Whom to Test? Active Sampling Strategies for Managing COVID-19

This paper presents methods to choose individuals to test for infection during a pandemic such as COVID-19, characterized by high contagion and presence of asymptomatic carriers. The smart-testing ideas presented here are motivated by active learning and multi-armed bandit techniques in machine learning. Our active sampling method works in conjunction with quarantine policies, can handle different objectives, is dynamic and adaptive in the sense that it continually adapts to changes in real-time data. The bandit algorithm uses contact tracing, location-based sampling and random sampling in order to select specific individuals to test. Using a data-driven agent-based model simulating New York City we show that the algorithm samples individuals to test in a manner that rapidly traces infected individuals. Experiments also suggest that smart-testing can significantly reduce the death rates as compared to current methods such as testing symptomatic individuals with or without contact tracing.

[1]  Tsuyoshi Murata,et al.  A multi-armed bandit approach for exploring partially observed networks , 2019, Applied Network Science.

[2]  Haoyang Sun,et al.  Interventions to mitigate early spread of SARS-CoV-2 in Singapore: a modelling study , 2020, The Lancet Infectious Diseases.

[3]  Nitesh V. Chawla,et al.  CoupledLP: Link Prediction in Coupled Networks , 2015, KDD.

[4]  N. Zheng,et al.  Global Optimization of Stochastic Black-Box Systems via Sequential Kriging Meta-Models , 2006, J. Glob. Optim..

[5]  David A. Cohn,et al.  Active Learning with Statistical Models , 1996, NIPS.

[6]  Danai Koutra,et al.  RolX: structural role extraction & mining in large graphs , 2012, KDD.

[7]  I. Cooper,et al.  A SIR model assumption for the spread of COVID-19 in different communities , 2020, Chaos, Solitons & Fractals.

[8]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[9]  Ellen Brooks-Pollock,et al.  Epidemic predictions in an imperfect world: modelling disease spread with partial data , 2015, Proceedings of the Royal Society B: Biological Sciences.

[10]  Tobi Saidel,et al.  Review of sampling hard-to-reach and hidden populations for HIV surveillance. , 2005, AIDS.

[11]  Zhiqiang Zheng,et al.  Selectively Acquiring Customer Information: A New Data Acquisition Problem and an Active Learning-Based Solution , 2006, Manag. Sci..

[12]  Lior Rokach,et al.  A framework for optimizing COVID-19 testing policy using a Multi Armed Bandit approach , 2020, ArXiv.

[13]  Lucie Abeler-Dörner,et al.  Quantifying SARS-CoV-2 transmission suggests epidemic control with digital contact tracing , 2020, Science.

[14]  Carl A. B. Pearson,et al.  The effect of control strategies to reduce social mixing on outcomes of the COVID-19 epidemic in Wuhan, China: a modelling study , 2020, The Lancet Public Health.

[15]  A. Atkeson,et al.  What Will Be the Economic Impact of Covid-19 in the Us? Rough Estimates of Disease Scenarios , 2020 .

[16]  J. P. D. Gardephe.  Jeannine Renee Lam v. New York City Department of Education , 2019 .

[17]  Mikhail Prokopenko,et al.  Modelling transmission and control of the COVID-19 pandemic in Australia , 2020, Nature Communications.

[18]  Petrônio C. L. Silva,et al.  COVID-ABS: An agent-based model of COVID-19 epidemic to simulate health and economic effects of social distancing interventions , 2020, Chaos, Solitons & Fractals.

[19]  Andreas Krause,et al.  Information Gathering in Networks via Active Exploration , 2015, IJCAI.

[20]  John Langford,et al.  The Epoch-Greedy Algorithm for Multi-armed Bandits with Side Information , 2007, NIPS.

[21]  David Buckeridge,et al.  Principles and Practice of Public Health Surveillance , 2015 .

[22]  M. Salathé,et al.  COVID-19 epidemic in Switzerland: on the importance of testing, contact tracing and isolation. , 2020, Swiss medical weekly.

[23]  P. Klepac,et al.  Feasibility of controlling COVID-19 outbreaks by isolation of cases and contacts , 2020, The Lancet Global Health.

