Search

Abstract Background Automated segmentation of coronary arteries is a crucial step for computer-aided coronary artery disease (CAD) diagnosis and treatment planning. Correct delineation of the coronary artery is challenging in X-ray coronary angiography (XCA) due to the low signal-to-noise ratio and confounding background structures. Methods A novel ensemble framework for coronary artery segmentation in XCA images is proposed, which utilizes deep learning and filter-based features to construct models using the gradient boosting decision tree (GBDT) and deep forest classifiers. The proposed method was trained and tested on 130 XCA images. For each pixel of interest in the XCA images, a 37-dimensional feature vector was constructed based on (1) the statistics of multi-scale filtering responses in the morphological, spatial, and frequency domains; and (2) the feature maps obtained from trained deep neural networks. The performance of these models was compared with those of common deep neural networks on metrics including precision, sensitivity, specificity, F1 score, AUROC (the area under the receiver operating characteristic curve), and IoU (intersection over union). Results With hybrid under-sampling methods, the best performing GBDT model achieved a mean F1 score of 0.874, AUROC of 0.947, sensitivity of 0.902, and specificity of 0.992; while the best performing deep forest model obtained a mean F1 score of 0.867, AUROC of 0.95, sensitivity of 0.867, and specificity of 0.993. Compared with the evaluated deep neural networks, both models had better or comparable performance for all evaluated metrics with lower standard deviations over the test images. Conclusions The proposed feature-based ensemble method outperformed common deep convolutional neural networks in most performance metrics while yielding more consistent results. Such a method can be used to facilitate the assessment of stenosis and improve the quality of care in patients with CAD.

BackgroundBlack people are disproportionally impacted by hypertension. New approaches for encouraging healthy lifestyles are needed to reduce hypertension and promote health equity in Black communities. ObjectiveIn this report, we describe the early-stage, virtual design of a just-in-time adaptive intervention (JITAI) to increase physical activity in partnership with members of a low-income, predominantly Black community. MethodsThe hallmark of JITAIs is highly contextualized mobile app push notifications. Thus, understanding participants' context and determinants of physical activity are critical. During the height of the COVID-19 pandemic, we conducted virtual discovery interviews and analysis guided by the Behavior Change Wheel (which focuses on participants' capacity, opportunity, and motivation to engage in physical activity), as well as empathy mapping. We then formed a community-academic participatory design team that partnered in the design sprint, storyboarding, and paper prototyping. ResultsFor this study, 5 community members participated in the discovery interviews, 12 stakeholders participated in the empathy mapping, 3 community members represented the community on the design team, and 10 community members provided storyboard or paper prototyping feedback. Only one community member had used videoconferencing prior to partnering with the academic team, and none had design experience. A set of 5 community-academic partner design principles were created: (1) keep users front and center, (2) tailor to the individual, (3) draw on existing motivation, (4) make physical activity feel approachable, and (5) make data collection transparent yet unobtrusive. To address community-specific barriers, the community-academic design team decided that mobile app push notifications will be tailored to participants’ baseline mobility level and community resources (eg, local parks and events). Push notifications will also be tailored based on the day (weekday versus weekend), time of day, and weather. Motivation will be enhanced via adaptive goal setting with supportive feedback and social support via community-generated notifications. ConclusionsWe completed early-stage virtual design of a JITAI in partnership with community participants and a community design team with limited design and videoconferencing experience. We found that designing JITAIs with the community enables these interventions to address community-specific needs, which may lead to a more meaningful impact on users' health.

ObjectiveData on patterns and correlates of opioid and benzodiazepines prescriptions among patients with chronic conditions are limited. Given a diminished capacity for hepatic clearance, patients with cirrhosis represent a high risk group for use. The aim of this study was to characterise the patterns and correlates of prescription opioid, benzodiazepine and dual drug prescriptions among individuals with common chronic diseases.DesignAnalysis of Truven Marketscan database to evaluate individuals with drug coverage with cirrhosis (n=169,181), chronic hepatitis C without cirrhosis (n=210 191), congestive heart failure (n=766 840) or chronic obstructive pulmonary disease (n=1 438 798). Pharmacy files were examined for outpatient prescriptions.ResultsPatients with cirrhosis had a significantly higher prevalence of opioid prescriptions (37.1 per 100 person-years vs 24.3–26.0, p≤0.001) and benzodiazepine prescriptions (21.3 per 100 person-years vs 12.1–12.9, p90 daily oral morphine equivalents) (29.1% vs 14.4%, p

The health care burden of ST elevation myocardial infarction (STEMI) in India is enormous. Yet, many patients with STEMI can seldom avail timely and evidence based reperfusion treatments. This gap in care is a result of financial barriers, limited healthcare infrastructure, poor knowledge and accessibility of acute medical services for a majority of the population. Addressing some of these issues, STEMI India, a not-for-profit organization, Cardiological Society of India (CSI) and Association Physicians of India (API) have developed a protocol of “systems of care” for efficient management of STEMI, with integrated networks of facilities. Leveraging newly-developed ambulance and emergency medical services, incorporating recent state insurance schemes for vulnerable populations to broaden access, and combining innovative, “state-of-the-art” information technology platforms with existing hospital infrastructure, are the crucial aspects of this system. A pilot program was successfully employed in the state of Tamilnadu. The purpose of this article is to describe the framework and methods associated with this programme with an aim to improve delivery of reperfusion therapy for STEMI in India. This programme can serve as model STEMI systems of care for other low-and-middle income countries.