Revealing underlying factors of absenteeism: A machine learning approach.

Introduction: The basis of support is understanding. In machine learning, understanding happens through assimilated knowledge and is centered on six pillars: big data, data volume, value, variety, velocity, and veracity. This study analyzes school attendance problems (SAP), which encompasses its legal statutes, school codes, students' attendance behaviors, and interventions in a school environment. The support pillars include attention to the physical classroom, school climate, and personal underlying factors impeding engagement, from which socio-emotional factors are often the primary drivers. Methods: This study asked the following research question: What can we learn about specific underlying factors of absenteeism using machine learning approaches? Data were retrieved from one school system available through the proprietary Building Dreams (BD) platform, owned by the Fight for Life Foundation (FFLF), whose mission is to support youth in underserved communities. The BD platform, licensed to K-12 schools, collects student-level data reported by educators on core values associated with in-class participation (a reported-negative or positive-behavior relative to the core values) based on Social-Emotional Learning (SEL) principles. We used a multi-phased approach leveraging several machine learning techniques (clustering, qualitative analysis, classification, and refinement of supervised and unsupervised learning). Unsupervised technique was employed to explore strong boundaries separating students using unlabeled data. Results: From over 20,000 recorded behaviors, we were able to train a classifier with 90.2% accuracy and uncovered a major underlying factor directly affecting absenteeism: the importance of peer relationships. This is an important finding and provides data-driven support for the fundamental idea that peer relationships are a critical factor affecting absenteeism. Discussion: The reported results provide a clear evidence that implementing socio-emotional learning components within a curriculum can improve absenteeism by targeting a root cause. Such knowledge can drive impactful policy and programming changes necessary for supporting the youth in communities overwhelmed with adversities.

Therapeutic closure of bronchopleural fistulas using ethanol.

Bronchopleural fistula (BPF) leading to persistent air leak (PAL), be it a complication of pulmonary resection, radiation, or direct tumor mass effect, is associated with high morbidity, impaired quality of life, and an increased risk of death. Incidence of BPF following pneumonectomy ranges between 4.4% and 20% with mortality ranging from 27.2% to 71%. Following lobectomy, incidence ranges from 0.5% to 1.5% in reported series. BPFs are more likely to occur following right-sided pneumonectomy, while patients undergoing bi-lobectomy were more likely to suffer BPF than those undergoing single lobectomy. In addition to supportive care, including appropriate antibiotics and nutrition, management of BPF includes pleural decontamination, BPF closure, and ultimately obliteration of the pleural space. There are surgical and bronchoscopic approaches for the management of BPF. Surgical interventions are best suited for large BPFs, and those occurring in the early postoperative period. Bronchoscopic techniques may be used for smaller BPFs, or when an individual patient is no longer a surgical candidate. Published reports have described the use of polyethylene glycol, fibrin glues, autologous blood products, gel foam, silver nitrate, and stenting among other techniques. The Amplatzer device, used to close atrial septal defects has shown promise as a bronchoscopic therapy. Following their approval under the humanitarian device exemption program for treatment of prolonged air leaks, endobronchial valves have been used for BPF. No bronchoscopic technique is universally applicable, and treatment should be individualized. In this report, we describe two separate cases where we use an Olympus© 21-gauge EBUS-TBNA (endobronchial ultrasound-transbronchial needle aspiration) needle for directed submucosal injection of ethanol leading to closure of the BPF and subsequent successful resolution of PAL.

A Multistage Approach for Image Registration.

Successful image registration is an important step for object recognition, target detection, remote sensing, multimodal content fusion, scene blending, and disaster assessment and management. The geometric and photometric variations between images adversely affect the ability for an algorithm to estimate the transformation parameters that relate the two images. Local deformations, lighting conditions, object obstructions, and perspective differences all contribute to the challenges faced by traditional registration techniques. In this paper, a novel multistage registration approach is proposed that is resilient to view point differences, image content variations, and lighting conditions. Robust registration is realized through the utilization of a novel region descriptor which couples with the spatial and texture characteristics of invariant feature points. The proposed region descriptor is exploited in a multistage approach. A multistage process allows the utilization of the graph-based descriptor in many scenarios thus allowing the algorithm to be applied to a broader set of images. Each successive stage of the registration technique is evaluated through an effective similarity metric which determines subsequent action. The registration of aerial and street view images from pre- and post-disaster provide strong evidence that the proposed method estimates more accurate global transformation parameters than traditional feature-based methods. Experimental results show the robustness and accuracy of the proposed multistage image registration methodology.