[24]  Eduardo L. Brugnago,et al.  Strong correlations between power-law growth of COVID-19 in four continents and the inefficiency of soft quarantine strategies , 2020, Chaos.

[25]  M. Olfson,et al.  Facing the COVID-19 epidemic in NYC: a stochastic agent-based model of various intervention strategies , 2020, medRxiv.

[26]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[27]  C. Whittaker,et al.  Report 9: Impact of non-pharmaceutical interventions (NPIs) to reduce COVID19 mortality and healthcare demand , 2020 .

[28]  Ramon Huerta,et al.  Contact tracing and epidemics control in social networks. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[29]  Sébastien Bubeck,et al.  Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems , 2012, Found. Trends Mach. Learn..

[30]  Herbert W. Hethcote,et al.  The Mathematics of Infectious Diseases , 2000, SIAM Rev..

[31]  Wang-Chien Lee,et al.  HIN2Vec: Explore Meta-paths in Heterogeneous Information Networks for Representation Learning , 2017, CIKM.

[32]  X. Chen,et al.  Allocation of COVID-19 Vaccines Under Limited Supply , 2020, medRxiv.

[33]  Buse Eylul Oruc,et al.  The impact of social distancing on COVID19 spread: State of Georgia case study , 2020, medRxiv.

[34]  Radu Marculescu,et al.  Centralized and decentralized isolation strategies and their impact on the COVID-19 pandemic dynamics , 2020, ArXiv.

[35]  Buse Eylul Oruc,et al.  Evaluating scenarios for school reopening under COVID19 , 2020, BMC Public Health.

[36]  Stefan Spinler,et al.  Spatial Resource Allocation for Emerging Epidemics: A Comparison of Greedy, Myopic, and Dynamic Policies , 2018, Manuf. Serv. Oper. Manag..

[37]  Lihong Li,et al.  An Empirical Evaluation of Thompson Sampling , 2011, NIPS.

[38]  R. Musonda,et al.  Studying dynamics of the HIV epidemic: population‐based data compared with sentinel surveillance in Zambia , 1998, AIDS.

[39]  D. Ginsbourger,et al.  A benchmark of kriging-based infill criteria for noisy optimization , 2013, Structural and Multidisciplinary Optimization.

[40]  David H. Wolpert,et al.  Bandit problems and the exploration/exploitation tradeoff , 1998, IEEE Trans. Evol. Comput..

[41]  Nitesh V. Chawla,et al.  metapath2vec: Scalable Representation Learning for Heterogeneous Networks , 2017, KDD.

[42]  Warren B. Powell,et al.  A Knowledge-Gradient Policy for Sequential Information Collection , 2008, SIAM J. Control. Optim..

[43]  Matthew J. Salganik,et al.  Assessing respondent-driven sampling , 2010, Proceedings of the National Academy of Sciences.

[44]  Aurélien Garivier,et al.  The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond , 2011, COLT.

[45]  Liliana Perez,et al.  An agent-based approach for modeling dynamics of contagious disease spread , 2009, International journal of health geographics.

[46]  Matt J Keeling,et al.  Contact tracing and disease control , 2003, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[47]  Tina Eliassi-Rad,et al.  ε - WGX: Adaptive Edge Probing for Enhancing Incomplete Networks , 2017, WebSci.

[48]  W. R. Thompson.  ON THE LIKELIHOOD THAT ONE UNKNOWN PROBABILITY EXCEEDS ANOTHER IN VIEW OF THE EVIDENCE OF TWO SAMPLES , 1933 .

[49]  Zahy Bnaya.  Social Network Search as a Volatile Multi-armed Bandit Problem , 2013 .

[50]  Charu C. Aggarwal,et al.  Heterogeneous Network Embedding via Deep Architectures , 2015, KDD.

[51]  Jeff G. Schneider,et al.  Active Search and Bandits on Graphs using Sigma-Optimality , 2015, UAI.

[52]  C. Rayner,et al.  Contact tracing and population screening for tuberculosis - who should be assessed? , 2003, Journal of public health medicine.

[53]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.