EigenEvent: An algorithm for event detection from complex data streams in syndromic surveillance

  title={EigenEvent: An algorithm for event detection from complex data streams in syndromic surveillance},
  author={Hadi Fanaee-T and Jo{\~a}o Gama},
Syndromic surveillance systems continuously monitor multiple pre-diagnostic daily streams of indicators from different regions with the aim of early detection of disease outbreaks. The main objective of these systems is to detect outbreaks hours or days before the clinical and laboratory confirmation. The type of data that is being generated via these systems is usually multivariate and seasonal with spatial and temporal dimensions. The algorithm What's Strange About Recent Events (WSARE) is… 

Revisiting Non-Specific Syndromic Surveillance

This work revisits published approaches for non-specific syndromic surveillance and presents a set of simple statistical modeling techniques which can serve as benchmarks for more elaborate machine learning approaches.

A Unifying Framework and Comparative Evaluation of Statistical and Machine Learning Approaches to Non-Specific Syndromic Surveillance

This work gives an overview of non-specific syndromic surveillance from the perspective of machine learning and proposes a unified framework based on global and local modeling techniques which can serve as benchmarks for the more elaborate machine learning approaches.

Anomaly detection in spatiotemporal data via regularized non-negative tensor analysis

A novel technique to localize spatiotemporal anomalous events based on tensor decomposition and employs a spatial-feature-temporal tensor model and analyzes latent mobility patterns through unsupervised learning is proposed.

Algorithms, applications and systems towards interpretable pattern mining from multi-aspect data

This dissertation proposes the M^3 framework, which consists of multiplex pattern discovery, multifaceted pattern evaluation, and multipurpose pattern presentation, to tackle the challenges of multi- aspect pattern discovery and develops algorithms, applications, and analytic systems to enable interpretable pattern discovery from multi-aspect data.

Online Data-Driven Prediction of Spatio-Temporal System Behavior Using High-Fidelity Simulations and Sparse Sensor Measurements

A generic online data-driven approach for the prediction of spatio-temporal behavior of dynamical systems using their simulation data combined with sparse, noisy sensors measurement data and has a prediction accuracy that is relatively robust to the sensors’ locations.

Tracking System Behavior from Resource Usage Data

The core idea is to model the data as a three-way tensor corresponding to the compute nodes, usage metrics, and time, and use the reconstruction error between the original tensor and the tensor reconstructed from a low rank tensor decomposition, as a scalar performance metric.



What's Strange About Recent Events (WSARE): An Algorithm for the Early Detection of Disease Outbreaks

An early disease outbreak detection algorithm called What's Strange About Recent Events (WSARE), which uses a multivariate approach to improve its timeliness of detection and incorporates a wide range of ideas, including association rules, Bayesian networks, hypothesis testing and permutation tests.

Bayesian Network Anomaly Pattern Detection for Disease Outbreaks

The baseline method of (Wong et al., 2002) is replaced with a Bayesian network which produces the baseline distribution by taking the joint distribution of the data and conditioning on attributes that are responsible for the trends.

Statistical Challenges Facing Early Outbreak Detection in Biosurveillance

This work focuses mainly on the monitoring of time series to provide early alerts of anomalies to stimulate investigation of potential outbreaks, with a brief summary of methods to detect significant spatial and spatiotemporal case clusters.

Time series modeling for syndromic surveillance

The systematic methodology described here can be generalized to other healthcare settings to develop automated surveillance systems capable of detecting anomalies in disease patterns and healthcare utilization.

Simulating Multivariate Syndromic Time Series and Outbreak Signatures

A method for simulating multivariate Syndromic count data, in the form of daily counts from multiple syndromic series, and an outbreak simulator that generates multivariate signatures of artificial outbreaks of different nature, which can be embedded within the simulated data to evaluate detection algorithm performance.

A Bayesian spatio-temporal method for disease outbreak detection

Differences in the detection performance of PC and PCTS are examined and show that the spatio-temporal Bayesian approach performs well, relative to the non-spatial, non-tem temporal approach.

A Multi-level Spatial Clustering Algorithm for Detection of Disease Outbreaks

The MSC algorithm is computationally efficient and it is able to provide more precise and compact clusters in a timely manner while keeping high detection accuracy (cluster sensitivity) and low false alarm rates.

A monitoring system for detecting aberrations in public health surveillance reports.

A monitoring system incorporating statistical 'flags' identifying unusually large increases in disease reports compared to the number of cases expected is described, consisting of univariate Box-Jenkins models and subsequent tracking signals from several statistical process control charts.

Detection of Outbreaks from Time Series Data Using Wavelet Transform

In this paper, we developed a new approach to detection of disease outbreaks based on wavelet transform. It is capable of dealing with two problems found in real-world time series data, namely,

Detection of spatial and spatio-temporal clusters

A general and powerful statistical framework for the automatic detection of spatial and space-time clusters, currently used in daily practice by several state and local health departments, and can detect outbreaks significantly faster than previous disease surveillance methods.