = 0.404). CONCLUSION: Ten percent of patients with SSc fulfill the 2019 EULAR/ACR classification criteria for SLE. These patients comprise a distinct demographic, serologic, and clinical phenotype but have similar severe SSc-specific end-organ damage and mortality as patients with SSc alone. Patients with SLE with Raynaud phenomenon should be evaluated for SSc-specific autoantibodies and scleroderma organ involvement.

Effect of High-Intensity Statin Therapy on Atherosclerosis (IBIS-4): Manual Versus Automated Methods of IVUS Analysis.

AIMS: Standard manual analysis of IVUS to study the impact of anti-atherosclerotic therapies on the coronary vessel wall is done by a core laboratory (CL), the ground truth (GT). Automatic segmentation of IVUS with a machine learning (ML) algorithm has the potential to replace manual readings with an unbiased and reproducible method. The aim is to determine if results from a CL can be replicated with ML methods. METHODS: This is a post-hoc, comparative analysis of the IBIS-4 (Integrated Biomarkers and Imaging Study-4) study (NCT00962416). The GT baseline and 13-month follow-up measurements of lumen and vessel area and percent atheroma volume (PAV) after statin induction were repeated by the ML algorithm. RESULTS: The primary endpoint was change in PAV. PAV as measured by GT was 43.95 % at baseline and 43.02 % at follow-up with a change of -0.90 % (p = 0.007) while the ML algorithm measured 43.69 % and 42.41 % for baseline and follow-up, respectively, with a change of -1.28 % (p < 0.001). Along the most diseased 10 mm segments, GT-PAV was 52.31 % at baseline and 49.42 % at follow-up, with a change of -2.94 % (p < 0.001). The same segments measured by the ML algorithm resulted in PAV of 51.55 % at baseline and 47.81 % at follow-up with a change of -3.74 % (p < 0.001). CONCLUSIONS: PAV, the most used endpoint in clinical trials, analyzed by the CL is closely replicated by the ML algorithm. ML automatic segmentation of lumen, vessel and plaque effectively reproduces GT and may be used in future clinical trials as the standard.

The Ability of Near-Infrared Spectroscopy to Identify Vulnerable Patients and Plaques: A Systematic Review and Meta-Analysis.

Previous studies have analyzed the efficacy of near-infrared spectroscopy-derived lipid core burden index (LCBI) in quantifying and identifying high-risk plaques and patients at increased risk of future major adverse cardiac outcomes/major adverse cardiovascular and cerebrovascular events. A maxLCBI4mm of 400 or greater seems to be an effective threshold for classifying at-risk plaques. This meta-analysis provides a more precise odds ratio with a narrow standard deviation that can be used to guide future studies.

Fully automated lumen and vessel contour segmentation in intravascular ultrasound datasets.

Segmentation of lumen and vessel contours in intravascular ultrasound (IVUS) pullbacks is an arduous and time-consuming task, which demands adequately trained human resources. In the present study, we propose a machine learning approach to automatically extract lumen and vessel boundaries from IVUS datasets. The proposed approach relies on the concatenation of a deep neural network to deliver a preliminary segmentation, followed by a Gaussian process (GP) regressor to construct the final lumen and vessel contours. A multi-frame convolutional neural network (MFCNN) exploits adjacency information present in longitudinally neighboring IVUS frames, while the GP regression method filters high-dimensional noise, delivering a consistent representation of the contours. Overall, 160 IVUS pullbacks (63 patients) from the IBIS-4 study (Integrated Biomarkers and Imaging Study-4, Trial NCT00962416), were used in the present work. The MFCNN algorithm was trained with 100 IVUS pullbacks (8427 manually segmented frames), was validated with 30 IVUS pullbacks (2583 manually segmented frames) and was blindly tested with 30 IVUS pullbacks (2425 manually segmented frames). Image and contour metrics were used to characterize model performance by comparing ground truth (GT) and machine learning (ML) contours. Median values (interquartile range, IQR) of the Jaccard index for lumen and vessel were 0.913, [0.882,0.935] and 0.940, [0.917,0.957], respectively. Median values (IQR) of the Hausdorff distance for lumen and vessel were 0.196mm, [0.146,0.275]mm and 0.163mm, [0.122,0.234]mm, respectively. Also, the mean value of lumen area predictions, and limits of agreement were -0.19mm2, [1.1,-1.5]mm2, while the mean value and limits of agreement of plaque burden were 0.0022, [0.082,-0.078]. The results obtained with the model developed in this work allow us to conclude that the proposed machine learning approach delivers accurate segmentations in terms of image metrics, contour metrics and clinically relevant variables, enabling its use in clinical routine by mitigating the costs involved in the manual management of IVUS datasets.

Human vs. machine vs. core lab for the assessment of coronary atherosclerosis with lumen and vessel contour segmentation with intravascular ultrasound.

