ABSTRACT
Global monitoring of novel diseases and outbreaks is crucial for pandemic prevention. To this end, movement data from cell-phones is already used to augment epidemiological models. Recent work has posed individual cell-phone metadata as a universal data source for syndromic surveillance for two key reasons: (1) these records are already collected for billing purposes in virtually every country and (2) they could allow deviations from people's routine behaviors during symptomatic illness to be detected, both in terms of mobility and social interactions. In this paper, we develop the necessary models to conduct population-level infectious disease surveillance by using cell-phone metadata individually linked with health outcomes. Specifically, we propose GraphDNA---a model that builds Graph neural networks (GNNs) into Dynamic Network Anomaly detection. Using cell-phone call records (CDR) linked with diagnostic information from Iceland during the H1N1v influenza outbreak, we show that GraphDNA outperforms state-of-the-art baselines on individual Date-of-Diagnosis (DoD) prediction, while tracking the epidemic signal in the overall population. Our results suggest that proper modeling of the universal CDR data could inform public health officials and bolster epidemic preparedness measures.
Supplemental Material
- Subutai Ahmad and Scott Purdy. 2016. Real-time anomaly detection for streaming analytics. arXiv preprint arXiv:1607.02480 (2016).Google Scholar
- Mohiuddin Ahmed, Abdun Naser Mahmood, and Jiankun Hu. 2016. A survey of network anomaly detection techniques. Journal of Network and Computer Applications, Vol. 60 (2016), 19--31.Google ScholarDigital Library
- Leman Akoglu, Mary McGlohon, and Christos Faloutsos. 2010. Oddball: Spotting anomalies in weighted graphs. In PAKDD.Google Scholar
- Samuel Altmann, Luke Milsom, Hannah Zillessen, Raffaele Blasone, Frederic Gerdon, Ruben Bach, Frauke Kreuter, Daniele Nosenzo, Séverine Toussaert, Johannes Abeler, et al. 2020. Acceptability of app-based contact tracing for COVID-19: Cross-country survey study. JMIR mHealth and uHealth, Vol. 8, 8 (2020), e19857.Google Scholar
- Khaled Ammar. 2016. Techniques and systems for large dynamic graphs. In SIGMOD.Google Scholar
- Linus Bengtsson, Jean Gaudart, Xin Lu, Sandra Moore, Erik Wetter, Kankoe Sallah, Stanislas Rebaudet, and Renaud Piarroux. 2015. Using mobile phone data to predict the spatial spread of cholera. Sci. Rep., Vol. 5 (2015), 8923.Google ScholarCross Ref
- Nita Bharti. 2021. Linking human behaviors and infectious diseases. PNAS, Vol. 118, 11 (2021).Google ScholarCross Ref
- Caroline O Buckee, Amy Wesolowski, Nathan N Eagle, Elsa Hansen, and Robert W Snow. 2013. Mobile phones and malaria: modeling human and parasite travel. Travel Med Infect Dis, Vol. 11, 1 (2013), 15--22.Google ScholarCross Ref
- Edenilson E Calore, David E Uip, and Nilda M Perez. 2011. Pathology of the swine-origin influenza A (H1N1) flu. JPRP, Vol. 207, 2 (2011), 86--90.Google Scholar
- Varun Chandola, Arindam Banerjee, and Vipin Kumar. 2009. Anomaly detection: A survey. ACM computing surveys (CSUR), Vol. 41, 3 (2009), 1--58.Google ScholarDigital Library
- Varun Chandola, Arindam Banerjee, and Vipin Kumar. 2010. Anomaly detection for discrete sequences: A survey. TKDE, Vol. 24, 5 (2010), 823--839.Google ScholarDigital Library
- Serina Chang, Emma Pierson, Pang Wei Koh, Jaline Gerardin, Beth Redbird, David Grusky, and Jure Leskovec. 2021. Mobility network models of COVID-19 explain inequities and inform reopening. Nature, Vol. 589, 7840 (2021), 82--87.Google Scholar
- Jinyin Chen, Xuanheng Xu, Yangyang Wu, and Haibin Zheng. 2018. Gc-lstm: Graph convolution embedded lstm for dynamic link prediction. arXiv preprint arXiv:1812.04206 (2018).Google Scholar
- Forrest W Crawford, Sydney A Jones, Matthew Cartter, et almbox. 2022. Impact of close interpersonal contact on COVID-19 incidence: Evidence from 1 year of mobile device data. Science advances, Vol. 8, 1 (2022).Google Scholar
- Laxman Dhulipala, Guy E Blelloch, and Julian Shun. 2019. Low-latency graph streaming using compressed purely-functional trees. In PLDI.Google Scholar
- Tolga Ergen and Suleyman Serdar Kozat. 2019. Unsupervised anomaly detection with LSTM neural networks. TNNLS, Vol. 31, 8 (2019), 3127--3141.Google ScholarCross Ref
