Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance

Carl Yang; Hongwen Song; Mingyue Tang; Leon Danon; Ymir Vigfusson

doi:10.1145/3534678.3542678

Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance

Carl Yang, Hongwen Song, Mingyue Tang, Leon Danon, Ymir Vigfusson^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

2 Citations (Scopus)

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.

Original language	English
Title of host publication	KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Publisher	Association for Computing Machinery (ACM)
Pages	4733-4742
Number of pages	10
ISBN (Electronic)	9781450393850
DOIs	https://doi.org/10.1145/3534678.3542678
Publication status	Published - 14 Aug 2022
Event	28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 - Washington, United States Duration: 14 Aug 2022 → 18 Aug 2022

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
ISSN (Print)	2154-817X

Conference

Conference	28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022
Country/Territory	United States
City	Washington
Period	14/08/22 → 18/08/22

Bibliographical note

Funding Information:
We thank the anonymous reviewers of our manuscript for constructive feedback, and past members and affiliates of Emory SimBioSys lab for early work on the problem. This research is partly supported by equipment and internal grants from Emory University, a hardware donation from NVIDIA Corporation, Icelandic Centre for Research Award 152620-051, UKRI (MRC and EPSRC) through grants MC/PC/19067, MR/V038613/1, EP/V051555/1, EP/N510129/1 and investigator-led grants from Pfizer.

Publisher Copyright:
© 2022 ACM.

Keywords

anomaly analysis
cell-phone call detail records
disease surveillance
graph neural networks
temporal networks

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3534678.3542678

Handle.net

Persistent link

Cite this

Yang, C., Song, H., Tang, M., Danon, L., & Vigfusson, Y. (2022). Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance. In KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 4733-4742). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). Association for Computing Machinery (ACM). https://doi.org/10.1145/3534678.3542678

Yang, Carl ; Song, Hongwen ; Tang, Mingyue et al. / Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance. KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM), 2022. pp. 4733-4742 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

@inproceedings{64643d97befc4f5bbcce64442bdc5561,

title = "Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance",

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.",

keywords = "anomaly analysis, cell-phone call detail records, disease surveillance, graph neural networks, temporal networks",

author = "Carl Yang and Hongwen Song and Mingyue Tang and Leon Danon and Ymir Vigfusson",

note = "Funding Information: We thank the anonymous reviewers of our manuscript for constructive feedback, and past members and affiliates of Emory SimBioSys lab for early work on the problem. This research is partly supported by equipment and internal grants from Emory University, a hardware donation from NVIDIA Corporation, Icelandic Centre for Research Award 152620-051, UKRI (MRC and EPSRC) through grants MC/PC/19067, MR/V038613/1, EP/V051555/1, EP/N510129/1 and investigator-led grants from Pfizer. Publisher Copyright: {\textcopyright} 2022 ACM.; 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 ; Conference date: 14-08-2022 Through 18-08-2022",

year = "2022",

month = aug,

day = "14",

doi = "10.1145/3534678.3542678",

language = "English",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

publisher = "Association for Computing Machinery (ACM)",

pages = "4733--4742",

booktitle = "KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining",

address = "United States",

}

Yang, C, Song, H, Tang, M, Danon, L & Vigfusson, Y 2022, Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance. in KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery (ACM), pp. 4733-4742, 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022, Washington, United States, 14/08/22. https://doi.org/10.1145/3534678.3542678

Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance. / Yang, Carl; Song, Hongwen; Tang, Mingyue et al.
KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM), 2022. p. 4733-4742 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance

AU - Yang, Carl

AU - Song, Hongwen

AU - Tang, Mingyue

AU - Danon, Leon

AU - Vigfusson, Ymir

N1 - Funding Information: We thank the anonymous reviewers of our manuscript for constructive feedback, and past members and affiliates of Emory SimBioSys lab for early work on the problem. This research is partly supported by equipment and internal grants from Emory University, a hardware donation from NVIDIA Corporation, Icelandic Centre for Research Award 152620-051, UKRI (MRC and EPSRC) through grants MC/PC/19067, MR/V038613/1, EP/V051555/1, EP/N510129/1 and investigator-led grants from Pfizer. Publisher Copyright: © 2022 ACM.

PY - 2022/8/14

Y1 - 2022/8/14

N2 - 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.

AB - 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.

KW - anomaly analysis

KW - cell-phone call detail records

KW - disease surveillance

KW - graph neural networks

KW - temporal networks

UR - http://www.scopus.com/inward/record.url?scp=85137148558&partnerID=8YFLogxK

U2 - 10.1145/3534678.3542678

DO - 10.1145/3534678.3542678

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:85137148558

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 4733

EP - 4742

BT - KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery (ACM)

T2 - 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022

Y2 - 14 August 2022 through 18 August 2022

ER -

Yang C, Song H, Tang M, Danon L, Vigfusson Y. Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance. In KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM). 2022. p. 4733-4742. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/3534678.3542678

Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this