Real-time monitoring of COVID-19 dynamics using automated trend fitting and anomaly detection

Abstract

As several countries gradually release social distancing measures, rapid detection of new localised COVID-19 hotspots and subsequent intervention will be key to avoiding large-scale resurgence of transmission. We introduce ASMODEE (Automatic Selection of Models and Outlier Detection for Epidemics), a new tool for detecting sudden changes in COVID-19 incidence. Our approach relies on automatically selecting the best (fitting or predicting) model from a range of user-defined time series models, excluding the most recent data points, to characterise the main trend in an incidence. We then derive prediction intervals and classify data points outside this interval as outliers, which provides an objective criterion for identifying departures from previous trends. We also provide a method for selecting the optimal breakpoints, used to define how many recent data points are to be excluded from the trend fitting procedure. The analysis of simulated COVID-19 outbreaks suggest ASMODEE compares favourably with a state-of-art outbreak-detection algorithm while being simpler and more flexible. We illustrate our method using publicly available data of NHS Pathways reporting potential COVID-19 cases in England at a fine spatial scale, for which we provide a template automated analysis pipeline. ASMODEE is implemented in the free R package trendbreaker.

Modelling that shaped the early COVID-19 pandemic response in the UK

“…The issue covers early models that were developed for the UK ( figure 4 ), often with limited data and initially relying on SARS-1-like parameters [ 15 ] and theoretical insights [ 31 ]. It includes models that are used in the ongoing overview of the epidemic with weekly consensus estimates of the Reproduction number [ 19 , 20 ], short term and medium-term projections [ 36 ] and real-time data stream monitoring [ 37 ] all playing a part. There are time-sensitive, changing policy questions, such as the impact of mass gatherings [ 38 ], reopening schools in May 2020 [ 39 – 41 ], the introduction of support bubbles [ 42 ] or the impact of contact tracing and lockdown [ 43 ].…”

Anomaly Detection in COVID-19 Time-Series Data

“…The existing anomaly detection techniques in COVID-19 data focus only on outbreak detection [5][6][7][8] in the COVID-19 tracking cases across the world. Karadayi et al [5] used a hybrid autoencoder network composed of a 3D convolutional neural network (CNN) and an autocorrelation based network for outbreak detection from spatio-temporal COVID-19 data provided by the Italian Department of Civil Protection.…”

“…Karadayi et al [5] used a hybrid autoencoder network composed of a 3D convolutional neural network (CNN) and an autocorrelation based network for outbreak detection from spatio-temporal COVID-19 data provided by the Italian Department of Civil Protection. Jombart et al [6] used linear regression, generalised linear models (GLMs), and Bayesian regression to detect sudden changes in potential COVID-19 cases in England. However, there has been no focus on quality assurance of COVID-19 data used for various analysis.…”

“…Existing anomaly detection techniques for COVID-19 data (some based on machine learning) focus only on outbreak detection [5][6][7][8] in the COVID-19 tracking cases across the world. Machine learning approaches [9][10][11] have also been used for data quality assurance in other domains.…”

Tracking the emergence of disparities in the subnational spread of COVID-19 in Brazil using an online application for real-time data visualisation: a longitudinal analysis

“…The field of real-time analysis of infectious disease data is rapidly expanding, in part due to greater automation, digitisation and online sharing of data (8). Projects such as the Johns Hopkins University Covid-19 Dashboard (9) aim to provide a global overview of cases and deaths with the goal of making international comparisons (10) and a number of sub-national-level real-time data dashboards have also been established for finer scale domestic comparisons such as that for Italy (11).…”