- Susan L. Erikson. 2018. Cell Phones ≠ Self and Other Problems with Big Data Detection and Containment during Epidemics. MAQ, Vol. 32, 3 (2018), 315--339.Google ScholarCross Ref
- Guoyao Feng, Xiao Meng, and Khaled Ammar. 2015. Distinger: A distributed graph data structure for massive dynamic graph processing. In IEEE BigData.Google Scholar
- Jeremy Ginsberg, Matthew H Mohebbi, Rajan S Patel, Lynnette Brammer, Mark S Smolinski, and Larry Brilliant. 2009. Detecting influenza epidemics using search engine query data. Nature, Vol. 457, 7232 (2009), 1012--1014.Google Scholar
- David M. Halbfinger, Isabel Kershner, and Ronen Bergman. 2020. To Track Coronavirus, Israel Moves to Tap Secret Trove of Cellphone Data. The New York Times (16 March 2020). Issue 2020-03-16.Google Scholar
- William L Hamilton, Rex Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In NeurIPS.Google Scholar
- Kelly J Henning. 2004. What is syndromic surveillance? MMWR (2004), 7--11.Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735--1780.Google Scholar
- David W Hosmer Jr, Stanley Lemeshow, and Rodney X Sturdivant. 2013. Applied logistic regression. Vol. 398.Google ScholarCross Ref
- Wenjie Hu, Yang Yang, Ziqiang Cheng, Carl Yang, and Xiang Ren. 2021. Time-Series Event Prediction with Evolutionary State Graph. In WSDM.Google Scholar
- International Telecommunication Union. 2020. Measuring digital development: Facts and figures 2020.Google Scholar
- George K Karagiannidis and Athanasios S Lioumpas. 2007. An improved approximation for the Gaussian Q-function. IEEE COMML, Vol. 11, 8 (2007), 644--646.Google Scholar
- Thomas N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In ICLR.Google Scholar
- Nishant Kishore, Mathew V Kiang, Kenth Engø-Monsen, Navin Vembar, Andrew Schroeder, Satchit Balsari, and Caroline O Buckee. 2020. Measuring mobility to monitor travel and physical distancing interventions: a common framework for mobile phone data analysis. The Lancet Digital Health (2020).Google Scholar
- Andrew M Kramer, J Tomlin Pulliam, Laura W Alexander, Andrew W Park, Pejman Rohani, and John M Drake. 2016. Spatial spread of the West Africa Ebola epidemic. Royal Society Open Science, Vol. 3, 8 (2016), 160294.Google ScholarCross Ref
- David Lazer, Ryan Kennedy, Gary King, and Alessandro Vespignani. 2014. The parable of Google Flu: traps in big data analysis. Science, Vol. 343, 6176 (2014), 1203--1205.Google Scholar
- Xiaoxiao Ma, Jia Wu, Shan Xue, Jian Yang, Quan Z Sheng, and Hui Xiong. 2021. A Comprehensive Survey on Graph Anomaly Detection with Deep Learning. arXiv preprint arXiv:2106.07178 (2021).Google Scholar
- Pankaj Malhotra, Lovekesh Vig, Gautam Shroff, and Puneet Agarwal. 2015. Long short term memory networks for anomaly detection in time series. In ESANN.Google Scholar
- Emmanuel Müller, Patricia Iglesias Sánchez, Yvonne Mülle, and Klemens Böhm. 2013. Ranking outlier nodes in subspaces of attributed graphs. In ICDEW.Google Scholar
- Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, Tao Schardl, and Charles Leiserson. 2020. Evolvegcn: Evolving graph convolutional networks for dynamic graphs. In AAAI.Google Scholar
- Adam Sadilek, Stephanie Caty, Lauren DiPrete, Raed Mansour, Tom Schenk, Mark Bergtholdt, Ashish Jha, Prem Ramaswami, and Evgeniy Gabrilovich. 2018. Machine-learned epidemiology: real-time detection of foodborne illness at scale. NPJ digital medicine, Vol. 1, 1 (2018), 1--7.Google Scholar
- Hacs im Sak, Andrew Senior, and Francc oise Beaufays. 2014. Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling. In INTERSPEECH.Google Scholar
- Loukas Samaras, Elena García-Barriocanal, and Miguel-Angel Sicilia. 2020. Syndromic surveillance using web data: a systematic review. J Innov Health Inform (2020), 39--77.Google Scholar
- Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2008. The graph neural network model. TNNLS, Vol. 20, 1 (2008), 61--80.Google Scholar
- Tamar Sharon. 2020. Blind-sided by privacy? Digital contact tracing, the Apple/Google API and big tech's newfound role as global health policy makers. Ethics and Information Technology (2020), 1--13.Google Scholar
- G Sigmundsdottir, T Gudnason, Ö Ólafsson, GE Baldvinsdottir, A Atladottir, A Löve, L Danon, and H Briem. 2010. Surveillance of influenza in Iceland during the 2009 pandemic. Euro Surveill., Vol. 15, 49 (2010), 19742.Google ScholarCross Ref
