A new method for assessing the risk of infectious disease outbreak

Liao, Yilan; Xu, Bing; Wang, Jinfeng; Liu, Xiaochi

doi:10.1038/srep40084

Cited by 37 publications

(33 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The expert knowledge method builds a network according to experts' comments and the results of literature reviews, while the network structure learning algorithm is based on the independence test proposed by Cheng and Greiner (1999). The network structure learning algorithm has three phases: drafting, thickening, and thinning (Liao et al 2017). In the first phase, the algorithm computes the mutual information of each pair of nodes as a measure of closeness, and it creates a draft based on this information.…”

Section: Building the Bbn Constructmentioning

confidence: 99%

Using a Bayesian belief network model for early warning of death and severe risk of HFMD in Hunan province, China

Liao

Liu

et al. 2018

Stoch Environ Res Risk Assess

Self Cite

View full text Add to dashboard Cite

Hand, foot, and mouth disease (HFMD) is a global infectious disease resulting in millions of cases and even hundreds of deaths. Although a newly developed formalin-inactivated EV71 (FI-EV71) vaccine is effective against EV71, which is a major pathogen for HFMD, no vaccine against HFMD itself has yet been developed. Therefore, establishing a sensitive and accurate early warning system for HFMD is important. The early warning model for HFMD in the China Infectious Disease Automated-alert and Response System combines control chart and spatial statistics models to detect spatiotemporal abnormal aggregations of morbidity. However, that type of early warning for HFMD just involves retrospective analysis. In this study, we apply a Bayesian belief network (BBN) to estimate the increased risk of death and severe HFMD in the next month based on pathogen detection and environmental factors. Hunan province, one of the regions with the highest prevalence of HFMD in China, was selected as the study area. The results showed that compared with the traditional early warning model for HFMD, the proposed method can achieve a very high performance evaluation (the average AUC tests were more than 0.92). The model is also simple and easy to operate. Once the structure of the BBN is established, the increased risk of death and severe HFMD in the next month can be estimated based on any one node in the BBN. Keywords Hand, foot, and mouth disease Á Early warning Á Spatiotemporal abnormal aggregation Á Moving percentile method Á Bayesian belief network

show abstract

Section: Building the Bbn Constructmentioning

confidence: 99%

Using a Bayesian belief network model for early warning of death and severe risk of HFMD in Hunan province, China

Liao

Liu

et al. 2018

Stoch Environ Res Risk Assess

Self Cite

View full text Add to dashboard Cite

show abstract

“…To our knowledge, no other study has been conducted on the performance of BODA. However, other algorithms using the Bayesian framework were used to detect outbreaks in various studies, most of which showed good performance (Garcia, Christen, & Capistran, 2015; Liao, Xu, Wang, & Liu, 2017; Texier et al., 2016, 2019). The BODA model has two advantages over traditional models, one using the Bayesian framework, which also uses the prior distribution to calculate the alarm threshold.…”

Section: Discussionmentioning

confidence: 99%

Performance of Bayesian outbreak detection algorithm in the syndromic surveillance of influenza‐like illness in small region

Aghaali

Kavousi

Shahsavani

et al. 2020

Transbound Emerg Dis

View full text Add to dashboard Cite

Early warning for Infectious disease outbreak is an important public health policy concern, and finding a reliable method for early warning remains one of the active fields for researchers. The purpose of this study was to evaluate the performance of the Bayesian outbreak detection algorithm in the surveillance of influenza‐like illness in small regions. The Bayesian outbreak detection algorithm (BODA) and modified cumulative sum control chart algorithm (CUSUM) were applied to daily counts of influenza‐like illness in Tehran, Iran. We used data from September 2016 through August 2017 to provide background counts for the algorithms, and data from September 2017 through August 2018 used for testing the algorithms. The performances of the BODA and modified CUSUM algorithms were compared with the results coming from experts' signal inspections. The data of syndromic surveillance of influenza‐like illness in Tehran had a median daily counts of 7 (IQR = 3–14). The data showed significant seasonal trends and holiday and day‐of‐the‐week effects. The utility of the BODA algorithm in real‐time detection of the influenza outbreak was better than the modified CUSUM algorithm. Moreover, the best performance was when a trend included in the analysis. The BODA algorithm was able to detect the influenza outbreaks with 4–5 days delay, with the least false‐positive alarm. Applying the BODA algorithm as an outbreak detection method in influenza‐like syndromic surveillance might be useful in early detection of the outbreaks in small regions.

show abstract

“…A number of studies related to machine learning modelling of infectious disease have been conducted on unsupervised analysis of several infectious diseases (PeterIdowu et al, 2013),measles outbreak prediction (Liao et al, 2017), dengue outbreak prediction (Rahmawati & Huang, 2016) and dengue infection risk (Fathima & Hundewale, 2012). Our prior work found that decision tree and Naive Bayes are among the techniques commonly used for disease risk prediction (Ahmad et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Handling Imbalanced Class Problem of Measles InfectionRisk Prediction Model

Ahmad

Ghani²,

Drus³

2019

IJEAT

View full text Add to dashboard Cite

Measles is an emerging infectious disease with increasing number of reported cases. It is a vaccine-preventable disease;thus, it is common to have imbalanced class problem in the dataset. This study aims to resolve the imbalanced class problem for the prediction of measles infection risk and to compare the predictive results on a balanced dataset based on three machine learningtechniques. The data that was utilized in this study contained 37,884 records of suspected measles casesthat were highly imbalanced towards negative measles cases. The Synthetic Minority Over-Sampling Technique (SMOTE) was performed to balance thedistribution of the target attribute. The balanced dataset was then modelled using logistic regression, decision tree and Naïve Bayes. The predicted results indicated that logistic regression executed on the balanced dataset by SMOTE has the highest and most accurateclassification with 94.5% overall accuracy, 93.9% true positive rate, 5.8% false positive rate and 5.1% false negative rate. Therefore, SMOTE and other over-sampling approaches may be applicable to overcome imbalanced class issues in the medical dataset.

show abstract

A new method for assessing the risk of infectious disease outbreak

Cited by 37 publications

References 31 publications

Using a Bayesian belief network model for early warning of death and severe risk of HFMD in Hunan province, China

Using a Bayesian belief network model for early warning of death and severe risk of HFMD in Hunan province, China

Performance of Bayesian outbreak detection algorithm in the syndromic surveillance of influenza‐like illness in small region

Handling Imbalanced Class Problem of Measles InfectionRisk Prediction Model

Contact Info

Product

Resources

About