Cooperative learning in virtual high school english language arts: An action research study

Cooperative learning (CL) has the potential to increase students' college and career readiness with benefits including higher student achievement, higher critical thinking, and greater psychological health (Johnson & Johnson, 1983, 1989;Kramarski & Mevarech, 2003;Natasi & Clements, 1991;Webb & Mastergeorge, 2003). This study explores student attitudes toward cooperative learning in two virtual high school English language arts (ELA) courses which occurred as a direct result of the COVID-19 pandemic. Employing action research methodology, the authors gained valuable insights about structuring cooperative learning in an online learning environment effectively. The study took place during the first eight weeks of two tenth grade ELA courses, one standard and one honors. Findings suggest many factors influence the implementation of effective cooperative learning within the virtual ELA classroom, including student attitudes and relationships, instructional time, class size, interdependence and group accountability, task completion, and modeling and practice. © 2023, IGI Global.

Enhance COVID-19 Mortality Prediction with Human Mobility Trend and Medical Information

In this work, we study national and state-level COVID-19 pandemic data in the United States with the help of human mobility trend data and auxiliary medical information. We analyze and compare various state-of-the-art time-series prediction techniques. We assess a spatio-temporal graph neural network model which forecasts the pandemic course by utilizing a hybrid deep learning architecture and human mobility data. Nodes in the graph represent the state-level deaths due to COVID-19 at any particular time point, edges represent the human mobility trend and temporal edges correspond to node attributes across time. We also study statistical modeling and machine learning techniques for mortality prediction in the United States. We evaluate these techniques on both state and national level COVID-19 data in the United States and claim that the SARIMAX and GCN-LSTM model generated forecast values using exogenous hospital information variables can enrich the underlying model to improve the prediction accuracy at both levels. Our best machine learning models perform 50% and 60% better than the baseline on an average on the national level and state-level data, respectively, while the statistical models perform 63% and 42% better. © 2021 IEEE.

Improving Neural Networks for Time-Series Forecasting using Data Augmentation and AutoML

Statistical methods such as the Box-Jenkins method for time-series forecasting have been prominent since their development in 1970. Many researchers rely on such models as they can be efficiently estimated and also provide interpretability. However, advances in machine learning research indicate that neural networks can be powerful data modeling techniques, as they can provide higher accuracy for a plethora of learning problems and datasets. In the past, they have been tried on time-series forecasting as well, but their overall results have not been significantly better than the statistical models especially for intermediate length times-series data. Their modeling capacities are limited in cases where enough data may not be available to estimate the large number of parameters that these non-linear models require. This paper presents an easy to implement data augmentation method to significantly improve the performance of such networks. Our method, Augmented-Neural-Network, which involves using forecasts from statistical models, can help unlock the power of neural networks on intermediate length time-series and produces competitive results. It shows that data augmentation, when paired with Automated Machine Learning techniques such as Neural Architecture Search, can help to find the best neural architecture for a given time-series. Using the combination of these, demonstrates significant enhancement in the forecasting accuracy of three neural network-based models for a COVID-19 dataset, with a maximum improvement in forecasting accuracy by 21.41%, 24.29%, and 16.42%, respectively, over the neural networks that do not use augmented data. © 2021 IEEE.

Radiation Oncology Virtual Education Rotation 2.0 for Residents: Preliminary Results

Purpose/Objective(s): Radiation Oncology Virtual Education Rotation (ROVER) is a virtual education platform developed to support radiation oncology education for medical students during COVID19 when away and in-person rotations were suspended. Due to the positive reception of ROVER, we created ROVER2.0 tailored to radiation oncology residents. Materials/Methods: ROVER2.0 comprises monthly case-based discussions on various topics with radiation oncology faculty from across the country and is tailored to radiation oncology residents. Sessions are 1 hour in duration and hosted over Zoom. Sessions were advertised on social media (Twitter) and on ARRO, ACRO, and ADROP mailing lists. Pre- and post-session surveys were used to explore resident perspectives on virtual education and assess the utility of virtual education as a modern learning platform. Results: Five ROVER2.0 sessions have been held, led by 17 faculty from 16 institutions (3-4 faculty per session) with a total of 868 registrants (R), 445 attendees (A), and 152 post-survey respondents (P): gastrointestinal (R = 186, A = 103, P = 50), genitourinary (R = 159, A = 83, P = 29), central nervous system (R = 140, A = 58, P = 19), pediatrics (R = 177, A = 94, P = 27), and head and neck (R = 206, A = 107, P = 27). 43.5% of registrants were female, 6.1% were PGY-1, 37.3% were PGY-2/3, and 45% were PGY-4-5. Of all registrants, 82% signed up for ROVER2.0 for the "opportunity to hear from a diverse expert panel." At baseline, 73.5% reported that their home programs conducted mock oral exams and programs were reported to have a median of 5 hours/week of dedicated didactics. A third or fewer reported that COVID-19 negatively impacted residency didactics (22.8%), faculty engagement in teaching (30.8%), or access to faculty (33.9%). 24.2%, 37.3%, and 38.5% of respondents felt that virtual platforms are superior, equal, or inferior to in-person learning, respectively. 98.0% considered the sessions very valuable or valuable and that it was very easy or easy (94.1%) to learn through the virtual format. 83.6% strongly agreed or agreed that they felt more confident treating the disease site cancer as a result of the session. 84.2% reported that they had no difficulty attending sessions due to clinical responsibilities. Conclusion: ROVER2.0 case-based sessions can augment radiation oncology residency didactics by providing exposure to different practices across the country as an adjunct to in-person learning. Most respondents felt that COVID-19 did not negatively impact educational quality, and a rapid transition to virtual platforms likely served as an important buffer. ROVER2.0 was met with enthusiasm and considered an effective teaching tool by radiation oncology resident participants. This virtual and open-access resource can facilitate accessible and equitable education to those negatively impacted by in-person learning restrictions and allow broader dissemination of information about radiation oncology.

Emergency Department Adaptations to COVID-19

BACKGROUND: The COVID-19 pandemic creates unique challenges for healthcare systems. While mass casualty protocols and plans exist for trauma-induced large-scale resource utilization events, contagious infectious disease mass casualty events do not have such rigorous procedures established. COVID-19 forces Emergency Departments (EDs) to simultaneously treat seriously ill patients and evaluate large influxes of 'worried well'-while maintaining both staff and patient safety. METHODS: The objectives of this project are to create an avenue to evaluate large surges of patients while minimizing hospital-acquired infections. After identifying areas for improvement and anticipating potential failures, we devised eight healthcare delivery innovations to address those areas and meet our objectives: (1) Parallel ED Lanes (2) Universal Respiratory Precautions (3) Respiratory Drive Through (RDT) (4) Medical Company (5) Provider Triage (6) ED Quarterback Patient Liaison (EDQB) (7) Virtual Registration (8) Virtual Ward. RESULTS: To date, no staff members have contracted COVID-19 within the ED footprint. Our RDT has seen 16,994 patients and the medical company 1,109. Provider triage has redirected 465 patients, while our EDQB has interacted with 532 and redirected 93 patients for same-day appointments with their Primary Care Manager (PCM). CONCLUSION: The system of care establish at our Military Treatment Facility (MTF) has been effective in maximizing staff and patient safety, while providing a new patient-centered healthcare delivery apparatus.