- Charles Spearman. 1987. The proof and measurement of association between two things. Am. J. Psychol., Vol. 100, 3/4 (1987), 441--471.Google ScholarCross Ref
- Xian Teng, Yu-Ru Lin, and Xidao Wen. 2017. Anomaly detection in dynamic networks using multi-view time-series hypersphere learning. In CIKM.Google Scholar
- Michele Tizzoni, Paolo Bajardi, Adeline Decuyper, Guillaume Kon Kam King, Christian M Schneider, Vincent Blondel, Zbigniew Smoreda, Marta C González, and Vittoria Colizza. 2014. On the use of human mobility proxies for modeling epidemics. PLoS Comput Biol, Vol. 10, 7 (2014), e1003716.Google ScholarCross Ref
- Ymir Vigfusson, Thorgeir A Karlsson, Derek Onken, Congzheng Song, Atli F Einarsson, Nishant Kishore, Rebecca M Mitchell, Ellen Brooks-Pollock, Gudrun Sigmundsdottir, et al. 2021. Cell-phone traces reveal infection-associated behavioral change. PNAS, Vol. 118, 6 (2021).Google ScholarCross Ref
- Dashun Wang, Dino Pedreschi, Chaoming Song, Fosca Giannotti, and Albert-Laszlo Barabasi. 2011. Human mobility, social ties, and link prediction. In KDD.Google Scholar
- Xuhong Wang, Baihong Jin, Ying Du, Ping Cui, Yingshui Tan, and Yupu Yang. 2021. One-class graph neural networks for anomaly detection in attributed networks. Neural. Comput. Appl. (2021), 1--13.Google Scholar
- Amy Wesolowski, Nathan Eagle, Andrew J Tatem, David L Smith, Abdisalan M Noor, Robert W Snow, and Caroline O Buckee. 2012. Quantifying the impact of human mobility on malaria. Science, Vol. 338, 6104 (2012), 267--270.Google ScholarCross Ref
- Amy Wesolowski, Taimur Qureshi, Maciej F Boni, Pål Roe Sundsøy, Michael A Johansson, Syed Basit Rasheed, Kenth Engø-Monsen, and Caroline O Buckee. 2015. Impact of human mobility on the emergence of dengue epidemics in Pakistan. PNAS, Vol. 112, 38 (2015), 11887--11892.Google ScholarCross Ref
- Yuanzhen Xie, Zijing Ou, Liang Chen, Yang Liu, Kun Xu, Carl Yang, and Zibin Zheng. 2021. Learning and Updating Node Embedding on Dynamic Heterogeneous Information Network. In WSDM.Google Scholar
- Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, and Kannan Achan. 2020. Inductive representation learning on temporal graphs. arXiv preprint arXiv:2002.07962 (2020).Google Scholar
- Takahiro Yabe, Nicholas KW Jones, P Suresh C Rao, Marta C Gonzalez, and Satish V Ukkusuri. 2022. Mobile phone location data for disasters: A review from natural hazards and epidemics. Computers, Environment and Urban Systems, Vol. 94 (2022), 101777.Google ScholarCross Ref
- Wenchao Yu, Wei Cheng, Charu C Aggarwal, Kai Zhang, Haifeng Chen, and Wei Wang. 2018. Netwalk: A flexible deep embedding approach for anomaly detection in dynamic networks. In KDD.Google ScholarDigital Library
- Li Zheng, Zhenpeng Li, Jian Li, Zhao Li, and Jun Gao. 2019 a. AddGraph: Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN.. In IJCAI.Google Scholar
- Panpan Zheng, Shuhan Yuan, Xintao Wu, Jun Li, and Aidong Lu. 2019 b. One-class adversarial nets for fraud detection. In AAAI, Vol. 33. 1286--1293.Google ScholarDigital Library
Index Terms
- Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance
Recommendations
Disease surveillance using online news: Dengue and zika in tropical countries
Graphical abstractDisplay Omitted
Highlights- News reports are verified to provide near real-time indications of outbreaks.
- ...
Abstract BackgroundAround the world in tropical areas, certain vector-borne diseases have become endemic and hyperendemic. Among the developing nations, there are common difficulties in establishing the incidences of various ...
AI for Global Disease Surveillance
In this time of increasing concern over the deadly and costly threats of infectious diseases, preparation for, early detection of, and timely response to emerging infectious diseases and epidemic outbreaks are key public-health priorities and are ...
Visualization and analytics tools for infectious disease epidemiology
Graphical abstractDisplay Omitted Visualization tools for infectious disease epidemiology are diverse.Complex geospatial, molecular, and social data require novel visualization tools.We reviewed visualization tools throughout development and adoption ...
Comments