Abstract:The Coronavirus disease 2019 (COVID-19) global pandemic has transformed almost every facet of human society throughout the world. Against an emerging, highly transmissible disease, governments worldwide have implemented non-pharmaceutical interventions (NPIs) to slow the spread of the virus. Examples of such interventions include community actions, such as school closures or restrictions on mass gatherings, individual actions including mask wearing and self-quarantine, and environmental actions such as cleanin… Show more
“…Governments implemented a wide variety of nonpharmaceutical interventions (NPIs) aimed at controlling the disease spread and enforcing social isolation. Confinement and school closure as well as entertainment and cultural sector closure were the predominant NPIs taken by governments in 2020 1 . Accordingly, many radiology departments decreased the number of elective imaging examinations to minimize the spread of infection and free up much needed medical resources and staff 2–4 .…”
"No-shows", defined as missed appointments or late cancellations, is a central problem in healthcare systems. It has appeared to intensify during the COVID-19 pandemic and the nonpharmaceutical interventions, such as closures, taken to slow its spread. No-shows interfere with patients' continuous care, lead to inefficient utilization of medical resources, and increase healthcare costs. We present a comprehensive analysis of no-shows for breast imaging appointments made during 2020 in a large medical network in Israel. We applied advanced machine learning methods to provide insights into novel and known predictors. Additionally, we employed causal inference methodology to infer the effect of closures on no-shows, after accounting for confounding biases, and demonstrate the superiority of adversarial balancing over inverse probability weighting in correcting these biases. Our results imply that a patient's perceived risk of cancer and the COVID-19 time-based factors are major predictors. Further, we reveal that closures impact patients over 60, but not patients undergoing advanced diagnostic examinations.
“…Governments implemented a wide variety of nonpharmaceutical interventions (NPIs) aimed at controlling the disease spread and enforcing social isolation. Confinement and school closure as well as entertainment and cultural sector closure were the predominant NPIs taken by governments in 2020 1 . Accordingly, many radiology departments decreased the number of elective imaging examinations to minimize the spread of infection and free up much needed medical resources and staff 2–4 .…”
"No-shows", defined as missed appointments or late cancellations, is a central problem in healthcare systems. It has appeared to intensify during the COVID-19 pandemic and the nonpharmaceutical interventions, such as closures, taken to slow its spread. No-shows interfere with patients' continuous care, lead to inefficient utilization of medical resources, and increase healthcare costs. We present a comprehensive analysis of no-shows for breast imaging appointments made during 2020 in a large medical network in Israel. We applied advanced machine learning methods to provide insights into novel and known predictors. Additionally, we employed causal inference methodology to infer the effect of closures on no-shows, after accounting for confounding biases, and demonstrate the superiority of adversarial balancing over inverse probability weighting in correcting these biases. Our results imply that a patient's perceived risk of cancer and the COVID-19 time-based factors are major predictors. Further, we reveal that closures impact patients over 60, but not patients undergoing advanced diagnostic examinations.
“…Second, this study is conducted using two data sets consisting of COVID-19-related news reports. We intend to study the generalizability of EpiTopics by exploring other sources of data which may cover a broader range of countries, NPIs, tasks and documents [5,16]. For instance, the proposed method could be integrated into existing automated surveillance systems such as Global Public Health Intelligence Network (GPHIN) [17], which monitors general media news potentially related to public health, instead of being applied exclusively to COVID-19-related news.…”
Section: Discussionmentioning
confidence: 99%
“…Our proposed approach is novel both in terms of the public health focus and the machine learning methods. Other researchers have applied supervised learning to online media [3] and Wikipedia articles [5] to identify COVID-19 NPI, but the 'black box' nature of the models has made it difficult to interpret results and model parameters. Our approach also has less demand for labelled data as it exploits large-scale unlabeled data via unsupervised learning and transfer learning.…”
The COVID-19 global pandemic has highlighted the importance of non-pharmacological interventions (NPI) for controlling epidemics of emerging infectious diseases. Despite the importance of NPI, their implementation has been monitored in an ad hoc and uncoordinated manner, mainly through the manual efforts of volunteers. Given the absence of systematic NPI tracking, authorities and researchers are limited in their ability to quantify the effectiveness of NPI and guide decisions regarding their use during the progression of a global pandemic. To address this issue, we propose 3-stage machine learning framework called EpiTopics to facilitate the surveillance of NPI by mining the vast amount of unlabelled news reports about these interventions. Building on topic modeling, our method characterizes online government reports and media articles related to COVID-19 as a mixture of latent topics.Our key contribution is the use of transfer-learning to address the limited number of NPIlabelled documents and topic modelling to support interpretation of the results. At stage 1, we trained a modified version of the unsupervised dynamic embedded topic model (DETM) on 1.2 million international news reports related to COVID-19. At stage 2, we used the trained DETM to infer topic mixture from a small set of 2000 NPI-labelled WHO documents as the input features for predicting NPI labels on each document. At stage 3, we supply the inferred country-level temporal topics from the DETM to the pretrained document-level NPI classifier to predict country-level NPIs. We identified 25 interpretable topics, over 4 distinct and coherent COVID-related themes. These topics contributed to significant improvements in predicting the NPIs labelled in the WHO documents and in predicting country-level NPIs. Together, our work lay the machine learning methodological foundation for future research in global-scale surveillance of public health interventions.
“…Since the outbreak of the pandemic, a growing number of research projects have tried to capture the diverse ways that governments have implemented policies to slow the spread of COVID-19. Some of these projects focus on a single type of policy (UNDP and UN Women COVID-19 Global Gender Response Tracker 2021; Elgin, Basbug, and Yalaman 2020) or a particular region of the world (Naqvi 2021;Adolph et al 2021), whereas others aim at collecting data at world-wide scale across a range of indicators (COVID-19 Government Measures Dataset 2020; Porcher 2020; Grundy, Quinn, and Todowede 2021; Suryanarayanan et al 2021). Of this latter set, the datasets with the widest coverage and most detailed indicators include CoronaNet, OxCGRT, the Complexity Science Hub COVID-19 Control Strategies List (CCCSL) Desvars-Larrive et al 2020) and Health Intervention Tracking for COVID-19 (HIT-COVID) (Zheng et al 2020).…”
In this paper, we present new indices for government responses to COVID-19 within six policy areas crucial for understanding the drivers and effects of the pandemic: social distancing, schools, businesses, health monitoring, health resources and mask wearing. We create these measures from combining two of the most comprehensive COVID-19 datasets, the CoronaNet COVID-19 Government Response Event Dataset and the Oxford COVID-19 Government Response Tracker, using a Bayesian time-varying measurement model. Our daily indices track government responses for each of these policy areas from January 1st, 2020 to January 15th, 2021, for over 180 countries. By using a statistical model to generate these indices, we are able to estimate uncertainty within the index and provide external validation for these two COVID-19 policy datasets, showing that though they represent distinct data sources, they show strong convergent validity. We further explore the correlation between these indices and a range of social, public health, political and economic covariates. Our results show that while business restrictions and social distancing restrictions are strongly associated with reduced general anxiety, school restrictions are not. School restrictions are, however, associated with higher rates of personal contact with people outside the home, higher levels of income inequality and bureaucratic corruption. Additionally, we find that female heads of state are more likely to implement a broad array of pandemic-related restrictions than male leaders.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.