Th e COVID-19 pandemic has brought about a precipitous transformation in health care delivery in the nation's safety-net, primary care system of federally qualifi ed health centers (FQHCs). Th is study uses electronic health record data to quantify the extent of changes to visit volume in 36 FQHCs across 19 states as well as changes in quality metrics. We found a steep decline in in-person visits in March 2020 accompanied by a sharp increase in telehealth visits; however, combined volume remained 23% below pre-pandemic levels. Th e implications for public health are signifi cant, as preventive and chronic care deferral could lead to exacerbations of health disparities. Our examination of the impact on quality measures suggests that gaps in care are already emerging. Services that cannot be readily performed virtually are most aff ected. As FQHC visit numbers recover, concerted eff orts are needed to encourage access and re-engage at-risk groups that fell out of care.

Given a stream of entries in a multi-aspect data setting i.e., entries having multiple dimensions, how can we detect anomalous activities in an unsupervised manner? For example, in the intrusion detection setting, existing work seeks to detect anomalous events or edges in dynamic graph streams, but this does not allow us to take into account additional attributes of each entry. Our work aims to define a streaming multi-aspect data anomaly detection framework, termed MStream which can detect unusual group anomalies as they occur, in a dynamic manner. MStream has the following properties: (a) it detects anomalies in multi-aspect data including both categorical and numeric attributes; (b) it is online, thus processing each record in constant time and constant memory; (c) it can capture the correlation between multiple aspects of the data. MStream is evaluated over the KDDCUP99, CICIDS-DoS, UNSW-NB 15 and CICIDS-DDoS datasets, and outperforms state-of-the-art baselines.

Mitigating the risk arising from extreme events is a fundamental goal with many applications, such as the modelling of natural disasters, financial crashes, epidemics, and many others. To manage this risk, a vital step is to be able to understand or generate a wide range of extreme scenarios. Existing approaches based on Generative Adversarial Networks (GANs) excel at generating realistic samples, but seek to generate typical samples, rather than extreme samples. Hence, in this work, we propose ExGAN, a GAN-based approach to generate realistic and extreme samples. To model the extremes of the training distribution in a principled way, our work draws from Extreme Value Theory (EVT), a probabilistic approach for modelling the extreme tails of distributions. For practical utility, our framework allows the user to specify both the desired extremeness measure, as well as the desired extremeness probability they wish to sample at. Experiments on real US Precipitation data show that our method generates realistic samples, based on visual inspection and quantitative measures, in an efficient manner. Moreover, generating increasingly extreme examples using ExGAN can be done in constant time (with respect to the extremeness probability τ), as opposed to the O(1/τ) time required by the baseline approach.

No abstract

No abstract