Surveillance of Disease Outbreaks Using Unsupervised Uni-Multivariate Anomaly Detection of Time-Series Symptoms
(2024) 34th Medical Informatics Europe Conference, MIE 2024 In Studies in Health Technology and Informatics 316. p.1916-1920- Abstract
Effectively identifying deviations in real-world medical time-series data is a critical endeavor, essential for early surveillance of disease outbreaks. This paper demonstrates the integration of time-series anomaly detection techniques to develop surveillance systems for disease outbreaks. Utilizing data from Sweden's telephone counseling service (1177), we first illustrate the trends in physical and mental symptoms recorded as contact reasons, offering valuable insights for outbreak detection. Subsequently, an advanced anomaly detection technique is applied incrementally to these time-series symptoms as univariate and multivariate approaches to assess the effectiveness of a machine learning-based method on early detection of the... (More)
Effectively identifying deviations in real-world medical time-series data is a critical endeavor, essential for early surveillance of disease outbreaks. This paper demonstrates the integration of time-series anomaly detection techniques to develop surveillance systems for disease outbreaks. Utilizing data from Sweden's telephone counseling service (1177), we first illustrate the trends in physical and mental symptoms recorded as contact reasons, offering valuable insights for outbreak detection. Subsequently, an advanced anomaly detection technique is applied incrementally to these time-series symptoms as univariate and multivariate approaches to assess the effectiveness of a machine learning-based method on early detection of the COVID-19 outbreak.
(Less)
- author
- Hashemi, Atiye Sadat LU ; Ghazani, Mirfarid Musavian LU ; Ohlsson, Mattias LU ; Björk, Jonas LU and Dietler, Dominik LU
- organization
-
- EPI@LUND (research group)
- Centre for Environmental and Climate Science (CEC)
- eSSENCE: The e-Science Collaboration
- LU Profile Area: Natural and Artificial Cognition
- Division of Occupational and Environmental Medicine, Lund University
- EpiHealth: Epidemiology for Health
- LU Profile Area: Nature-based future solutions
- publishing date
- 2024-08
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Anomaly detection, Anomaly transformer, COVID-19 pandemic, Incremental learning, Public health surveillance
- host publication
- Digital Health and Informatics Innovations for Sustainable Health Care Systems - Proceedings of MIE 2024
- series title
- Studies in Health Technology and Informatics
- editor
- Mantas, John ; Hasman, Arie ; Demiris, George ; Saranto, Kaija ; Marschollek, Michael ; Arvanitis, Theodoros N. ; Ognjanovic, Ivana ; Benis, Arriel ; Gallos, Parisis ; Zoulias, Emmanouil and Andrikopoulou, Elisavet
- volume
- 316
- pages
- 5 pages
- publisher
- IOS Press
- conference name
- 34th Medical Informatics Europe Conference, MIE 2024
- conference location
- Athens, Greece
- conference dates
- 2024-08-25 - 2024-08-29
- external identifiers
-
- pmid:39176866
- scopus:85202005899
- ISSN
- 0926-9630
- 1879-8365
- ISBN
- 9781643685335
- DOI
- 10.3233/SHTI240807
- project
- Improved preparedness for future pandemics and other health crises through large-scale disease surveillance
- Pandemic preparedness in the era of big data: Disease surveillance tools using individual-level register data and novel mobility data
- eSSENCE@LU 10:6 - Pandemic preparedness in the era of big data: Disease surveillance tools using individual-level register data and novel mobility data
- language
- English
- LU publication?
- yes
- id
- 936889b5-41a7-4afe-a229-4e8cb7e2caee
- date added to LUP
- 2024-10-28 13:33:59
- date last changed
- 2024-11-11 16:10:35
@inproceedings{936889b5-41a7-4afe-a229-4e8cb7e2caee, abstract = {{<p>Effectively identifying deviations in real-world medical time-series data is a critical endeavor, essential for early surveillance of disease outbreaks. This paper demonstrates the integration of time-series anomaly detection techniques to develop surveillance systems for disease outbreaks. Utilizing data from Sweden's telephone counseling service (1177), we first illustrate the trends in physical and mental symptoms recorded as contact reasons, offering valuable insights for outbreak detection. Subsequently, an advanced anomaly detection technique is applied incrementally to these time-series symptoms as univariate and multivariate approaches to assess the effectiveness of a machine learning-based method on early detection of the COVID-19 outbreak.</p>}}, author = {{Hashemi, Atiye Sadat and Ghazani, Mirfarid Musavian and Ohlsson, Mattias and Björk, Jonas and Dietler, Dominik}}, booktitle = {{Digital Health and Informatics Innovations for Sustainable Health Care Systems - Proceedings of MIE 2024}}, editor = {{Mantas, John and Hasman, Arie and Demiris, George and Saranto, Kaija and Marschollek, Michael and Arvanitis, Theodoros N. and Ognjanovic, Ivana and Benis, Arriel and Gallos, Parisis and Zoulias, Emmanouil and Andrikopoulou, Elisavet}}, isbn = {{9781643685335}}, issn = {{0926-9630}}, keywords = {{Anomaly detection; Anomaly transformer; COVID-19 pandemic; Incremental learning; Public health surveillance}}, language = {{eng}}, pages = {{1916--1920}}, publisher = {{IOS Press}}, series = {{Studies in Health Technology and Informatics}}, title = {{Surveillance of Disease Outbreaks Using Unsupervised Uni-Multivariate Anomaly Detection of Time-Series Symptoms}}, url = {{http://dx.doi.org/10.3233/SHTI240807}}, doi = {{10.3233/SHTI240807}}, volume = {{316}}, year = {{2024}}, }