A machine learning (ML) algorithm for automatic segmentation of intravascular ultrasound was previously validated. It has the potential to improve efficiency, accuracy and precision of coronary vessel segmentation compared to manual segmentation by interventional cardiology experts. The aim of this study is to compare the performance of human readers to the machine and against the readings from a Core Laboratory. This is a post-hoc, cross-sectional analysis of the IBIS-4 study. Forty frames were randomly selected and analyzed by 10 readers of varying expertise two separate times, 1 week apart. Their measurements of lumen, vessel, plaque areas, and plaque burden were performed in an offline software. Among humans, the intra-observer variability was not statistically significant. For the total 80 frames, inter-observer variability between human readers, the ML algorithm and Core Laboratory for lumen area, vessel area, plaque area and plaque burden were not statistically different. For lumen area, however, relative differences between the human readers and the Core Lab ranged from 0.26 to 12.61%. For vessel area, they ranged from 1.25 to 9.54%. Efficiency between the ML algorithm and the readers differed notably. Humans spent 47 min on average to complete the analyses, while the ML algorithm took on average less than 1 min. The overall lumen, vessel and plaque means analyzed by humans and the proposed ML algorithm are similar to those of the Core Lab. Machines, however, are more time efficient. It is warranted to consider use of the ML algorithm in clinical practice.

Changes in Percutaneous Coronary Interventions Deemed "Inappropriate" by Appropriate Use Criteria.

BACKGROUND: Recent studies have demonstrated relatively high rates of percutaneous coronary interventions (PCIs) classified as "inappropriate." The New York State Department of Health shared rates with hospitals and announced the intention of withholding reimbursement pending demonstration of clinical rationale for Medicaid patients with inappropriate PCIs. OBJECTIVES: The objective was to examine changes over time in the number and rate of inappropriate PCIs. METHODS: Appropriate use criteria were applied to PCIs performed in New York in patients without acute coronary syndromes or previous coronary artery bypass graft surgery in periods before (2010 through 2011) and after (2012 through 2014) efforts were made to decrease inappropriateness rates. Changes in the number of appropriate PCIs were also assessed. RESULTS: The percentage of inappropriate PCIs for all patients dropped from 18.2% in 2010 to 10.6% in 2014 (from 15.3% to 6.8% for Medicaid patients, and from 18.6% to 11.2% for other patients). The total number of PCIs in patients with no acute coronary syndrome/no prior coronary artery bypass graft surgery that were rated as inappropriate decreased from 2,956 patients in 2010 to 911 patients in 2014, a reduction of 69%. For Medicaid patients, the decrease was from 340 patients to 84 patients, a decrease of 75%. For a select set of higher-risk scenarios, there were higher numbers of appropriate PCIs per year in the period from 2012 to 2014. CONCLUSIONS: The inappropriateness rate for PCIs and the use of PCI for elective procedures in New York has decreased substantially between 2010 and 2014. This decrease has occurred for a large proportion of PCI hospitals.

Relationship between socioeconomic status and physical fitness in junior high school students.

BACKGROUND: Research on physical fitness often regards socioeconomic status (SES) as a confounding factor. However, few studies investigate the impact of SES on fitness. This study investigated the impact of SES on physical fitness in both males and females, with an economic-based construct of SES. METHODS: The sample consisted of 954 6th, 7th, and 8th graders from a public, urban, Illinois middle school. The students participated in the FITNESSGRAM battery of fitness assessments as part of physical education. Descriptive statistics were calculated for height, weight, age, and sex. Students were grouped as high or low SES depending on whether they qualified for the federal free lunch program. A multivariate analysis of variance controlled for age and stratified by sex compared the raw scores from the fitness test for low and high SES students. Odds ratios stratified by sex were calculated for the likelihood of not achieving the FITNESSGRAM Healthy Fitness Zone standards among SES groups. RESULTS: Girls of the low SES group had significantly lower scores on the FITNESSGRAM assessments and were significantly less likely to achieve Healthy Fitness Zone status than the girls from the high SES groups. For boys, SES was a significant main effect for body composition but not for the other fitness tests conducted. CONCLUSION: SES is related to physical fitness in girls but not in boys. A potential explanation for this is that boys are more likely to engage in vigorous leisure time activity regardless of SES than girls.

Physical fitness and academic performance in middle school students.

AIM: The purpose of this study was to determine whether physical fitness is linked to academic success in middle school students. METHODS: The FITNESSGRAM test battery assessed students (n = 838) in the five components of health-related fitness. The Illinois Standardized Achievement Test (ISAT) was used to assess academic achievement in reading and math. RESULTS: The largest correlations were seen for aerobic fitness and muscular endurance (ranging from 0.12 to 0.27, all p < 0.05). Boys in the Healthy Fitness Zone (HFZ) for aerobic fitness or muscular endurance were 2.5-3 times more likely to pass their math or reading exams. Girls in the HFZ for aerobic fitness were approximately 2-4 times as likely to meet or exceed reading and math test standards. CONCLUSIONS: Aerobic capacity and muscular endurance seem to positively affect academic achievement in middle school students.